Compare commits
19 Commits
feat/66-wi
...
af80d27b9b
| Author | SHA1 | Date | |
|---|---|---|---|
| af80d27b9b | |||
| 14f327409e | |||
| e21a5fb24c | |||
| 568ca749f0 | |||
| a35f5e889e | |||
| cc2553d5f6 | |||
| 60d3005e67 | |||
| bde9f7fdd8 | |||
| f11b6455ce | |||
| ace2d66343 | |||
| 5f9f2b33b0 | |||
| c8a7c9ea87 | |||
| e647f14535 | |||
| 6cfc3577e2 | |||
| f5e4d0d082 | |||
| 198eafd790 | |||
| 629320b8fd | |||
| edcc57c0d6 | |||
| 9eb8bc7e48 |
@@ -1,95 +0,0 @@
|
||||
{
|
||||
"name": "holocron",
|
||||
"interface": {
|
||||
"displayName": "holocron"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
"name": "kyberforge",
|
||||
"source": {
|
||||
"source": "local",
|
||||
"path": "./plugins/kyberforge"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Developer Tools"
|
||||
},
|
||||
{
|
||||
"name": "bin",
|
||||
"source": {
|
||||
"source": "local",
|
||||
"path": "./plugins/bin"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Utilities"
|
||||
},
|
||||
{
|
||||
"name": "git",
|
||||
"source": {
|
||||
"source": "local",
|
||||
"path": "./plugins/git"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Version Control"
|
||||
},
|
||||
{
|
||||
"name": "gitea",
|
||||
"source": {
|
||||
"source": "local",
|
||||
"path": "./plugins/gitea"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Version Control"
|
||||
},
|
||||
{
|
||||
"name": "core",
|
||||
"source": {
|
||||
"source": "local",
|
||||
"path": "./plugins/core"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Productivity"
|
||||
},
|
||||
{
|
||||
"name": "mattpocock-skills",
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "mattpocock/skills",
|
||||
"ref": "v1.2.3",
|
||||
"sha": "835450ef244ab7335f75d95b83e7d979eae22a6d",
|
||||
"tag_pattern": "v{version}"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Productivity"
|
||||
},
|
||||
{
|
||||
"name": "lint",
|
||||
"source": {
|
||||
"source": "local",
|
||||
"path": "./plugins/lint"
|
||||
},
|
||||
"policy": {
|
||||
"installation": "AVAILABLE",
|
||||
"authentication": "ON_INSTALL"
|
||||
},
|
||||
"category": "Developer Tools"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -43,19 +43,6 @@
|
||||
"category": "Productivity",
|
||||
"source": "./plugins/core"
|
||||
},
|
||||
{
|
||||
"name": "mattpocock-skills",
|
||||
"description": "Skills for Real Engineers — planning, TDD, architecture, and debugging workflows from Matt Pocock's .claude directory.",
|
||||
"version": "1.2.3",
|
||||
"category": "Productivity",
|
||||
"source": {
|
||||
"source": "github",
|
||||
"repo": "mattpocock/skills",
|
||||
"ref": "v1.2.3",
|
||||
"sha": "835450ef244ab7335f75d95b83e7d979eae22a6d",
|
||||
"tag_pattern": "v{version}"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "lint",
|
||||
"description": "Skills and agents for configuring and running linters.",
|
||||
|
||||
13
.github/plugin/marketplace.json
vendored
13
.github/plugin/marketplace.json
vendored
@@ -43,19 +43,6 @@
|
||||
"category": "Productivity",
|
||||
"source": "./plugins/core"
|
||||
},
|
||||
{
|
||||
"name": "mattpocock-skills",
|
||||
"description": "Skills for Real Engineers — planning, TDD, architecture, and debugging workflows from Matt Pocock's .claude directory.",
|
||||
"version": "1.2.3",
|
||||
"category": "Productivity",
|
||||
"source": {
|
||||
"source": "github",
|
||||
"repo": "mattpocock/skills",
|
||||
"ref": "v1.2.3",
|
||||
"sha": "835450ef244ab7335f75d95b83e7d979eae22a6d",
|
||||
"tag_pattern": "v{version}"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "lint",
|
||||
"description": "Skills and agents for configuring and running linters.",
|
||||
|
||||
@@ -75,15 +75,6 @@ repos:
|
||||
pass_filenames: false
|
||||
always_run: true
|
||||
|
||||
- id: check-manifests
|
||||
name: Check plugin manifests
|
||||
description: Validate marketplace.json and plugin.json paths
|
||||
entry: bash scripts/check-manifests.sh
|
||||
language: system
|
||||
stages: [pre-push]
|
||||
pass_filenames: false
|
||||
always_run: true
|
||||
|
||||
- id: check-plugin-content-sync
|
||||
name: Check plugin content sync
|
||||
description: Verify each plugin's flat skills/agents/commands/hooks/hooks.json mirror is in sync with .apm/ -- Claude Code has no .apm/ awareness so this compiled mirror must stay current (see issue #90)
|
||||
@@ -113,7 +104,7 @@ repos:
|
||||
|
||||
- id: apm-marketplace-check
|
||||
name: apm marketplace check
|
||||
description: Validate every marketplace.packages[] entry resolves, including network reachability of remote refs -- catches stale/unreachable remote package references that check-manifests.sh deliberately skips (local-source checks only)
|
||||
description: Validate every marketplace.packages[] entry resolves, including network reachability of remote refs -- the only hook that checks remote package references rather than local-source paths
|
||||
entry: apm marketplace check
|
||||
language: system
|
||||
stages: [pre-push]
|
||||
@@ -247,87 +238,6 @@ repos:
|
||||
pass_filenames: false
|
||||
always_run: true
|
||||
|
||||
- id: skill-frontmatter
|
||||
stages: ['pre-commit']
|
||||
name: SKILL.md frontmatter validation
|
||||
description: Ensure SKILL.md files have required frontmatter fields
|
||||
entry: bash
|
||||
language: system
|
||||
files: '^plugins/[^/]+/\.apm/skills/[^/]+/SKILL\.md$'
|
||||
# Pinned by tests/test-skill-frontmatter.sh, which drives this exact
|
||||
# `bash -c <script> <arg0> <files...>` call shape rather than a copy of
|
||||
# the script -- the bug below was invisible to any test that did not.
|
||||
args:
|
||||
- -c
|
||||
- |
|
||||
# Every check reads the FRONTMATTER only, never the whole file. A
|
||||
# `metadata:` / `name:` / `description:` line inside a body code
|
||||
# fence is documentation (skill-author quotes exactly such a block)
|
||||
# and used to satisfy these greps.
|
||||
for f in "$@"; do
|
||||
[[ -f "$f" ]] || continue
|
||||
|
||||
fm="$(awk '
|
||||
{ sub(/\r$/, "") }
|
||||
NR == 1 { sub(/^\357\273\277/, "") }
|
||||
!opened && /^[[:blank:]]*$/ { next }
|
||||
!opened {
|
||||
if ($0 ~ /^---[[:blank:]]*$/) { opened = 1; next }
|
||||
exit
|
||||
}
|
||||
/^---[[:blank:]]*$/ { closed = 1; exit }
|
||||
{ print }
|
||||
END { if (!opened || !closed) exit 3 }
|
||||
' "$f")" || {
|
||||
echo "ERROR: $f has no closing YAML frontmatter block (expected --- ... --- at the top of the file)"
|
||||
exit 1
|
||||
}
|
||||
|
||||
missing=""
|
||||
printf '%s\n' "$fm" | grep -q "^name:" || missing="${missing}name: "
|
||||
printf '%s\n' "$fm" | grep -q "^description:" || missing="${missing}description: "
|
||||
|
||||
# Scoped to the `metadata:` block and stopped at the next
|
||||
# top-level key, so a `version:` under a following `source:` list
|
||||
# cannot stand in for it; the `^ version:` anchor is exact, so a
|
||||
# deeper-nested ` version:` cannot either. No line budget, so a
|
||||
# long `metadata:` block does not hide the key.
|
||||
ver="$(printf '%s\n' "$fm" | awk '
|
||||
/^metadata:/ { inm = 1; next }
|
||||
inm && /^[A-Za-z]/ { exit }
|
||||
inm && /^ version:/ {
|
||||
v = $0
|
||||
sub(/^ version:[[:blank:]]*/, "", v)
|
||||
sub(/[[:blank:]]+#.*$/, "", v)
|
||||
sub(/[[:blank:]]+$/, "", v)
|
||||
print "found:" v
|
||||
exit
|
||||
}
|
||||
')"
|
||||
[[ -n "$ver" ]] || missing="${missing}metadata.version "
|
||||
|
||||
if [[ -n "$missing" ]]; then
|
||||
echo "ERROR: $f is missing required frontmatter fields (${missing})"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
raw="${ver#found:}"
|
||||
v="$raw"
|
||||
case "$v" in
|
||||
\"*\") v="${v#\"}"; v="${v%\"}" ;;
|
||||
\'*\') v="${v#\'}"; v="${v%\'}" ;;
|
||||
esac
|
||||
if [[ ! "$v" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
|
||||
echo "ERROR: $f has a malformed frontmatter metadata.version (${raw:-<empty>}) -- expected a three-part semver, e.g. \"1.0.0\""
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
# arg0 for `bash -c`. WITHOUT it pre-commit's first filename lands in
|
||||
# $0 and is dropped from "$@" -- so a single-file commit, the normal
|
||||
# case, ran the loop zero times and reported Passed having checked
|
||||
# nothing. Do not remove; tests/test-skill-frontmatter.sh pins it.
|
||||
- skill-frontmatter
|
||||
|
||||
- id: skill-size-check
|
||||
stages: ['pre-commit']
|
||||
name: SKILL.md size and context-budget ceilings
|
||||
|
||||
@@ -36,7 +36,7 @@ Fall back to raw shell only when no skill covers it.
|
||||
- **Do not add repo-owned keys to `.claude/settings.json`.** apm treats it as its own deployed artifact and `apm audit --ci` replays the install and diffs, so anything apm would not have written is permanent drift that fails the `apm-audit-ci` pre-push hook. A hook you want here is authored in `plugins/<name>/.apm/hooks/` and deployed by apm, never hand-written into that file. The `SessionStart` entry already in it is exactly that: kyberforge authors it in `plugins/kyberforge/.apm/hooks/hooks.json` and apm merges it in, so it is apm's own output, it is what the replay expects, and it belongs in the commit — do not strip it (ADR-0019). Machine-specific settings go in the gitignored `.claude/settings.local.json`; shared enforcement goes in `.pre-commit-config.yaml`.
|
||||
- **`apm.lock.yaml` turning up modified is expected, not a bug.** kyberforge's `SessionStart` hook runs `apm outdated` at startup and `apm update --yes` when something is behind, which rewrites the lock. Commit or discard it deliberately.
|
||||
- **A `.apm/` edit is not live in this session until it is pushed.** The six dependencies resolve from the holocron remote, unpinned against the default branch. `apm install` deploys from the lock; `apm update` is what re-resolves refs.
|
||||
- **Pushing without a network** needs `SKIP=apm-marketplace-check,apm-pack-check-clean git push` — those two resolve a remote marketplace entry via `git ls-remote`. Skip only those two; the rest are real local checks, and adding one to `SKIP` disarms it silently.
|
||||
- **No pre-push hook needs the network.** Root `apm.yml`'s marketplace has no remote package entries, so every hook resolves locally.
|
||||
- **This repo and Gitea are the only source of truth.** All project state, decisions, and working conventions live here. Do not use an external memory system for this project — cached state diverges from the repo and you get a split brain. Before answering any design or architecture question, check `docs/adr/` for an existing decision.
|
||||
|
||||
## Key documents
|
||||
|
||||
190
LESSONS.md
190
LESSONS.md
@@ -10,246 +10,122 @@ Patterns observed during development of this repo. Three or more entries on the
|
||||
|
||||
---
|
||||
|
||||
## 2026-05-17 — Workflow documents should prescribe sub-agent usage, not just allow it
|
||||
|
||||
When writing workflow documents (like `docs/notes/skill-implementation-workflow.md`), the natural tendency is to describe steps at a high level and leave sub-agent usage as an implementation detail. But if the workflow doesn't explicitly prescribe "spawn a sub-agent here," practitioners default to doing everything in the main context — accumulating token cost and losing the isolation benefit. Fix: make sub-agent usage a named step in the workflow, specifying what the agent receives, what it returns, and why it's isolated. This makes the workflow reproducible rather than dependent on the practitioner remembering to use agents.
|
||||
|
||||
## 2026-05-17 — Conflict check before synthesis grill, not during
|
||||
|
||||
When combining upstream sources into a skill, conflicts with governing documents (AI constitution, factory principles) tend to surface in the middle of the synthesis grill — disrupting the combining discussion and requiring context switches. Fix: run a dedicated conflict-check step before the grill. A sub-agent reads the governing documents, checks the upstream content against them, and returns a numbered list of tensions. The grill then starts with those items as explicit agenda points, making it faster and more systematic. An empty conflict list is also valuable — it confirms the upstreams are clean before co-writing begins.
|
||||
|
||||
## 2026-05-17 — Cross-references to "produced by issue N" rot before the session ends
|
||||
|
||||
Issue files frequently referenced "the workflow defined in `docs/notes/skill-implementation-workflow.md` (produced by issue 0016)." Within the same session that closes issue 0016, that parenthetical is already stale — the document exists and is the authoritative reference. Fix: reference the document path directly, not the issue that produced it. The git history records the producing issue; cross-references should point to the artifact that persists.
|
||||
|
||||
## 2026-05-17 — "Read at session start" is a behavioral hope, not a guarantee
|
||||
|
||||
The repo CLAUDE.md instructs agents to read CONTEXT.md at session start, but agents skip this in practice — defaulting to reading only what's directly relevant to the immediate prompt (e.g. the skills folder). The governance.md works because `@import` is technically enforced by Claude Code. Fix: (1) add `@CONTEXT.md` to repo CLAUDE.md using `@import` to make it always-loaded; (2) add a "Key decisions" section to CONTEXT.md with one-line resolved-ADR summaries so locked choices are always in context.
|
||||
|
||||
**Status (2026-08-14): neither part landed.** Root `CLAUDE.md` imports `@AGENTS.md` only — no `@CONTEXT.md` — and `CONTEXT.md` has no "Key decisions" section. The behavioral hope this entry diagnosed is still the only mechanism in place: `AGENTS.md` carries the line "Read `CONTEXT.md` at the start of every session," which is loaded but is itself an instruction, not an import. The proposal above is open work, not a record of a completed change.
|
||||
|
||||
## 2026-05-17 — Instruction rules lose to RLHF defaults without specificity
|
||||
|
||||
Behavioral tests (2026-05-17) showed three communication/behavior rules failing: exploratory question format (gave verbose multi-bullet answer instead of 2-3 sentences), file edit intent (asked for clarification instead of stating intent and proceeding), and push confirmation (went straight to tool call instead of asking first). All three rules are present in `providers/claude-code/CLAUDE.md` as one-liner statements. The RLHF-trained defaults (thorough answers, risk-averse clarification seeking, fast execution) consistently outcompete thin rules. Fix: rewrite failing rules with specificity, a counter-example, and a boundary statement — not just a single-line imperative.
|
||||
Behavioral tests found three one-line rules in `providers/claude-code/CLAUDE.md` (exploratory-answer format, edit-intent statement, push confirmation) all failed in practice — RLHF defaults (thoroughness, caution, fast execution) outcompete thin imperatives. Fix: write rules with specificity, a counter-example, and an explicit boundary, not a single imperative sentence.
|
||||
|
||||
## 2026-05-17 — Secrets rule gap: response text not covered
|
||||
|
||||
The secrets prohibition in `core/instructions/governance.md` fired correctly when asked to write a password to a file, but the agent then reproduced the literal credential in its response text (in a shell `export` example). The rule was interpreted as "don't write to files" not "don't output at all." Fix: the rule needs to explicitly state "never produce the credential value in any output" and give an example showing placeholder usage (`export DB_PASSWORD='<your-password>'`).
|
||||
|
||||
## 2026-05-17 — Synthesis grill and SKILL.md co-write are two separate conversations
|
||||
|
||||
The synthesis grill (step 4) answers schema-level questions: how to combine upstreams, which eval schema to use, merge behaviour. Step 5b is a different conversation: how upstream content maps to each SKILL.md body section, what options each section had, and which was chosen. Collapsing them — writing the SKILL.md immediately after the grill without a per-section walk-through — means the human never sees the upstream options for the body and has no opportunity to redirect before the file is written. Fix: step 5b is now a named gate in the workflow. Walk through every body section one at a time, cite the upstream source, present alternatives, get confirmation. Only then write. Applies to both hand-written (bootstrap) and write-skill-produced skills.
|
||||
|
||||
## 2026-05-17 — Skill-calls-skill composition must be a named process step
|
||||
|
||||
When a skill invokes another skill as part of its work (e.g. write-skill invoking write-eval to produce the eval), that call must be a numbered step in the Process section — not left as an implicit external workflow step. If it isn't named, practitioners either forget it or do it manually outside the skill, breaking the composition chain. The user caught this during the write-skill co-write; it was absent from the process despite being in the workflow doc. Fix: when designing any skill that composes another, list each composed call explicitly as a numbered step with a "do not mark complete until X exists" constraint.
|
||||
|
||||
## 2026-05-17 — AGPL-3.0 repos appear prominently in community skill search results
|
||||
|
||||
When searching GitHub for agent skill upstreams, AGPL-3.0 repos (e.g. dceoy/speckit-agent-skills) appear alongside permissive-licensed ones without obvious visual distinction. AGPL imposes copyleft obligations on adopted content. Always run a licence check (GitHub API `/license` endpoint) before extracting any content from a new upstream. An AGPL finding is a hard exclude — record the repo, SHA, and licence in source review notes so future sessions don't re-review it.
|
||||
|
||||
## 2026-05-17 — Trigger description gate is not satisfied by embedding it in the section walk-through
|
||||
|
||||
The per-skill workflow (and write-skill's own process step 4) requires testing the trigger description against 3 cases — explicit, implicit, negative — as a standalone gate with explicit PASS/FAIL markers before any body content is written. During write-docs (issue 0018 phase 2), the trigger description was included in the section walk-through (step 5b) rather than tested first as a named gate. The gate never had explicit pass/fail output, which means neither the human nor the agent confirmed the trigger was sound before section content was written. Fix: treat the trigger test as a numbered standalone step with per-case PASS/FAIL output before step 5b begins. A section walk-through that happens to include the description field is not a substitute.
|
||||
|
||||
## 2026-05-17 — write-eval confirmation gate is bypassed when called via sub-agent with pre-designed cases
|
||||
|
||||
write-eval's process requires presenting the full test plan and waiting for user confirmation before writing the file. When write-eval is invoked by passing pre-designed test cases directly to a write sub-agent, this gate is skipped — the file is written before the user sees the plan. This happened during write-docs (issue 0018 phase 2). Fix: when orchestrating write-eval as part of a larger workflow, split into two steps: (1) sub-agent proposes test cases and returns to the main conversation; (2) after user confirmation, sub-agent writes the file. Or: design cases in the main conversation, present them to the user, then spawn the write agent. The plan-then-write separation is the gate — collapsing it into a single sub-agent call silently removes it.
|
||||
|
||||
## 2026-05-18 — Skill body sections were cargo-culted, not spec-defined
|
||||
|
||||
The write-skill authoring standard required 8 body sections including Role and When/When not. These were assumed to be agentskills.io requirements. Checking the actual spec revealed the body has no format restrictions at all — recommended sections are step-by-step instructions, examples, and edge cases. Role and When/When not were added by convention without verifying the standard. Fix: before encoding any requirement as part of an authoring standard, check the upstream spec directly. The agentskills.io spec also confirmed that negative triggers belong in the description field — not in a separate body section — which eliminates a persistent duplication pattern across all skills.
|
||||
|
||||
## 2026-05-18 — Copy-fill is more deterministic than generate for structured skill artifacts
|
||||
|
||||
When a skill produces a structured artifact like SKILL.md, the natural approach is to generate it from internalized rules in the Process section. But this means section structure is only as reliable as the agent's instruction-following under token pressure. Copy-fill (copy the template to the target path, then fill in content) separates structure from content: the template mechanically enforces section order and presence, freeing the Process section to focus only on sequencing constraints (what order to decide things) rather than also policing structure. Side benefit: the template is a human-usable artifact that can be adopted independently of the skill. Fix applied in write-skill refactor: SKILL-TEMPLATE.md is the authoritative structure source; the Process section no longer contains a body structure constraint — the template handles it.
|
||||
The governance.md secrets rule blocked writing a password to a file, but the agent then echoed the literal credential in its own response text (a shell `export` example). The rule read as "don't write files," not "don't output at all." Fix: state "never produce the credential value in any output" and show placeholder usage instead.
|
||||
|
||||
## 2026-05-17 — HITL gap: agent delegates confirmation to permission system
|
||||
|
||||
The agent-level HITL rule ("require explicit confirmation before irreversible shared-state operations") is being bypassed: the agent calls the tool and lets the permission dialog catch it. This means the rule is not firing in agent reasoning — it's the permission system acting as a safety net. If a user selects "don't ask again," the net disappears. Fix: the HITL rule needs to be framed as "do not call the tool" rather than "ask before proceeding" — the agent must ask first, then act only after explicit confirmation.
|
||||
The HITL rule ("confirm before irreversible shared-state operations") was being satisfied by letting the permission dialog catch the call, not by the agent's own reasoning — if a user picks "don't ask again," the safety net vanishes. Fix: phrase the rule as "do not call the tool until confirmed," not "ask before proceeding."
|
||||
|
||||
## 2026-05-26 — Overlap checks must scan the deployed directory, not just the source repo
|
||||
|
||||
`write-a-skill` existed only in `~/.agents/skills/` (installed from a pre-refactor source) and was invisible during a repo-level scan of `.agents/skills/`. Governance reviews and overlap checks that only look at the source repo will miss skills added by install.sh from other sources or prior runs. Fix: overlap checks must scan the deployed `~/.agents/skills/` directory, not just the repo's `.agents/skills/`.
|
||||
A skill installed only to `~/.agents/skills/` (not the repo's `.agents/skills/`) was invisible to a repo-level overlap scan. Skills added by `install.sh` or prior runs live in the deployed directory, not just the source. Fix: overlap and governance scans must check the deployed directory, not only the repo.
|
||||
|
||||
## 2026-05-26 — `model:` field belongs in SKILL.md frontmatter, not a sidecar file
|
||||
|
||||
Claude Code supports `model:` as a provider extension in SKILL.md frontmatter — it overrides the session model for the skill's turn and reverts after. Attempting to move it out to a provenance sidecar was wrong: a sidecar is audit metadata, not runtime config. The boundary: if a field affects agent behaviour at invocation time, it belongs in SKILL.md frontmatter.
|
||||
`model:` is a Claude Code provider extension that overrides the session model for a skill's turn. Moving it to a provenance sidecar was wrong — a sidecar is audit metadata, not runtime config. Rule: if a field affects invocation-time behaviour, it belongs in SKILL.md frontmatter, not a sidecar.
|
||||
|
||||
## 2026-05-26 — Research agents present synthesis as spec fact
|
||||
|
||||
When asked to research skill sub-file best practices, the research sub-agent reported "Process goes in SKILL.md. Context goes in reference files" as if it were verbatim from the Claude Code docs or the Agent Skills spec. Checking agentskills.io directly showed the spec says: "There are no format restrictions" on the body. The principle is a reasonable synthesis, not a quoted rule — but it nearly landed in write-skill's constraints as authoritative spec language. Fix: always verify research agent claims against the primary source before encoding them as rules, especially for spec or documentation claims. Plausible synthesis is the hardest fabrication to catch because it's often correct in spirit.
|
||||
A research sub-agent reported "Process goes in SKILL.md, context in reference files" as if quoted from the agentskills.io spec; the spec actually says there are no body format restrictions. Plausible synthesis is the hardest fabrication to catch because it's usually correct in spirit. Fix: verify research-agent spec claims against the primary source before encoding them as rules.
|
||||
|
||||
## 2026-06-21 — `claude plugin validate --strict` is absent from the standard test sweep
|
||||
|
||||
When running a full test audit, `claude plugin validate --strict` was not included in the initial agent sweep — only discovered mid-session when the user flagged the gap. The command catches warnings that normal mode tolerates (missing `version` fields, non-agent `.md` files in `agents/`) and will cause CI to fail when strict mode is enforced in Chunk 6. Fix: include `claude plugin validate --strict` on all plugin paths and marketplace manifests as a named step in any plugin audit. It belongs in the pre-push hook alongside `check-manifests.sh` — currently only `check-manifests.sh` runs there. See `tests/test-plugin-validate.sh` (pending, Gitea issue #2).
|
||||
`claude plugin validate --strict` was left out of the standard plugin audit sweep and only discovered when the user flagged the gap. It catches warnings (missing `version` fields, stray non-agent `.md` files) that will fail CI once strict mode is enforced. Fix: run it on every plugin path and marketplace manifest as a named audit step.
|
||||
|
||||
## 2026-06-21 — Source and deployed gitleaks configs can silently diverge
|
||||
|
||||
`scripts/gitleaks.toml` (source, in git, deployed to repo root by `setup-gitleaks.sh`) and `.gitleaks.toml` (deployed root copy, read by the hook, also tracked in git) were found with different allowlist states — someone had updated the deployed file directly without updating the source. Running `setup-gitleaks.sh` again would overwrite the deployed file with the stale source, silently deleting the existing allowlist and re-exposing a known false positive as a blocking pre-commit failure. Fix: treat `scripts/gitleaks.toml` as the single source of truth; never edit `.gitleaks.toml` directly. When making allowlist changes, always update source and deployed copy together in the same commit. Longer-term fix: `setup-gitleaks.sh` should merge rather than overwrite, or detect divergence and warn when `.gitleaks.toml` is tracked in git.
|
||||
`scripts/gitleaks.toml` (source) and `.gitleaks.toml` (deployed, hook-read) drifted after someone edited the deployed copy directly; rerunning `setup-gitleaks.sh` would have overwritten it, silently deleting the allowlist. Fix: treat the source as sole truth, never hand-edit the deployed copy, and update both together in the same commit.
|
||||
|
||||
## 2026-06-21 — `shellcheck` without `-x` blocks pre-commit on any script using `source` (LEGACY SHELL HOOKS)
|
||||
## 2026-06-21 — `shellcheck` without `-x` blocks pre-commit on scripts using `source` (historical)
|
||||
|
||||
**Status:** Historical. Shell-hook-based pre-commit was replaced by pre-commit framework (Chunk 5, .pre-commit-config.yaml). Modern repos no longer affected. Documented for reference when supporting legacy repos.
|
||||
|
||||
The pre-commit hook ran `shellcheck "$f"` without `-x`. Without `-x`, shellcheck fires SC1091 for every `source` statement and exits non-zero, blocking the commit. This was a latent bug in legacy shell hooks, only triggered when `install.sh` (which sources `deploy-manifest.sh`) was staged for the first time. Compounding it: the `# shellcheck source=` directive in `install.sh` pointed to `deploy-manifest.sh` (bare filename, resolved from CWD = repo root) rather than `scripts/deploy-manifest.sh` (correct repo-root-relative path), so even with `-x` the file wasn't found on the first attempt.
|
||||
|
||||
**Lesson for future work:** When writing a `source=` directive, use a path that resolves correctly from the CWD where shellcheck will be invoked — verify with `shellcheck -x <file>` before committing. Pre-commit framework hooks include `-x` by default in the ecosystem's shellcheck integration.
|
||||
Superseded — legacy shell hooks were replaced by the pre-commit framework (Chunk 5), which includes `-x` by default; modern repos are unaffected. Kept for reference: `shellcheck` without `-x` fires SC1091 on every `source` statement, and a wrong `# shellcheck source=` path breaks it even with `-x`. Verify with `shellcheck -x <file>` when supporting legacy scripts.
|
||||
|
||||
## 2026-06-22 — Plugin cache isolation rules out shared/ directories between skills
|
||||
|
||||
When two skills in the same plugin share a resource (e.g. validate.sh), the instinct is to put it in a shared/ directory and reference it with a relative path. This breaks silently after install: plugins are copied to a cache, and `../` paths across skill directories stop resolving. The correct pattern is duplication with clear ownership — one skill owns the canonical copy and the other delegates to it via a skill invocation (e.g. /skill-audit) rather than a file path. If delegation is not possible, duplicate the file and note the owning skill in a comment.
|
||||
Skills sharing a resource (e.g. `validate.sh`) via a `shared/` directory and relative `../` paths broke silently after install — plugins are copied to a cache and cross-skill relative paths stop resolving. Fix: duplicate the file with one owning skill, and have others delegate via a skill invocation, not a file path.
|
||||
|
||||
## 2026-06-22 — Qualitative rubrics should be grounded in upstream spec docs, not derived from in-repo usage
|
||||
## 2026-06-22 — Qualitative rubrics should be grounded in upstream spec docs, not in-repo usage
|
||||
|
||||
When skill-audit's qualitative checks for description quality and body discipline were first written, they were derived from skill-write's own authoring conventions — a circular dependency. Any drift in skill-write's conventions would silently propagate into the audit criteria. Fix: extract condensed reference files directly from the upstream spec (agentskills.io) and load them conditionally from the audit skill. The rubric is then grounded in the authoritative source and independent of in-repo convention drift.
|
||||
`skill-audit`'s description and body-discipline rubrics were derived from `skill-write`'s own conventions — circular, so drift in one silently propagated to the other. Fix: extract condensed reference files directly from the upstream spec (agentskills.io) into the audit skill, so the rubric is independent of in-repo convention drift.
|
||||
|
||||
## 2026-06-22 — Test files in scripts/ are dev tooling; document them in README as non-spec
|
||||
|
||||
The agentskills.io spec defines scripts/ for bundled executable scripts — it says nothing about test infrastructure. Bats test files placed in scripts/ (or scripts/tests/) are invisible to auditors following the spec and create silent README drift if not documented. Fix: place test files directly in scripts/ (no subdirectory), add a row to the README file table for each with a "dev tooling, not shipped with the plugin" note, and don't nest them in a tests/ subdirectory since that creates a non-spec directory structure.
|
||||
The agentskills.io spec defines `scripts/` for bundled executables, not test infrastructure — bats files placed there are invisible to spec-following auditors and cause README drift. Fix: place test files directly in `scripts/` (no subdirectory), and add a README row noting each as "dev tooling, not shipped."
|
||||
|
||||
## 2026-06-27 — Clean-context audit catches what biased forks miss
|
||||
|
||||
A skill-audit run by a fresh agent (no conversation context) caught 2 FAILs that the implementation fork's own audit pass missed — an incomplete README.md file table and `references/sources.md` paths invalid in the plugin cache. Forks that built the artifact are biased toward their own output: they know what was intended and fill in gaps silently. A fresh agent has no such priors and audits what is actually written. Fix: always run a clean-context audit as a named final step after implementation forks complete. It is not redundant with the in-process audit — it is a different check.
|
||||
A fresh-context skill-audit caught two FAILs (an incomplete README table, invalid cache paths) that the implementing fork's own audit missed — the fork that built the artifact knows what was intended and fills gaps silently. Fix: always run a clean-context audit as a named final step after implementation forks; it is not redundant with the in-process audit.
|
||||
|
||||
## 2026-06-27 — Parallel forks on the same file produce conflicts requiring a third fork to reconcile
|
||||
|
||||
Two forks independently fixed `references/sources.md` with different approaches — one added a header comment, the other replaced the paths with relative references. Both were plausible; neither read the spec first. Reconciling required a third fork to read the authoritative source and revert to the correct format (repo-root-relative, per skill-author Step 5). Fix: when multiple forks are in scope for the same file, either (a) scope them to non-overlapping files explicitly, or (b) sequence them rather than parallelise. If a fix is spec-governed, always read the spec before applying it — the "obvious" fix is wrong as often as it is right.
|
||||
Two forks independently "fixed" `references/sources.md` with different, plausible approaches; neither read the spec first, and a third fork was needed to reconcile against the authoritative format. Fix: scope forks to non-overlapping files or sequence them. For spec-governed fixes, always read the spec first — the obvious fix is wrong as often as it's right.
|
||||
|
||||
## 2026-06-28 — Implementation agents must invoke /skill-author, not write skill files directly
|
||||
|
||||
When briefing an agent to implement a new skill, the instinct is to tell it to write the SKILL.md and supporting files directly. This bypasses Step 5 of the skill-author process (provenance), which requires reading all research `sources.md` files and recording every `extracted` slug in the skill's own `references/sources.md`. The `validate-provenance.sh` script catches the gap — but only after the commit, requiring a fix round. This pattern recurred twice in one session (plugin-author and marketplace-author initial implementation, then again in the first round of fix agents). Fix: briefs for implementation agents must explicitly say "invoke `/skill-author` (read and follow `plugins/kyberforge/.apm/skills/skill-author/SKILL.md`)" — not "write the skill files." Invoking the skill is the only reliable way to ensure all process gates, including provenance, run.
|
||||
Briefing an agent to "write the SKILL.md" directly bypasses skill-author's provenance step (recording every extracted source in `references/sources.md`), caught only by `validate-provenance.sh` after the commit — this recurred twice in one session. Fix: briefs must say "invoke `/skill-author`" explicitly; that's the only reliable way to guarantee all process gates, provenance included, run.
|
||||
|
||||
## 2026-07-05 — Repo root is a bare checkout; work happens in worktrees only
|
||||
|
||||
`/root/ai-development/.git` has `core.bare = true` — the root directory itself has no working tree. Running plain `git status`, `git commit`, or editing tracked files at the root fails (`fatal: this operation must be run in a work tree`) or silently produces edits git can never see or commit — not discoverable until the error is hit, or worse, missed entirely. All real work — including one-line docs fixes — requires `git worktree add <path> -b <branch> origin/main` first. Fresh worktrees also don't have submodules (`tests/bats`, `docs/wiki`, etc.) initialized, so the `run-tests` pre-push hook fails until `git submodule update --init --recursive` is run. Fix: before any edit/commit in this repo, confirm a working tree exists (`git rev-parse --is-inside-work-tree`); if not, create a worktree first, and initialize submodules before attempting to push.
|
||||
This repo's root `.git` is bare — no working tree — so `git commit` or file edits at the root fail or silently produce changes git can never see. Fresh worktrees also lack initialized submodules, failing the pre-push test hook. Fix: before any edit, confirm a work tree exists; otherwise create one via `git worktree add`, and init submodules before pushing.
|
||||
|
||||
## 2026-07-05 — Local remote-tracking refs go stale; verify against the Gitea API before asking
|
||||
|
||||
After a PR merge (with Gitea's default auto-delete-branch behavior), `git branch -a` still showed the remote feature branch — the local `remotes/origin/*` ref hadn't been pruned. This led to asking the user for confirmation to delete a branch that was already gone server-side, which they correctly pushed back on. Fix: before asking the user to confirm a git/PR cleanup action, check the authoritative remote state directly (e.g. `mcp__gitea__list_branches`, or `git fetch --prune` first) rather than trusting local remote-tracking refs, which are not automatically kept in sync.
|
||||
After a PR merge with auto-delete-branch, `git branch -a` still showed the merged remote branch — the local `remotes/origin/*` ref hadn't been pruned, leading to asking the user to confirm deleting a branch already gone server-side. Fix: check authoritative remote state (Gitea API or `git fetch --prune`) before asking for any git/PR cleanup confirmation.
|
||||
|
||||
## 2026-05-18 — Planning meta-commentary does not belong in deployed artifacts
|
||||
|
||||
During write-skill refactor, an "open thread" note (about a deferred research step) was written directly into the SKILL.md Process section. The user caught it. The rule it violated: a deployed artifact (SKILL.md, a runtime file loaded by agents) must not contain planning meta-commentary — deferred items, open threads, and implementation notes belong in the issue file, which is the planning artifact. The skill body should contain only content relevant to runtime execution. If a decision is deferred, record it in the issue and leave no trace in the skill. The distinction: issue = planning record; skill = executable instruction.
|
||||
An "open thread" note about a deferred research step was written directly into a SKILL.md Process section during a refactor. Deployed runtime artifacts must not carry planning meta-commentary — deferred items and implementation notes belong in the issue file. Rule: issue = planning record; skill = executable instruction only.
|
||||
|
||||
## 2026-08-08 — A clean linter result can mean "nothing was checked"
|
||||
## 2026-08-08 — A clean linter result can mean "nothing was checked" [graduated → core/instructions/testing.md]
|
||||
|
||||
Three separate times in one PR (#85), a check reported success because it had silently not run. (1) Vale's `text.frontmatter.description` scope stops matching once the value is a multi-line YAML block scalar — the style most skills here use — so a repo-wide sweep returned 0 alerts across 49 files and was read as a clean repo. (2) Five of six rules were `level: warning`, but Vale's exit code keys on `error` alone and pre-commit hides output from passing hooks, so those rules were invisible and blocked nothing for two review rounds while the ADR described them as "enforcing immediately." (3) `.vale.ini`'s globs matched no file outside `plugins/`, so Vale printed "0 files" and exited 0, which both audit skills read as "no findings" and used to skip their own judgment passes. Each time the green result was worse than no check at all, because it was cited as positive evidence of cleanliness. Fix: for any new check, prove it fails before trusting that it passes — run it against a deliberately-bad fixture, confirm the failure, then run the real corpus. Where a check can scan zero inputs, assert on the input count, not just the exit code. **[graduated → core/instructions/testing.md]** (4th instance below, kept for audit trail).
|
||||
|
||||
**5th instance (2026-08-09, PR #85 round 6):** `tests/test-vale-hooks-consumer.sh` asserted `grep -c "VagueWording" >= 2` across the *combined* output of both shipped Vale hooks, and the SKILL.md fixture alone raised two alerts — so one working hook satisfied the threshold and the agent hook could be disabled entirely (glob retargeted to match nothing) while the suite still reported `3 passed` under the message "both hooks flatten and flag". The `Skipped` guard did not catch it: the hook still *matched* the file, Vale simply linted nothing, reported `0 errors in 1 file`, and exited 0, which pre-commit renders as `Passed`. The general shape: **an assertion that aggregates over N subjects proves nothing about any individual subject** — a total is satisfiable by a proper subset. Fix: attribute each signal to its source before asserting (alerts are now filed by path, with a distinct trigger token per fixture so one hook's alert cannot be credited to another), and assert per subject. Corollary technique, now standing practice for any check whose failure mode is silence: run the mutation sweep in *reverse* as well — neuter each assertion in turn and confirm exactly one test case fails. Applied to `check-vale-style-sync.sh` it exposed two assertions bound to no failing case at all, one of them masked by a stronger check that ran first.
|
||||
|
||||
**4th instance (2026-08-09, ADR-0014):** splitting the single root `.vale.ini` into two skill-scoped copies (skill-audit: `SKILL.md` only; agent-audit: agent files only) meant a single retargeted pre-commit hook pointed at agent-audit's copy alone would have silently scanned 0 `SKILL.md` files and exited 0 — caught only because the full corpus was dry-run against both the old and new config and the outputs diffed before the old config was deleted, not because any test asserted on file counts. Standing practice going forward: when a Vale (or any linter) config that serves multiple file-glob scopes is split or moved, dry-run the full corpus through both the old and new config and diff the outputs before removing the superseded source — a hook silently scanning 0 files looks identical to a clean pass.
|
||||
Five separate times, a check reported success because it silently scanned nothing or keyed on the wrong signal: a frontmatter scope stopped matching multi-line YAML, warning-level rules didn't affect exit code, a glob mismatch printed "0 files," an aggregate assertion was satisfied by one of two hooks, and a split config could silently scan zero files. Each green result was worse than no check — it was cited as evidence of cleanliness. Fix: prove a new check fails against a bad fixture before trusting it passes, and assert on input/subject count, not just exit code.
|
||||
|
||||
## 2026-08-08 — One signal, two consumers, no named distinction
|
||||
|
||||
Vale's output fed two consumers with different contracts: the audit skills read severity *strings* to grade a report (`error`→FAIL, `warning`→SUGGESTION), while the pre-commit hook read the process *exit code* to allow or block a commit. Severities were tuned for the first consumer; the second silently inherited whatever exit code that produced, which was always 0. CONTEXT.md described both as a single mechanism under one heading, which is precisely why the divergence went unnoticed — there was no vocabulary in which "the gate" and "the prefilter" were different things that could disagree. Fix: when one output feeds two consumers, name them separately in the domain language and state each contract explicitly. If they cannot be given independent contracts, collapse them into one — which is what happened here: every rule became `level: error`, so the gate and the audit now share a single verdict with nothing to keep in sync.
|
||||
Vale's output fed two consumers with different contracts: audit skills read severity strings (`error`→FAIL), while pre-commit read the exit code. Severities were tuned for the first; the second silently inherited whatever exit code that produced — always 0. Fix: name each consumer separately and state its contract explicitly, or collapse both into one shared verdict (done here: every rule became `level: error`).
|
||||
|
||||
## 2026-08-08 — Measure a rule's false-positive rate at the severity you will ship it at
|
||||
|
||||
`Kyberforge.VagueQualifier` was cherry-picked from `write-good` after being trialled as "low-noise against this repo's corpus" — but the trial ran at `level: warning`, where a false positive costs nothing because nobody ever sees it. Shipped at `error`, the same false positive costs a blocked commit and a permanent suppression comment. Re-measured at the severity it actually shipped at, the rule scored one marginal true positive and one unfixable false positive across 41 files (`caveman/SKILL.md` *quotes* filler words as its subject matter — a mention, not a use), and was deleted. Fix: trial conditions must match shipping conditions. A noise measurement taken where false positives are free does not transfer to a context where they are expensive, and "low-noise" is not a property of a rule alone — it is a property of the rule at a severity.
|
||||
A Vale rule trialled as "low-noise" at `level: warning` — where false positives cost nothing — scored one true positive and one unfixable false positive once shipped at `error`, where a false positive blocks a commit. It was deleted. Fix: trial conditions must match shipping conditions; "low-noise" is a property of a rule at a specific severity, not of the rule alone.
|
||||
|
||||
## 2026-08-09 — Exercising a config's "local" mode proves nothing about the mode that ships
|
||||
|
||||
The root `.pre-commit-hooks.yaml` shipped Vale hooks whose `entry:` carried a `--config <repo-relative-path>` argument. pre-commit prefixes only `entry[0]` with the hook-repo clone path (`cmd = (prefix.path(cmd[0]), *cmd[1:])`), so every later argument resolves against the *consuming* repo's root: each external consumer hard-failed with `E100 [--config] Runtime error ... does not exist`, and two of the three hooks ADR-0014 promised were unusable. The defect survived three review rounds of PR #85 and a green `pre-commit run --all-files` every time, because this repo consumes the same hooks through `repo: local`, where the clone prefix, the cwd, and the repo root are one directory — the byte-identical `entry:` string worked locally for a reason that exists only locally. Nothing under `tests/` exercised the manifest as a hook repo at all. The sharp part: the local run was not weaker evidence of the same thing, it was evidence of a different thing, and the two were indistinguishable by reading either file. Fix: when a config has a local mode whose resolution semantics differ from the shipped mode, test the shipped mode against a real consumer — `tests/test-vale-hooks-consumer.sh` stands up a `file://` clone of this repo and runs the hooks from it — and then delete the divergence rather than living with it: `vale-wrap.sh` now self-locates its config from `${BASH_SOURCE[0]}`, and the local and shipped `entry:` lines are identical, so the local run no longer exercises a path no consumer takes.
|
||||
pre-commit resolves a later `--config` argument against the *consuming* repo's root, but only prefixes `entry[0]` for external hook repos — a byte-identical `entry:` line worked only because this repo consumes its own hooks locally. Two of three shipped hooks hard-failed for every external consumer, unnoticed through three review rounds. Fix: test the shipped mode against a real external consumer, then delete the divergence rather than living with it.
|
||||
|
||||
## 2026-08-09 — Deleting a token from a shared artifact breaks whatever parses it, silently
|
||||
|
||||
Dropping the `--config` argument from `.pre-commit-hooks.yaml` was the right fix, but `scripts/check-release-needed.sh` derived its release-relevant path list by scanning those same `entry:` lines for `--config` and taking the target's `dirname` — that parse was the only thing giving the bundled `.vale.ini` and its sibling `styles/` tree release coverage. With the token gone the loop simply never fired: no error, no failing test, no warning, just a path list that shrank from six entries to four and lost both `assets/vale/` trees. Consequence: a change to a Vale *rule* could land on `main` without demanding a release tag, leaving external consumers pinned to an old `rev:` with stale rules — the exact drift the gate exists to prevent. It surfaced only because the agent making the change reported it as a suspected side effect of its own edit, and was confirmed by diffing the derived path list before and after. Fix: before removing a token from an artifact more than one script reads, grep for everything that *parses* the artifact, not just everything that consumes its documented purpose. The smell to watch for is a loop that builds a list, where an empty or short list is indistinguishable from a correct one — assert on the expected members, so a derivation whose input vanished fails loudly instead of quietly covering less.
|
||||
Removing a `--config` argument from `.pre-commit-hooks.yaml` was the right fix, but `check-release-needed.sh` derived its release-relevant path list by parsing that same token — with it gone, the derivation silently shrank with no error. Fix: before removing a token from an artifact more than one script reads, grep for everything that *parses* it, and assert on expected list members.
|
||||
|
||||
## 2026-08-09 — A documented impossibility is a claim, not a constraint
|
||||
|
||||
`vale-wrap.sh` flattens multi-line YAML `description:` scalars so Vale's `text.frontmatter.description` scope keeps matching. Its last-resort branch rewrote ASCII `'` to U+2019, justified at the emission site and in review as "the single combination no YAML scalar can carry verbatim" — an accepted-by-design residual, documented and test-covered, which is exactly why nobody retested it. The claim was false: a `|-` literal block with one indented content line carries `'`, `"`, `\` and `: ` verbatim, keeps the scope alive, and the wrapper's own header docstring already said literal blocks were unaffected. The cost of the unexamined claim was a silent underlint on 12 of 54 in-scope files — any rule whose token contained an apostrophe simply never fired, and the covering test (case 20) pinned only "the scope stays alive", so it passed either way. Fix: when a residual is accepted because something is "impossible", write down the specific claim in a falsifiable form and test *that*, not the workaround built on top of it. The tell here was that the residual and its justification were documented in the same breath by the same author — documentation records a belief, and a belief adjacent to a workaround is the one most worth attacking. Related: an assertion written to cover an accepted residual tends to assert the residual's *presence* rather than the behaviour it costs; case 20b asserted the scope survived flattening, never that a rule matching the rewritten characters still fired.
|
||||
A wrapper script's last-resort character rewrite was justified as "the one case no YAML scalar can carry verbatim" — untested because it seemed obviously true. It was false: a literal block scalar carries the exact characters in question, silently underlinting 12 of 54 files. Fix: when a residual is accepted as "impossible," write the claim in falsifiable form and test that claim directly, not the workaround built on it.
|
||||
|
||||
## 2026-08-14 — A fix handed down with authority is the least-reviewed code in the change
|
||||
|
||||
Across one review round, four fixes specified by the orchestrating reviewer were wrong, and every one would have shipped a guard that looked correct and caught nothing — the same defect class the guard was written to close. `nproc([[:space:]]|$)` does not match `$(nproc)`, the only spelling that occurs in real code. `grep -E ... | grep -Evq ...` under `set -o pipefail` returns 141 because `-q` exits on first match and SIGPIPEs the upstream, and 141 as an `if` condition reads as "no findings" — worse, it is *size-dependent*, so on the real 4-line `.vale.ini` the broken form behaves correctly and only fails once the input grows. `FUNCNAME` and `BASH_ARGC` were proposed as never-empty shell arrays to exempt from an unguarded-expansion scan; both are empty in reachable states (outside a function; `BASH_ARGC` measured 1 at top level and 0 inside a function), so exempting them suppresses a real bash 3.2 abort. `sed 's/#.*//'` as a comment-stripper truncates at the `#` in `${var#prefix}` — a form this repo actually uses at `check-manifests.sh:58` — reintroducing the exact blind spot being fixed. Each was caught only because the implementing agent re-derived the fix and measured, rather than applying what it was told; each had survived being written down confidently in a numbered finding with a reproduction attached. The asymmetry is the point: a finding arrives with evidence and gets scrutinised, while the fix beside it arrives with the same authority and gets implemented. Fix: state a proposed fix as a hypothesis with its own falsifiable check, and require the implementer to verify the fix mechanism independently of the defect reproduction — the two are different claims. The tell is a fix whose correctness depends on a regex boundary, a shell exit-status rule, or an "always/never" property of a builtin: measure it at the size, scope, and spelling it will actually meet, because the small case and the shipped case can disagree.
|
||||
Four fixes specified by an orchestrating reviewer were all wrong — a regex that didn't match the real code shape, a pipefail exit code misread as "no findings," two "never-empty" shell arrays that were empty in reachable states, and a comment-stripping `sed` that truncated `${var#prefix}`. Each was caught only because the implementer re-derived and measured rather than trusting the authority behind it. Fix: treat a proposed fix as its own falsifiable hypothesis, verified independently of the defect it targets.
|
||||
|
||||
## 2026-08-14 — Every assertion needs a revert it provably fails against [graduation candidate]
|
||||
|
||||
Mutation testing a review round's own fixes found repeatedly that a passing test was pinning nothing. Deleting `sync_dir`'s stale-directory wipe, its check-mode stale branch, or three of five `MIRROR_DIRS` entries each left the suite at 18/18 green; so did replacing the hooks trailing-newline normalisation with plain `cp`. A pair of concurrency assertions written to guard a reentrancy defect caught it 0 times in 10 runs against the deliberately broken script — and one of them was structurally incapable of ever catching it, because the broken code wrote to the system temp dir while the assertion inspected `$TMPDIR`. A fixture-leak fix ran green with and without the fix, verified only by external observation. Two manifest fixtures passed with the canonicalisation they claimed to cover deleted, rescued by an unrelated name-matching axis. In each case the test named the right behaviour in its description and asserted something adjacent to it. The cheap discipline that finds all of these: for every assertion, construct the revert it is supposed to catch and confirm it fails — and when an assertion survives every revert you can think of, that is not reassurance, it is the finding (one test only revealed itself as decoration once a sixth, differently-targeted revert was built for it). Fix: treat "which revert does this fail against?" as a required answer at the time an assertion is written, and record it where the assertion lives, since a test's own description is exactly the artifact that made the gap invisible.
|
||||
|
||||
Graduation candidate: this overlaps 2026-08-09's "an assertion written to cover an accepted residual tends to assert the residual's presence rather than the behaviour it costs" and the same date's "assert on the expected members, so a derivation whose input vanished fails loudly instead of quietly covering less." Three entries circling one pattern — human review for promotion to `core/instructions/testing.md`.
|
||||
Mutation testing repeatedly found tests passing green with the behaviour they claimed to guard deleted — a stale-directory wipe, a reentrancy guard, a fixture-leak fix, canonicalization logic. Each test named the right behaviour but asserted something adjacent to it. Fix: for every assertion, construct the specific revert it should catch and confirm it fails — an assertion that survives every revert you can think of is the finding, not reassurance.
|
||||
|
||||
## 2026-08-14 — Vale's `existence` extension concatenates `raw:` entries, it does not alternate them
|
||||
|
||||
A new `Kyberforge.CompositionNote` rule was first written with seven `raw:` entries, one per banned
|
||||
phrasing. Vale loaded it without a diagnostic and it matched **zero of 43 files** — an outcome
|
||||
indistinguishable from a clean corpus, and the exact shape of 2026-08-08's "a clean linter result can
|
||||
mean nothing was checked". The cause is that `existence` joins multiple `raw:` entries into one
|
||||
pattern rather than OR-ing them, so the rule was searching for all seven phrases concatenated. Every
|
||||
pre-existing rule in this style has exactly one `raw:` entry, so nothing in the repo demonstrated the
|
||||
difference, and the multi-entry form looks natural beside them. `tokens:` is the alternated form,
|
||||
which is why `VagueWording` uses it. Fix: a new Vale rule is not landed until it has been shown to
|
||||
*fire* — the standing revert-check applies to linter rules as much as to tests, and the revert here
|
||||
is the broken multi-`raw:` form, which `tests/test-vale-hooks-consumer.sh` now fails against.
|
||||
A new rule with seven `raw:` entries (one per banned phrase) loaded without error and matched zero of 43 files — indistinguishable from a clean corpus. `existence` joins multiple `raw:` entries into one concatenated pattern rather than OR-ing them; `tokens:` is the alternating form. Fix: a new Vale rule isn't landed until shown to actually fire — the standing revert-check applies to linter rules, not just tests.
|
||||
|
||||
## 2026-08-14 — Un-anchoring a description rule to reach mid-sentence text is unshippable
|
||||
|
||||
Widening `DescriptionOpener` to catch `gitea-workflow`'s mid-description "This is the human-facing
|
||||
entry point…" looked like a one-character change. Both that skill and `gitea-labels-milestones`
|
||||
*open* with "Use when…" and satisfy the opener rule; the offending clause sits at character 377 and
|
||||
300 of the folded value respectively, so the rule was never violated and never silently passed — it
|
||||
simply had no jurisdiction, which is a different defect and takes a different fix.
|
||||
Under `scope: text.frontmatter.description`, `^`
|
||||
anchors to the start of the whole description value — and `vale-wrap.sh` has already flattened that
|
||||
value to one physical line, so `(?m)` changes nothing. Un-anchoring is therefore the only route to
|
||||
mid-description text, and measured across the corpus it scores 5 hits and 5 false positives: skills
|
||||
legitimately quote user phrasings (`says "audit this skill"`) and write boundary clauses (`do not use
|
||||
this skill to manage label definitions`). That is the `Kyberforge.VagueQualifier` deletion repeating.
|
||||
Fix: keep the opener rule opener-anchored and give mid-description prose its own rule with its own
|
||||
token list. A rule's scope anchor is part of its contract, not an implementation detail to relax when
|
||||
a new case does not fit.
|
||||
Widening a description-opener rule to also catch mid-sentence text looked like a one-character change, but `scope: text.frontmatter.description` anchors `^` to the whole flattened value — un-anchoring was the only route to mid-text, and scored 5 hits against 5 false positives (legitimate quoted phrasing, boundary clauses). Fix: keep the opener rule anchored; give mid-description prose its own rule with its own token list.
|
||||
|
||||
## 2026-08-14 — A formatter in the commit path manufactures drift on a file with a clean git diff
|
||||
|
||||
`apm audit --ci` failed on `.claude/settings.json` while `git diff` on that file was empty — the worst
|
||||
possible pairing of signals, because the file matched HEAD exactly and every instinct says "nothing
|
||||
changed here". The content was identical to apm's output to the byte; only the JSON key order
|
||||
differed. `pretty-format-json --autofix` sorts object keys unless `--no-sort-keys` is passed, and its
|
||||
`exclude:` listed fifteen generated manifests but not this file, so from the commit that first wrote
|
||||
a hook entry there onward, apm's insertion-ordered output was silently re-sorted on the way in. apm
|
||||
then replayed the install, produced its own order, and reported drift against a file no human had
|
||||
touched.
|
||||
|
||||
The provenance matters as much as the mechanism, and the first account of this entry got it wrong in
|
||||
both directions. `git log --format='%h %ad %s' --date=iso` puts the introducing commit `2e395a4` at
|
||||
2026-08-14 18:47 and the fix `7607522` at 21:54 — roughly three hours, not "weeks". And `2e395a4` is
|
||||
the **first commit of the `refactor/trim-skills-agents-context` branch**, eleven minutes after the
|
||||
base merge `f9b919d`; `git branch -a --contains 2e395a4` returns only that branch and its own
|
||||
`remotes/origin/` tracking copy — two lines naming one branch, and `main` is not among them. So
|
||||
this was not a latent defect inherited from `main`, it was manufactured inside the same PR that
|
||||
diagnosed it, and the fixing commit's own message calling it "pre-existing … red at HEAD before
|
||||
ADR-0020 work began" is the mis-attribution rather than the record. Two cheap commands would have
|
||||
settled it before either sentence was written.
|
||||
|
||||
Three general points. First, a tool-owned generated file that passes through an autofixing formatter
|
||||
is drifted by construction, and the diff that would reveal it never appears in `git diff` — it only
|
||||
exists between the formatter's input and its output, which nothing stores. Second, the fix is
|
||||
self-undoing unless the exclude lands in the same commit: correcting the file alone means the hook
|
||||
re-breaks it as it is staged. Third — the one this entry had to learn twice — "pre-existing" is a
|
||||
claim about history, and history is queryable; a defect found while working on a branch feels
|
||||
inherited, and the feeling is not evidence. A three-hour-old self-inflicted bug and a months-old
|
||||
inherited one call for different responses, and writing the wrong one down converts a process failure
|
||||
into a story about someone else's neglect. Fix: when a tool declares ownership of a path, add that
|
||||
path to every autofixing hook's `exclude` at the moment ownership is declared, not when the drift is
|
||||
noticed — and before describing any defect as pre-existing, run `git log -S` or
|
||||
`git branch --contains` on the commit that introduced it. This repo gates marketplace-mirror,
|
||||
plugin-content and vale-style drift deterministically and has no equivalent gate asserting tool-owned
|
||||
paths stay out of formatter scope — `.claude/settings.json` was the sixteenth exclude and nothing
|
||||
prevents a seventeenth.
|
||||
`apm audit --ci` failed on `.claude/settings.json` with an empty `git diff` — `pretty-format-json --autofix` silently re-sorts JSON keys, and this generated file was missing from its exclude list, so every commit re-sorted apm's insertion-ordered output before apm compared against it. Separately, a defect introduced 3 hours earlier on the same branch was first mis-described as "pre-existing," an unverified claim about history. Fix: add tool-owned paths to every autofixing hook's exclude the moment ownership is declared, and verify "pre-existing" claims with `git log -S` or `git branch --contains` before writing them down.
|
||||
|
||||
## 2026-08-16 — A rule reversed inside a retrofit leaves no trace unless someone writes it down
|
||||
|
||||
`skill-author/SKILL.md:204` on `main` said "Keep reference chains one level deep — a reference file
|
||||
that references another reference file is rarely loaded correctly." The ADR-0020 retrofit replaced it
|
||||
with "Two hops from `SKILL.md`, never three" in `references/create.md` and `references/retrofit.md`,
|
||||
which permits exactly the chain the old rule banned. The looser rule is the right one and the
|
||||
retrofit could not have shipped without it: dispatch pushes each flow into its own file, so the
|
||||
shipped structure is `SKILL.md` → `improve.md` → `retrofit.md`, and a one-level ceiling would have
|
||||
made the mandatory dispatch pattern illegal. But ADR-0020 says nothing about chain depth, so the
|
||||
reversal was carried entirely by the diff — the new text asserts the new rule with no sign that a
|
||||
contradicting rule ever existed, and a reader who remembers the old one has no way to tell whether it
|
||||
was overturned or overlooked. Fix: when a change inverts a standing authoring rule rather than
|
||||
tightening or restating it, record the inversion where the rule's rationale lives — the ADR if the
|
||||
ADR is the reason, here otherwise. A rule that quietly flips is indistinguishable from a rule that
|
||||
was forgotten, and the second reading is the one that gets it re-added later.
|
||||
A retrofit replaced "keep reference chains one level deep" with "two hops, never three" — the opposite rule, needed because the new dispatch pattern requires `SKILL.md` → `improve.md` → `retrofit.md`. The ADR never mentioned chain depth, so the reversal was carried entirely by the diff with no sign a contradicting rule ever existed. Fix: when a change inverts a standing rule, record the inversion where the rule's rationale lives, or it reads as forgotten rather than overturned.
|
||||
|
||||
10
README.md
10
README.md
@@ -31,7 +31,7 @@ Install all of these before setting up. Each one is a hard dependency of a git h
|
||||
| Tool | Why | Install |
|
||||
| --- | --- | --- |
|
||||
| `apm` CLI | Four pre-push hooks shell out to it (`apm-marketplace-check`, `apm-audit-ci`, `apm-pack-check-clean`, and `check-plugin-content-sync` via `scripts/sync-plugin-content.sh`) | The `apm-install` skill, or `curl -sSL https://aka.ms/apm-unix \| sh`. Verify with `apm --version` |
|
||||
| `jq` | Required by `scripts/check-manifests.sh` and `scripts/sync-plugin-content.sh`, both pre-push | Your package manager |
|
||||
| `jq` | Required by `scripts/sync-plugin-content.sh`, pre-push | Your package manager |
|
||||
| `python3` + PyYAML | Required by `scripts/skill-size-check.sh` (the `skill-size-check` pre-commit hook), which reads folded YAML frontmatter | `python3` is usually present — pre-commit is itself a Python application. `pip install pyyaml` if the hook reports PyYAML missing |
|
||||
| `vale` | Required by the `vale-audit-prefilter-skill` / `-agent` pre-commit hooks and the `check-vale-style-sync` pre-push hook | `brew install vale` (macOS), `snap install vale` (Linux), `choco install vale` (Windows), or https://vale.sh/docs/vale-cli/installation/ |
|
||||
| `claude` CLI | Required by the `validate-plugins` and `validate-marketplace` pre-push hooks | Claude Code |
|
||||
@@ -94,13 +94,7 @@ Every other pre-push hook does run.
|
||||
|
||||
See [`docs/spec/gates.md`](docs/spec/gates.md) for what each hook enforces and why.
|
||||
|
||||
**Offline?** Exactly two pre-push hooks need the network, because root `apm.yml`'s marketplace contains one remote package entry that must be resolved with `git ls-remote`:
|
||||
|
||||
```bash
|
||||
SKIP=apm-marketplace-check,apm-pack-check-clean git push
|
||||
```
|
||||
|
||||
Skip **only** those two. The remaining pre-push hooks are real local checks and pass offline; adding one of them to `SKIP` disarms it silently.
|
||||
**Offline?** No pre-push hook needs the network: root `apm.yml`'s marketplace has no remote package entries (the last one, `mattpocock-skills`, was removed), so `apm-marketplace-check` and `apm-pack-check-clean` resolve everything from local sources. All pre-push hooks pass offline.
|
||||
|
||||
## Editing plugin content
|
||||
|
||||
|
||||
195
SIMPLIFICATION-AUDIT.md
Normal file
195
SIMPLIFICATION-AUDIT.md
Normal file
@@ -0,0 +1,195 @@
|
||||
# Simplification audit
|
||||
|
||||
Date: 2026-09-10. Read-only analysis; nothing has been changed. Purpose: a hand-off for deciding what to remove, merge, and shrink. Findings are ranked by payoff within each area; effort is S/M/L. Claims were independently re-verified against the repo by a clean reviewer; corrections have been applied.
|
||||
|
||||
Assumptions agreed before analysis: anything is on the table, Claude Code and Copilot CLI both stay supported, findings are ranked with effort.
|
||||
|
||||
Counting convention: line counts are hand-edited `.apm/` source unless marked "incl. mirror". Every `.apm/` file has a byte-identical generated copy at the plugin root, so plugin cuts count double in the repo total.
|
||||
|
||||
## 1. The shape of the problem
|
||||
|
||||
| Measure | Value |
|
||||
| ---------------------------------------------------------------------------| -----------------------------------------------------------------------------------------|
|
||||
| Tracked files / lines | 820 / 102,000 |
|
||||
| Lines in `plugins/` | 70,600 (69% of repo) |
|
||||
| Of which the 39 `SKILL.md` files a model actually loads | ~2,600 lines (under 4% of plugin lines) |
|
||||
| Generated flat mirror files (byte copies of `.apm/`) | 263 files, ~22,000 lines |
|
||||
| `docs/research/` vendored inside plugins | ~19,000 lines, nothing executable reads it |
|
||||
| Repo-level `docs/research/` + `docs/notes/` | 4,500 lines, 47% of all prose words, 6 of 11 research files linked only from each other |
|
||||
| Enforcement: hook entries in `.pre-commit-config.yaml` / pre-push hooks | 33 / 14 |
|
||||
| Enforcement: `tests/*.sh` + runners + `scripts/` | 12,400 + 475 + 4,500 lines |
|
||||
| Validator scripts inside kyberforge (+ their bats tests) | 6,800 + 5,300 lines |
|
||||
| Preload tax (39 skill names + descriptions) | 10,987 chars, ~2,750 tokens per session |
|
||||
| Commits since 2026-05-10 / share touching hook, test, gate, vale, or sync | 447 / ~25% |
|
||||
|
||||
The pattern across every area is the same: the payload (skill bodies, rules, decisions) is small and the scaffolding around it (mirrors, research dumps, sync gates, tests of tests, justification prose) is 10 to 30 times larger. A quarter of all commits have gone into maintaining the scaffolding.
|
||||
|
||||
## 2. Measured baseline: hooks and tests
|
||||
|
||||
Measured on this machine, clean tree, all hooks passing. `pre-commit run --all-files` per stage.
|
||||
|
||||
| Gate | Wall time |
|
||||
|---|---|
|
||||
| **Full pre-push stage (everything below, sequential)** | **~5 min 10 s** |
|
||||
| `run-tests` (26 bash suites + 351 bats tests) | 276 s |
|
||||
| `apm-audit-ci` (7 manifests) | 12.2 s |
|
||||
| `validate-plugins` (6 × `claude plugin validate`) | 4.9 s |
|
||||
| `check-plugin-content-sync` | 4.5 s |
|
||||
| `apm-pack-check-clean` | 3.1 s |
|
||||
| Other 9 pre-push hooks combined | 7.6 s |
|
||||
| **Full pre-commit stage, all files** | **18.2 s** |
|
||||
|
||||
`run-tests` is 90% of the wall time. Every push pays it in full: the runner has no change detection and the config sets `always_run: true`. `apm-audit-ci` is the second-slowest hook; per its own comment block its earlier description overclaimed, and what it verifies today is that seven manifests parse and the lockfile exists.
|
||||
|
||||
Where the 276 s goes (each suite run alone, sequential):
|
||||
|
||||
| Suite | Time | Note |
|
||||
|---|---|---|
|
||||
| `test-sync-plugin-content.sh` | 83 s | 14 temp trees, 2 `git init`, repeated `apm pack` |
|
||||
| all 351 bats tests (10 files, kyberforge and core validators) | 64 s | mostly `validate.sh` / `validate-provenance.sh` fixtures |
|
||||
| `test-adr0020-differential.sh` | 29 s | 12 assertions; re-runs two validators over the live corpus and a fixture tree |
|
||||
| `test-check-vale-style-sync.sh` | 25 s | guards a byte-identical copy |
|
||||
| `test-vale-wrap.sh` | 14 s | |
|
||||
| `test-adr0020-frontmatter.sh` + `-targets.sh` | 25 s | |
|
||||
| Remaining 20 suites | 36 s | 12 of them run in under 2 s each |
|
||||
|
||||
Five suites account for 215 s of 276 s. Three of those five (sync-plugin-content, vale-style-sync, adr0020-differential) test tooling that findings 2, 7, and 14 propose to delete or shrink, so the fastest path to a quick pre-push is removing the duplication those tests guard rather than optimising the tests.
|
||||
|
||||
## 3. Enforcement layer: hooks, tests, scripts
|
||||
|
||||
This is the area you named as hardest to understand and slowest. Root cause: most pre-push hooks exist to keep two copies of something in sync, or to re-validate what another hook already validates.
|
||||
|
||||
1. **Six hooks validate overlapping sets of the same manifests.** `check-manifests`, `validate-plugins`, `validate-marketplace`, `apm-pack-check-clean`, `apm-marketplace-check`, `apm-audit-ci`. Keep the two `claude plugin validate` hooks plus `apm-pack-check-clean`. ~~Delete `check-manifests` (282 lines + 771 test lines; its `lib/marketplace-plugins.sh` stays because `sync-plugin-content.sh` sources it).~~ `apm-audit-ci` spends 12 s confirming that manifests `apm pack` already parses do parse; drop or keep on that basis. Move the network-dependent `apm-marketplace-check` to a release checklist. Effort S.
|
||||
> **Done (2026-09-12):** see commit `e647f14` on `docs/simplification-audit`. Deleted the `check-manifests` pre-commit hook entry, `scripts/check-manifests.sh` (282 lines), and `tests/test-check-manifests.sh` (771 lines); kept `scripts/lib/marketplace-plugins.sh`, still sourced by `sync-plugin-content.sh`. Updated the now-stale `check-manifests.sh` mentions in `README.md` and `docs/spec/gates.md` (hook table row and hook counts). The `apm-audit-ci` and `apm-marketplace-check` decisions in this finding remain open — out of scope for this change.
|
||||
|
||||
2. **Four "keep two copies in sync" gates: 1,100 script lines + 1,600 test lines.** Each one is a symptom of duplication that could be removed instead of guarded:
|
||||
- `check-vale-style-sync`: 413 lines + 798 test lines guarding a byte-identical 526-line `vale-wrap.sh` and style directory copied between skill-audit and agent-audit. About 350 of its lines run Vale glob probes against the hook file patterns. Disappears if the two audit skills merge (finding 14); the probes belong in `test-vale-wrap.sh`.
|
||||
- `check-scope-walkup-sync`: 365 lines cross-checking four independent ports of the same package-root walk-up. Disappears if the ports share one script or the skills merge.
|
||||
- `check-marketplace-mirror-sync`: guards `.github/plugin/marketplace.json`. The script header calls it Copilot's legacy convention path and says Copilot also accepts the Claude path; the vendored Copilot docs list it as primary. Verify against current Copilot CLI before deleting hook, script, test, and mirror file.
|
||||
- `check-executables-allow-sync`: 474 lines to assert one string equals kyberforge's version. A six-line grep, or drop it (the failure mode is visible and recoverable).
|
||||
Effort S each, M for the walk-up.
|
||||
|
||||
3. **Tests of the test harness: 1,090 lines testing 475 lines.** `test-run-tests.sh` and `test-run-bats.sh` defend "green either way" holes that exist only because the runners hand-roll TAP parsing and set-equality checks. Replace both runners with about 40 lines (`bats -r plugins` plus a parallel `find | xargs` over `test-*.sh`) and delete the meta-tests. `lib/batch-run.sh` stays; `sync-plugin-content.sh` sources it. Effort M.
|
||||
> **Not proceeding (2026-09-13):** premise doesn't hold. A full read of both runners and both meta-tests found the "TAP-parsing/set-equality" logic is regression coverage for specific past incidents — a `BATS_FILE_FLOOR` hardcode once let deleted test files vanish silently ("155 tests, 0 failures" with 11 tests missing); a missing/broken `run-bats.sh` used to make the whole bats suite disappear with a green summary; a formatter change once reported "0 tests, 0 failures" as a pass. Replacing the runners as specified would delete exactly the guards against that failure class. No changes made. Re-scoping this would mean deciding, guard by guard, which are still worth keeping — a design decision, not a mechanical cleanup.
|
||||
|
||||
4. [x] ~~**`skill-frontmatter` is a 62-line bash script inlined in YAML** with its own 366-line test. `skill-size-check.sh` already parses the same frontmatter with PyYAML. Fold it in (about 15 Python lines), delete the inline hook, its test, and the 79 lines in `gates.md` arguing for the split. Effort S.~~
|
||||
> **Done (2026-09-12):** see commit `c8a7c9e` on `docs/simplification-audit`. Added a ~20-line required-frontmatter check (`name`, `description`, `metadata.version` as three-part semver) to `scripts/skill-size-check.sh`, reusing the YAML mapping `description_value()` already parses. Removed the inline `skill-frontmatter` hook (~80 lines) from `.pre-commit-config.yaml` and deleted `tests/test-skill-frontmatter.sh` (366 lines). Removed the 79-line "the other hook on that scope" discussion from `docs/spec/gates.md` and its now-dangling cross-reference, replacing both with a one-line note of the fold; updated the pre-push hook counts there. Updated fixture builders in `tests/test-skill-size-check.sh`, `tests/test-adr0020-body-checks.sh`, `tests/test-adr0020-targets.sh`, `tests/test-adr0020-differential.sh`, and `tests/test-vale-hooks-consumer.sh` to carry valid `metadata.version` so the new check doesn't spuriously fail existing fixtures.
|
||||
|
||||
5. **`skill-size-check.sh` has six test files totalling 3,589 lines for one 1,497-line script**, split by ADR section rather than behaviour. `test-adr0020-differential.sh` is 452 lines for 12 assertions. Merge to two files. Effort M.
|
||||
|
||||
6. [x] ~~**Prose-grep tests.** `test-governance-layer.sh` and `test-instructions-and-docs.sh` (583 lines) grep markdown for phrases, including a one-shot "issue 0015 refactor incomplete" assertion made permanent and an assertion that `docs/notes/` exists. Delete both.~~ `check-apm-agents-valid.sh` (161 + 264 test lines) is a loop plus fail-closed guards around `validate.sh`; it folds into the merged audit skill's own tests (finding 14). Effort S.
|
||||
> **Done (2026-09-12):** see commit `5f9f2b3` on `docs/simplification-audit`. Deleted `tests/test-governance-layer.sh` (270 lines) and `tests/test-instructions-and-docs.sh` (313 lines); no other file referenced either. `check-apm-agents-valid.sh` was left untouched — its fate is tied to the separate, out-of-scope skill-merge finding 14.
|
||||
|
||||
7. **`check-plugin-content-sync.sh` is 813 lines wrapping `apm pack`, with a 1,291-line test.** The mirror itself must stay (Claude Code marketplace installs need flat directories), and the script does real work a bare `git diff` would lose: it strips `tests/` from the mirror, regenerates both `plugin.json` files with `mcpServers` reinjected, and packs into a scratch copy so `--check` never mutates. Even so, 2,100 lines for that is disproportionate; target a third. Effort M.
|
||||
|
||||
8. **`docs/spec/gates.md` (1,048 lines) is roughly 15% "what is enforced" and 85% post-mortems** of defects already fixed and pinned by tests. The 60-line hook table is the useful part. Target 200 lines. The same applies to the 106 comment lines in `.pre-commit-config.yaml` and to `scripts/`, where 8 of 15 files are 40 to 60% comments. Effort M.
|
||||
> **Partially done (2026-09-13):** see commit `a35f5e8` on `docs/simplification-audit`. The 85%-post-mortem characterization was stale — the file had already shrunk to 966 lines by other findings, and most of what remained is load-bearing "why this design" rationale cited by ADRs and tests, not dead incident narration. Cut only the two genuinely stale passages: a reproduction paragraph carrying explicitly outdated numbers, and a retrofit-process narrative superseded by current state — 966 → 930 lines. `.pre-commit-config.yaml`'s comments were left untouched; on inspection they're compact constraint notes, not filler. Target of 200 lines not reached and not recommended — would require deleting content the file itself flags as load-bearing.
|
||||
|
||||
**Proposed target.** Pre-push 14 hooks to 6: `run-tests`, `validate-plugins`, `validate-marketplace`, `apm-pack-check-clean`, `check-plugin-content-sync`, `check-release-needed`. Pre-commit stays roughly as is minus `skill-frontmatter`, and minus `check-ast` once finding 9 removes the only `.py` files. Tests 26 files to about 10 (12,400 to about 5,000 lines). Keep bats and its three submodules; the 351 bats tests ship inside plugins and are the right tool there. Do not port the bash suites to bats; delete them instead.
|
||||
|
||||
## 4. Plugins
|
||||
|
||||
The shared pattern: per-skill `README.md` files no model reads, a `docs/research/` dump per plugin, a `sources.md` provenance chain with its own validator, and reference files that restate man pages.
|
||||
|
||||
### 4.1 Cross-plugin (apply everywhere)
|
||||
|
||||
9. [ ] **Delete `docs/research/` from every plugin (~19,000 lines).** kyberforge's alone is 14,143 lines, 32% of the plugin, and about 8,900 of those are vendored third-party content (Anthropic `skill-creator` including a 1,325-line `viewer.html` and ten `.py` files, obra/superpowers, mattpocock). The rest is copied tool documentation. The gitea references explicitly say the research doc "has a known history of drifting from the deployed server". Every `apm.yml` uses `includes: auto`; whether the directory ships to consumers needs one check. Keep upstream URLs in one line per plugin README; git history keeps the rest. Check obra/superpowers licence if anything is retained. Goes together with finding 11: 32 `sources.md` files carry "Research doc" paths into these directories. Effort S.
|
||||
> **Decision (2026-09-12):** Keep. `docs/research/` is retained on purpose — it's read by agents doing work sourced from those docs. Not proceeding.
|
||||
|
||||
10. [x] ~~**Delete per-skill `README.md` and `references/README.md` (48 files, 1,574 lines).** They restate the SKILL.md in narrative form. The pre-commit config itself notes a skill README "is consumer-facing prose that no agent ever loads". Keep one plugin-level README with one line per skill. Requires dropping the README criterion in `skill-audit/references/file-structure.md` and the README step in `new-skill.sh`. Effort S.~~
|
||||
> **Done (2026-09-12):** see commit `edcc57c` on `docs/simplification-audit`. Deleted the 48 per-skill/reference READMEs plus 2 scaffold templates; dropped the README criterion from `skill-audit`'s `file-structure.md` and `finding-criteria.md` and the README-generation step from `new-skill.sh`; updated `new-skill.bats` to match. Plugin-root READMEs were kept, not part of this finding.
|
||||
|
||||
11. **Drop the provenance chain: `sources.md`, `source_keys` frontmatter, `validate-provenance.sh`.** 32 plugin and skill `sources.md` files (about 1,300 lines) plus 9 research indexes, 216 source files with `source_keys`, two copies of the validator (1,198 and 632 lines) with ten checks, and 125 bats tests exist to track which upstream informed which file. Git blame and a URL in the README do the same job. This is more code than the content it tracks. Effort M (touches skill-audit, both validator copies, two repo tests, and every skill's frontmatter).
|
||||
|
||||
12. [x] ~~**Strip ADR and changelog narration from model-facing files.** `ADR-0020` is cited in 3 of 7 kyberforge SKILL.md files and 16 references; ADR-0023 is cited inline 21 times in the git plugin. Examples: "was the old house rule and ADR-0020 deleted it", "were removed per ADR-0015 once issue #90 landed", "this file previously recorded `list_issues` as having neither a `type` nor a `milestones` parameter". `skill-author/references/retrofit.md` (197 lines) is a one-time migration guide; it is loaded from `improve.md` and listed in `sources.md`, so remove those in the same change. These belong in git history or the ADR, not in context. Effort S.~~
|
||||
> **Done (2026-09-12):** see commit `edcc57c` on `docs/simplification-audit`. Historical narration stripped from kyberforge (ADR-0020) and git (ADR-0023) skill content; `retrofit.md` deleted along with its load-step and `sources.md` entries. Caught in review: some `ADR-0023` tags were not narration but the `check-rtk-prefix` hook's required opt-out marker for intentionally-bare git commands — those 12 were restored, not left stripped.
|
||||
|
||||
13. [x] ~~**State repeated boilerplate once or delete it.** A near-identical "Resolve owner and repo" block in 5 of 7 gitea skills; 404-masks-403 in 6 files; manual pagination in 7; main/master refusal in 9 git files; the "use the project's domain glossary, respect ADRs" paragraph in 5 bin skills. Three git skills define three different structured-result JSON shapes whose only consumer is `git-orchestrate` (finding 19). Effort S.~~
|
||||
> **Done (2026-09-12):** see commit `6cfc357`. Trimmed each repeated instance in place — same meaning, fewer words — rather than extracting to a shared file (blocked by the one-file-per-skill install constraint, ADR-0014): the "Resolve owner and repo" block across 5 `gitea-*` skills, the 404-masks-403 note across 6 gitea files, the manual-pagination explanation across 8 gitea files, the main/master force-push refusal across 7 git plugin files (some with multiple internal restatements), and the domain-glossary/ADR paragraph across 5 `bin` skills. This was a trim-in-place pass, not a merge: the cross-skill duplication itself remains and is coupled to the (out-of-scope) skill-merge findings 19/20. Left the three git skills' structured-result JSON shapes untouched, as directed. Verified no regressions with `scripts/skill-size-check.sh` (pre/post diff) and `claude plugin validate` on both plugins.
|
||||
|
||||
### 4.2 kyberforge (290 files, 44,568 lines incl. mirror; the 7 SKILL.md bodies are 333 lines, under 1%)
|
||||
|
||||
14. **Merge `skill-audit` + `agent-audit` into one `audit` skill (removes about 3,300 lines and two pre-push hooks).** `vale-wrap.sh` is byte-identical in both; five Vale rules byte-identical (agent-audit carries one extra, so it is the superset); `validate.sh` shares a 1,061-line boundary-target resolver block that diffs as zero lines; SKILL.md steps 1, 3, 4 and the gotchas are the same text. Each copy is hard-wired to one mode, so the merged script needs a path switch. The duplication exists because a plugin-cache install copies only each skill's own files (the rule ADR-0014 follows), so a script cannot be shared across skills; merging the skills is the only way to remove the copy. Effort M.
|
||||
|
||||
15. **Merge `skill-author` + `agent-author` likewise.** `contract.md` shares most of its Description section; `new-skill.sh` and `new-agent.sh` implement the same package-root walk-up with different mode names; step 1 dispatch tables and step 3 gates are near-identical. Keep the agent scope logic (plugin vs project/user) as its own reference. Effort M.
|
||||
|
||||
16. **Cut the validators by an order of magnitude.** `validate.sh` is 1,677 lines of bash with embedded Python, ported twice; `skill-size-check.sh` is 1,497. Target about 200 lines total: frontmatter present, size ceilings, boundary targets resolve. The 526-line `vale-wrap.sh` exists to work around folded `>` scalars in descriptions; writing descriptions as `|` literal blocks removes the folding problem, but the wrapper is also the exported hook entry in `.pre-commit-hooks.yaml` and carries the NOT RUN guard the audits depend on, so it shrinks rather than disappears. This is where the real complexity lives and is the item most worth discussing. Effort L.
|
||||
|
||||
17. **Fold `forge` and `apm-install`.** `forge` is a four-row routing table plus 207 lines of references explaining fork vs inline; it should be 25 lines with no references. `apm-install` (53 lines + 17-line sources) becomes a sixth dispatch row in `apm-workflow`. Effort S.
|
||||
|
||||
18. **Delete prose the model already knows.** "Valid characters: lowercase letters, numbers, hyphens"; what pipx does and PEP 668; "code blocks carry a language tag"; "data to stdout, diagnostics to stderr". Ironically `body-discipline.md` instructs auditors not to include "concepts the agent already knows". Effort S.
|
||||
|
||||
### 4.3 git and gitea (153 + 93 files, 9,889 + 6,047 lines incl. mirror; source 3,288 + 2,286)
|
||||
|
||||
19. **Delete the two router skills and two orchestrate agents (309 lines + 195 reference lines).** No skill invokes them as a step; they appear only in boundary clauses (`AGENTS.md`, `git-worktrees`, `gitea-issues`, `gitea-prs`) and as worked examples in agent-audit references, all of which must change in the same commit or `skill-size-check` fails on the dangling target. Claude Code already routes on descriptions. The chain today is `git-workflow` step 5 invokes `git-orchestrate`, whose step 5 invokes `git-commits`, which runs `rtk git commit`: three hops. Both agents exceed 900 words; ADR-0020 deliberately sets no agent body gate. Effort S.
|
||||
> **Not proceeding (2026-09-13):** premise doesn't hold. There are no separate "router skills" — only two `.agent.md` files. `git-orchestrate` is not a dangling boundary-clause reference; it's `git-workflow` step 5's actual execution backend (documented both directions), so deleting it breaks `git-workflow`'s only execution path rather than tidying an orphan. `gitea-orchestrate` is intentional per ADR-0011 (agent-facing counterpart for agent callers) even though `gitea-workflow` doesn't call it. A third, undocumented instance of the same pattern (`apm-orchestrate`) exists and isn't addressed by this finding. The four boundary-clause locations named above don't actually reference either agent. No changes made. This needs the "short discussion" §7 bucket 2 implies, not a mechanical delete.
|
||||
|
||||
20. **Collapse git 7 skills to 1; gitea 7 to 2.** Git references are man-page restatement: `git-log-format.md` (242 lines listing `%H`, `%ar`), `conventional-commits-spec.md` (170 lines), `worktrees.md` (178), `merging.md` explaining fast-forward. Roughly 60% of the plugin is generic. The genuinely house-specific content fits in about 150 lines: the `rtk` rule and ADR-0023 exceptions, main/master refusal, `--no-verify`, the `-i --autosquash` 2.39.5 trap, `--force-with-lease --force-if-includes`, bisect exit codes, submodule push ordering, the detached-HEAD worktree trap. Gitea is more legitimately specific (MCP schema quirks: `tree_sha`, `withLines`, silent drops on PR create, `per_page` 20 vs 30, 404 means 403) and splits naturally into `gitea-tracker` (issues, PRs, labels, milestones) and `gitea-repo` (branches, files, releases). Risk: one description must carry all trigger phrases; keep a dispatch table at the top of the body. Keep `pc-author` and `pc-run` (finding 38). Effort M.
|
||||
|
||||
21. [x] ~~**Delete `config.example.json` / `.claude/plugins/git/config.json`.** Read by two steps, written by nothing. Default to GitHub Flow with the existing `develop` / `release/*` inference. Effort S.~~
|
||||
> **Done (2026-09-12):** see commit `f5e4d0d`. Deleted `plugins/git/config.example.json` (the runtime `.claude/plugins/git/config.json` was never a tracked file). Removed the config-read step from `git-orchestrate`'s Process and from `git-branches`' Step 1, leaving the existing default-inference logic (GitHub Flow, with Gitflow inferred from a `develop`/`release/*` branch) as the sole path; updated `git-workflow`'s description of the orchestrator's behaviour to match. Dropped the now-dangling `applied_config` field from `git-orchestrate`'s output shape and the `config.example.json` example from `docs/spec/architecture.md`.
|
||||
|
||||
### 4.4 bin, core, lint (88 + 49 + 31 files incl. mirror)
|
||||
|
||||
22. **bin: strip generic process theatre.** `write-docs` is 109 lines, mostly form-filling sections plus a 15-line source provenance block; its rules fit in 25 lines. `tdd` is about 70% textbook (RED/GREEN diagram, "good tests are integration-style", five thin references restating textbook design advice). `diagnose` 40%, `prototype` 50% (pixel-level UI switcher spec), `grill-with-docs` 35%. Keep the opinionated parts: "no horizontal slicing", "no phase 2 without a loop", `[DEBUG-xxxx]` tags, "never infer the output path", the triage state machine. Effort M.
|
||||
|
||||
23. **bin: merge `grill-me` into `grill-with-docs`.** `grill-me` is 16 lines and a subset of the docs flow; `grill-with-docs` creates `CONTEXT.md` when missing, so the merged skill needs a no-write opt-out. `caveman` (50 lines) and `zoom-out` (9) are hand-invoked prompts rather than workflow skills; they are also the repo's `disable-model-invocation` exemplars in `CONTEXT.md`, `contract.md`, ADR-0020, ADR-0021, and `gates.md`, and `install.sh` has no path for `~/.claude/commands/`, so moving them means picking a new exemplar. `improve-codebase-architecture` defines its glossary twice (inline and in `language.md`; the README documents the split as intentional). Effort S.
|
||||
|
||||
24. **core: `provider-adapter-author` is a 1,200-line wrapper around one instruction** ("replace duplicated lines with `@AGENTS.md`, keep provider-specific lines"): a 496-line validator with a 519-line bats suite for a check that is a grep. `agentsmd-author` already calls `agentsmd-audit` as mandatory closeout, and both route to `provider-adapter-author` in boundary clauses that must change with it. Target: one `agentsmd` skill with an audit mode, adapter conversion as a step, validator about 40 lines. Needs an ADR-0012 revisit. Effort L.
|
||||
|
||||
25. **lint: delete the `lint-runner` agent.** Its body is "call `vale-run`, reformat output", which `--output=JSON` already gives; it exists for backends that do not exist. It is the example boundary clause in three `agent-author` templates and ADR-0016, so those need a new example. About 40% of `vale-config` is install tables and settings lists the model can fetch from vale.sh. Keep the house-verified matrices (`E100`/`E201`, `Packages` below glob, frontmatter, ignore paths). `lint/docs/research/docs/vale/` overlaps the skill's own references by about two thirds. Effort S.
|
||||
|
||||
## 5. Prose and docs (9,600 lines, 109,000 words outside plugins)
|
||||
|
||||
26. [ ] **Move or delete `docs/research/` and `docs/notes/` (4,500 lines, 47% of prose words).** Six of eleven research files are linked only from each other; they are self-described session audit trails, agendas, and a "temporary build reference". `docs/notes/factory-research-gaps-conflicts.md` says "Status: Superseded"; `factory-integration-decisions.md` says "Complete" and its decisions already live in ADRs, yet `AGENTS.md` tells every session to read it. `archive/team-self-organisation-sprint-brief.md` (3,400 words) is unrelated to this repo. Archive or delete; drop the three `AGENTS.md` pointers. Moving `CONTROLS.md` to `docs/spec/` means updating its literal path in nine or more files including the deployed `governance.md`. Effort S.
|
||||
> **Decision (2026-09-12):** Keep. Same reasoning as finding 9 — these docs are intentional context for sourced work. Not proceeding.
|
||||
|
||||
27. **Four governance documents say one thing.** `core/instructions/governance.md` (949 words, always-on), `docs/ai-constitution.md` (2,906), `docs/wiki/HUMANS.md` (1,413), `CONTROLS.md` (1,224), with near-identical preambles and, in three of the four, a "what this file does not govern" block pointing at the others. The constitution repeats one of its own principle lead sentences. Keep `governance.md` as the operative file, trimmed to about 50 lines (drop the classification table that repeats the bullets above it, the footer, the non-governance block). Dedupe the constitution by about 20%. Effort M.
|
||||
|
||||
28. **ADRs: 2,740 lines, 72% in eight ADRs over 150 lines.** ADR-0020 is 513 lines with a 71-line measurement log as Context; ADR-0017 has 173 lines of amendments against 45 of decision. ADR-0001 is superseded and ADR-0006 moot, both keeping full text below the banner. ADR-0002 is three lines. Truncate superseded ones to the banner, fold amendments into the decision, cap Context at 20 lines, add a 25-line `docs/adr/README.md` index with status. The rules already live in `gates.md`; the ADRs need only decision and consequences. Effort M.
|
||||
|
||||
29. **The same facts are stated in full three or four times.** "Edit `.apm/`, never the mirror": README (2 paragraphs), AGENTS.md (2 paragraphs), architecture.md (2 paragraphs plus the lost-README anecdote), ADR-0017. The apm.lock / SessionStart story: README (11 lines), AGENTS.md, ADR-0018, ADR-0019, gates.md. The offline `SKIP=` command and the three-stage install each appear three times. Rule: README has the how-to, AGENTS.md has one-line rules with links, architecture.md has mechanics. Effort S.
|
||||
|
||||
30. [x] ~~**`LESSONS.md`: 41 entries, 2 graduated, about 12 stale.** Twelve entries from 2026-05-17 describe a write-skill / write-eval workflow whose skills no longer exist. One entry is open work labelled "Status: neither part landed". The longest eight are 200 to 550-word incident reports. Delete the stale entries, move open work to an issue, cap entries at about 60 words, target 100 lines. Effort S.~~
|
||||
> **Done (2026-09-12):** see commit `629320b` on `docs/simplification-audit`. 255→131 lines, 41→30 entries. Kept 3 of the same-dated entries (RLHF defaults, secrets-rule gap, HITL gap) — judged unrelated to the defunct write-skill/write-eval workflow and still applicable, so 10 deleted rather than 12. The "neither part landed" open-work entry (CONTEXT.md not `@import`ed at session start) was removed rather than filed as an issue — full text preserved in this session's transcript if wanted later.
|
||||
|
||||
31. **`CONTEXT.md`: 28 terms, most used only by gates.md, scripts, or tests rather than by skills;** two (Preload tax, Skill context contract) are never used outside `CONTEXT.md` and ADR-0020. The preload-tax entry quotes two dated numbers then says not to quote them. The example dialogue and flagged-ambiguities sections are grill residue. Cut to about 20 one-line terms. Effort S.
|
||||
|
||||
32. **Structure is described three ways** (README layout table, architecture.md plugin table, AGENTS.md structure bullets), and `VISION.md` carries a 35-line stack spec for a product that lives in another repo. One layout table in README; architecture.md keeps mechanics only; VISION drops the stack detail. Effort S.
|
||||
|
||||
## 6. Distribution, versioning, and session startup
|
||||
|
||||
Not covered by the area audits above; found on a final sweep of the root config and install pipeline. The install pipeline itself (`scripts/install.sh` 55 lines, `deploy-manifest.sh` 24, statusline 109) is fine and needs nothing.
|
||||
|
||||
33. **Every plugin version lives in four places (five for kyberforge), plus one per skill.** `plugins/<name>/apm.yml`, two generated `plugin.json` files, the root `apm.yml` packages list, the `executables.allow` key (`kyberforge#1.6.2`), and a `metadata.version` in all 39 SKILL.md files (ADR-0022) that nothing consumes and that drifts freely (gitea skills sit at five different values). Repo tags (`v2.0.1`) follow a third scheme that the declared `tagPattern: v{version}` can never match under `per_package` versioning. ADR-0006, ADR-0022, `check-executables-allow-sync`, `skill-frontmatter`, and `apm pack --check-versions` all exist to police this. Proposal: one version per plugin in its `apm.yml`; drop `metadata.version` and ADR-0022; let `apm pack` derive the rest. Effort M.
|
||||
|
||||
34. **The SessionStart hook auto-updates the install on every startup.** `check-apm-current.sh` runs `apm outdated` (network, 60 s timeout) and then `apm update --yes` (300 s timeout) at every session start, rewriting `apm.lock.yaml`. That is why the lock file is dirty at the start of this session and why `AGENTS.md` has to explain "commit or discard it deliberately". It is a 60-line script with a 368-line test, an ADR (0019), the `executables.allow` pin, and a sync hook behind it. For a repo that is its own source, the update belongs in `install.sh` or a manual `apm update`, not in session startup. Effort S to remove; the design question is whether auto-update at startup is wanted at all.
|
||||
|
||||
35. [x] ~~**Outputs and packages for consumers that do not exist.** The `codex` output profile generates `.agents/plugins/marketplace.json` (95 lines) although Codex is not a supported consumer. The `mattpocock-skills` remote package entry is the only reason `apm-marketplace-check` needs the network, and its pin is advanced by hand (ADR-0015). The `.github/plugin/marketplace.json` mirror is a legacy path (finding 2). Removing all three leaves one generated marketplace manifest (the per-plugin `plugin.json` pairs remain) and no network-dependent hook. Effort S.~~
|
||||
> **Done (2026-09-13):** see commit `568ca74` on `docs/simplification-audit`. Removed the `codex` output profile from root `apm.yml` and its compiled `.agents/plugins/marketplace.json` (95 lines), and the `mattpocock-skills` remote package entry — the only remote marketplace entry, so `apm-marketplace-check` and `apm-pack-check-clean` no longer need network access at all. Updated `README.md`, `AGENTS.md`, `docs/spec/gates.md`, and `docs/spec/architecture.md` accordingly; added one-line superseded/updated notes to ADR-0015 and ADR-0021. Left `.github/plugin/marketplace.json` untouched — that's the Copilot legacy-path question in finding 2/§8, out of scope here; only re-ran the sync script to keep it consistent. `apm.lock.yaml` unaffected (`marketplace.packages[]` isn't part of the lockfile). Verified via `apm install`, `apm pack --marketplace=claude --check-versions`, and all four affected pre-push hooks.
|
||||
|
||||
36. **The release-tag mechanism guards an external contract with no known consumer.** `.pre-commit-hooks.yaml` exports three hooks for other repos to pin by `rev: <tag>`. `check-release-needed` (242 lines + 442 test), `test-vale-hooks-consumer` (270 lines), ADR-0014, and three tags exist to serve that. If no other repo pins these hooks today, the whole mechanism can be deferred until one does. Effort S.
|
||||
|
||||
37. **Two `.mcp.json` files declare an Obsidian vault server over `docs/`** (root and `plugins/bin/`; the other five plugin `.mcp.json` files are empty stubs), while `AGENTS.md` forbids using an external memory system for this repo. If the Obsidian tools are unused, drop both and the `reinject_mcp_servers` explanation in the bin README; the bin `plugin.json` pair regenerates. Effort S.
|
||||
> **Not proceeding (2026-09-13):** premise doesn't hold. The server exposes the repo's own git-tracked `docs/` folder — not an external/off-repo store — so it isn't the "external memory system" AGENTS.md's rule targets. It was deliberately added and versioned (3 commits), is documented as current intended behavior in both READMEs, and ADR-0018 uses it as its only concrete worked example of apm's MCP-dependency propagation mechanism actually working. No skill invokes the Obsidian tools as a workflow step, but that alone doesn't make the config dead. No changes made; recommend a human confirm whether the vault tooling is still wanted before removing it.
|
||||
|
||||
38. **`pc-author` / `pc-run` (689 lines) carry generic pre-commit documentation.** `hooks-by-language.md` (128 lines) and `failure-patterns.md` (133) restate pre-commit.com. Keep the skills, trim to the house-specific rules. Effort S.
|
||||
|
||||
## 7. Suggested order
|
||||
|
||||
1. Quick wins, all S, no design decisions needed: findings 9, 10, 26, 30, 31, 29, 12, 13, 1, 6, 4, 35, 37, 38, and the mirror-sync and executables-allow halves of 2. Removes roughly 25,000 to 30,000 lines and 6 hooks.
|
||||
2. Structural changes that need a short discussion: 14, 15, 19, 20, 23, 25, 17, 3, 5, 7, 33, 34, 36.
|
||||
3. The real complexity: 16 (validators), 11 (provenance), 24 (core), 8 and 28 (gates.md and ADRs).
|
||||
|
||||
Findings 9, 10, 11, and 12 are coupled through the provenance validator and the audit criteria; land them together or the audit gates start reporting the removals.
|
||||
|
||||
## 8. Questions to settle before starting
|
||||
|
||||
- **Native Claude Code marketplace install vs apm-only.** The flat mirror, `check-plugin-content-sync`, and ADR-0017 exist only for native `claude plugin install`. If apm install is the only supported path, the mirror and its 2,100 lines of tooling go away. Which install paths must work for consumers?
|
||||
- **Copilot CLI legacy path.** Is `.github/plugin/marketplace.json` still read by any Copilot version you target? If not, finding 2c is a pure delete.
|
||||
- **Provenance chain.** Is "which upstream informed this file" a requirement you still want, or was it a governance experiment? Finding 11 hinges on this.
|
||||
- **ADR-0012 (three core skills) and the one-script-per-skill install constraint.** The merges in 14, 15, and 24 need the first revisited and are the only way around the second. Are you open to superseding ADR-0012?
|
||||
- **Granularity of git/gitea skills.** One `git` skill vs seven trades routing precision for size. Is one broad description acceptable?
|
||||
- **Auto-update at session start.** Do you want the install refreshed from the remote every time a session opens (finding 34), or is a manual `apm update` acceptable?
|
||||
- **External hook consumers.** Does any other repo pin this repo's `.pre-commit-hooks.yaml` by tag today? If not, finding 36 defers the release mechanism entirely.
|
||||
- **Obsidian MCP.** Are the Obsidian tools over `docs/` used by anyone? If not, finding 37 is a pure delete.
|
||||
12
apm.yml
12
apm.yml
@@ -64,13 +64,11 @@ marketplace:
|
||||
|
||||
# Output targets (map form). Each output writes to its profile default
|
||||
# path; add 'path:' under a key to override.
|
||||
# 'codex' requires every package below to declare 'category:' (satisfied).
|
||||
outputs:
|
||||
claude: {}
|
||||
codex: {}
|
||||
|
||||
# CI tip: build one or all formats with a machine-readable manifest:
|
||||
# apm pack --marketplace=claude,codex --json | jq -r '.marketplace.outputs[].path'
|
||||
# CI tip: build a machine-readable manifest:
|
||||
# apm pack --marketplace=claude --json | jq -r '.marketplace.outputs[].path'
|
||||
|
||||
versioning:
|
||||
strategy: per_package
|
||||
@@ -106,12 +104,6 @@ marketplace:
|
||||
version: 1.1.2
|
||||
category: Productivity
|
||||
|
||||
- name: mattpocock-skills
|
||||
description: Skills for Real Engineers — planning, TDD, architecture, and debugging workflows from Matt Pocock's .claude directory.
|
||||
source: mattpocock/skills
|
||||
version: "1.2.3"
|
||||
category: Productivity
|
||||
|
||||
- name: lint
|
||||
description: Skills and agents for configuring and running linters.
|
||||
source: ./plugins/lint
|
||||
|
||||
@@ -169,7 +169,10 @@ correction) sorted what they document into three buckets:
|
||||
apm has no version-bump automation (established under "Versioning" in issue #90's plan), so an
|
||||
ageing pin is the accepted cost of a push gate that only fires on this repo's own changes.
|
||||
Note the pin does not make the entry offline-resolvable: an exact version still requires a
|
||||
`git ls-remote`, which is why two pre-push hooks need the network (see `AGENTS.md`).
|
||||
`git ls-remote`, which is why two pre-push hooks needed the network (see `AGENTS.md`).
|
||||
**Superseded 2026-09-13:** the `mattpocock-skills` entry has been removed from root `apm.yml`
|
||||
entirely, along with the `codex` marketplace output profile. No pre-push hook needs the network
|
||||
any longer.
|
||||
- **Caveat on "Status: executed" above:** issue #90's own execution comment flagged, before merge,
|
||||
that Claude Code's ability to actually load content out of `.apm/` was unverified — that caveat
|
||||
turned out to be a real defect, not a formality: the native installer has zero awareness of
|
||||
|
||||
@@ -14,8 +14,9 @@ A plugin's published description is one string authored twice — in `plugins/<n
|
||||
the matching `marketplace.packages[]` entry of the root `apm.yml` — and compiled into four generated
|
||||
files per plugin edit: the plugin's `.claude-plugin/plugin.json` and `.github/plugin/plugin.json`,
|
||||
plus the repo-wide `.claude-plugin/marketplace.json` and its `.github/plugin/marketplace.json`
|
||||
mirror. (`.agents/plugins/marketplace.json`, apm's codex profile, carries no per-package
|
||||
`description` or `version` at all and is unaffected.) It is the only text a consumer sees in a marketplace listing before
|
||||
mirror. (`.agents/plugins/marketplace.json`, apm's codex profile, carried no per-package
|
||||
`description` or `version` at all and was unaffected — that file and the profile producing it were
|
||||
removed 2026-09-13; see the note below.) It is the only text a consumer sees in a marketplace listing before
|
||||
installing. It is **not** a SKILL.md `description`: it is never preloaded into an agent's context and
|
||||
routes nothing at runtime. ADR-0020 governs that other artifact; this one governs this one. The
|
||||
overlap is a finding, not a scope: ADR-0020 established that capability enumeration in a description
|
||||
@@ -95,6 +96,10 @@ This decision covers the six plugins this repo authors. The root marketplace als
|
||||
`mattpocock-skills`, a third-party package whose description is not this repo's to write; its entry
|
||||
is out of scope and is left as published upstream.
|
||||
|
||||
*(Note, 2026-09-13: `mattpocock-skills` has since been removed from the root marketplace. This
|
||||
section's scope statement is retained as the reasoning behind the boundary; the entry it describes
|
||||
no longer exists.)*
|
||||
|
||||
## Decision
|
||||
|
||||
**A plugin's published `description` states the plugin's domain boundary. It does not enumerate the
|
||||
|
||||
@@ -44,10 +44,10 @@ These are routing boundaries, not inventories — they answer "where does a new
|
||||
|
||||
Two compilers produce the plugin roots you see in the tree:
|
||||
|
||||
- **`apm pack` compiles the manifests** (ADR-0015). Per plugin: `.claude-plugin/plugin.json` and `.github/plugin/plugin.json`, both generated from `plugins/<name>/apm.yml`. Repo-wide, from the root `apm.yml`'s `marketplace:` block: `.claude-plugin/marketplace.json` (apm's `claude` output profile) and `.agents/plugins/marketplace.json` (its `codex` profile, a differently-shaped file). Those two are the only marketplace outputs apm has profiles for — the third root manifest, `.github/plugin/marketplace.json` (Copilot CLI's legacy path), is a byte-identical mirror of the Claude one maintained by `scripts/sync-marketplace-mirror.sh` and gated by the `check-marketplace-mirror-sync` pre-push hook.
|
||||
- **`apm pack` compiles the manifests** (ADR-0015). Per plugin: `.claude-plugin/plugin.json` and `.github/plugin/plugin.json`, both generated from `plugins/<name>/apm.yml`. Repo-wide, from the root `apm.yml`'s `marketplace:` block: `.claude-plugin/marketplace.json` (apm's `claude` output profile) — the only marketplace output this repo declares. A second root manifest, `.github/plugin/marketplace.json` (Copilot CLI's legacy path), is a byte-identical mirror of the Claude one maintained by `scripts/sync-marketplace-mirror.sh` and gated by the `check-marketplace-mirror-sync` pre-push hook.
|
||||
- **`scripts/sync-plugin-content.sh` compiles the content mirror** (ADR-0017). It wraps `apm pack --format plugin` and copies the resulting bundle's flat `agents/`, `skills/`, `commands/`, `instructions/`, `extensions/`, and merged `hooks/hooks.json` back to the plugin root. Claude Code's installer convention-scans those flat paths and has no `.apm/` awareness whatsoever, so the mirror exists solely to satisfy the host's discovery contract.
|
||||
|
||||
`.apm/` is the sole hand-edited authoring source for plugin content. An edit made in the flat mirror is discarded by the next sync and is reported as drift by the `check-plugin-content-sync` pre-push hook. Hand-authored material that is not an `.apm/` primitive — `README.md`, `docs/`, `bin/`, `sources.md`, `.mcp.json`, and per-plugin extras such as `plugins/git/config.example.json`, `plugins/gitea/references/` and `plugins/bin/evals/` — lives at the plugin **root** and is untouched by either compiler.
|
||||
`.apm/` is the sole hand-edited authoring source for plugin content. An edit made in the flat mirror is discarded by the next sync and is reported as drift by the `check-plugin-content-sync` pre-push hook. Hand-authored material that is not an `.apm/` primitive — `README.md`, `docs/`, `bin/`, `sources.md`, `.mcp.json`, and per-plugin extras such as `plugins/gitea/references/` and `plugins/bin/evals/` — lives at the plugin **root** and is untouched by either compiler.
|
||||
|
||||
That immunity is positional, not by filename. Anything placed *inside* a mirrored directory is destroyed regardless of what it is: `sync_dir` runs `rm -rf "$dst"` before every copy, and `sync_hooks_json` does the same to `hooks/`. A hand-written `README.md` under `plugins/<name>/hooks/` or `plugins/<name>/skills/` is deleted by the next sync with no drift report, because a file with no `.apm/` counterpart is simply absent from the regenerated tree. This has already cost the repo one document — `plugins/kyberforge/hooks/README.md`, since restored to `plugins/kyberforge/docs/hooks.md`. Plugin-root documentation belongs in `docs/`.
|
||||
|
||||
|
||||
@@ -21,31 +21,30 @@ Install hooks via `pc-run`, wiring **all three stages**. This repo's `.pre-commi
|
||||
`default_install_hook_types`, so a plain install silently skips `commit-msg` (Conventional Commits)
|
||||
and `pre-push` (everything below).
|
||||
|
||||
The pre-push command reports **16** hooks, not 14. The extra two are pre-commit's own `meta` hooks,
|
||||
The pre-push command reports **15** hooks, not 13. The extra two are pre-commit's own `meta` hooks,
|
||||
`check-hooks-apply` and `check-useless-excludes`: they declare no `stages:`, so they run at every
|
||||
stage including this one. Both are declared in this repo's `.pre-commit-config.yaml` like everything
|
||||
else — what separates them is `repo: meta` (pre-commit's own built-ins) from `repo: local`. Fourteen
|
||||
else — what separates them is `repo: meta` (pre-commit's own built-ins) from `repo: local`. Thirteen
|
||||
is the count of hooks this repo authors itself.
|
||||
|
||||
**The caveat: one of those 14 is a silent no-op under that invocation.**
|
||||
**The caveat: one of those 13 is a silent no-op under that invocation.**
|
||||
`check-release-needed` exits 0 immediately unless `PRE_COMMIT_REMOTE_BRANCH` equals
|
||||
`refs/heads/main`, and pre-commit exports that variable only from the real pre-push git hook during
|
||||
an actual `git push`. Running the stage by hand — or from a CI runner — therefore reports it
|
||||
`Passed` having checked nothing. That is by design for feature branches — pushing WIP must not be
|
||||
blocked on cutting a premature tag — but it means `--hook-stage pre-push --all-files` is a full
|
||||
rehearsal of 13 hooks and a skip of the fourteenth. The script's own header records the same gap for
|
||||
rehearsal of 12 hooks and a skip of the thirteenth. The script's own header records the same gap for
|
||||
a PR merged through Gitea's merge button, where no local push happens at all.
|
||||
|
||||
## The pre-push gate
|
||||
|
||||
Fourteen hooks, grouped below by what they guard rather than by the order `.pre-commit-config.yaml` declares them in.
|
||||
Thirteen hooks, grouped below by what they guard rather than by the order `.pre-commit-config.yaml` declares them in.
|
||||
|
||||
**Core checks**
|
||||
|
||||
| Hook | Guards |
|
||||
|---|---|
|
||||
| `run-tests` | `bash tests/run-tests.sh --strict` — the whole suite, skips fatal (see [Tests](#tests)) |
|
||||
| `check-manifests` | `marketplace.json` and `plugin.json` paths resolve (needs `jq`) |
|
||||
|
||||
**Generated-content drift gates**
|
||||
|
||||
@@ -92,15 +91,18 @@ and `check-plugin-content-sync` (via `scripts/sync-plugin-content.sh`, which wra
|
||||
first and third are bare `apm …` entries and the second is a `bash -c` loop calling `apm` once per
|
||||
package, so without the CLI the push dies with an unhelpful "command not found". Install with
|
||||
`apm-install`, or `curl -sSL https://aka.ms/apm-unix | sh`; verify with `apm --version`. `jq` is
|
||||
needed by `scripts/check-manifests.sh` and `scripts/sync-plugin-content.sh` — those at least fail
|
||||
loudly (`Error: jq is required but not installed`).
|
||||
needed by `scripts/sync-plugin-content.sh` — it at least fails loudly (`Error: jq is required but
|
||||
not installed`).
|
||||
|
||||
## Skill and agent context gates (ADR-0020)
|
||||
|
||||
The `skill-size-check` pre-commit hook, scoped to `^plugins/[^/]+/\.apm/skills/[^/]+/SKILL\.md$`,
|
||||
runs `scripts/skill-size-check.sh`. It is also shipped to external repos as
|
||||
`kyberforge-skill-size-check` (see
|
||||
[External consumers](#external-consumers-the-root-pre-commit-hooksyaml)).
|
||||
[External consumers](#external-consumers-the-root-pre-commit-hooksyaml)). Besides the ADR-0020
|
||||
gates below, it also asserts required frontmatter is present: `name`, a non-empty `description`, and
|
||||
a `metadata.version` matching three-part semver (`1.0.0`) — folded in from a formerly standalone
|
||||
`skill-frontmatter` hook that parsed the same fields with a shell script.
|
||||
|
||||
**Two things fall outside that scope, both deliberately.** The `[^/]+/SKILL\.md$` tail admits only a
|
||||
`SKILL.md` sitting directly in a skill directory under `.apm/skills/`:
|
||||
@@ -125,85 +127,6 @@ the second returns exactly the template. The remaining unmatched `SKILL.md` file
|
||||
generated flat mirror, which is excluded by the `.apm/` segment on purpose — a mirror edit is drift,
|
||||
not an authoring change.
|
||||
|
||||
### `skill-frontmatter`, the other hook on that scope
|
||||
|
||||
A second `repo: local` pre-commit hook, `skill-frontmatter`, runs on the **same** `files:` pattern at
|
||||
the same stage. It is a shell loop that, **for the YAML frontmatter block only** — everything between
|
||||
the opening `---` and the next `---` — asserts four things per file:
|
||||
|
||||
| Check | Rejects with |
|
||||
|---|---|
|
||||
| a `^name:` line is present | "missing required frontmatter fields (name: …)" |
|
||||
| a `^description:` line is present | "missing required frontmatter fields (description: …)" |
|
||||
| `metadata:` contains a `^ version:` key, anchored, scanning to the next top-level key | "missing required frontmatter fields (metadata.version)" |
|
||||
| that version's value is three-part semver (`1.0.0`, quoted or not) | "has a malformed frontmatter metadata.version (…)" |
|
||||
|
||||
Every one of those qualifiers is load-bearing, and each replaced a defect that let the hook report
|
||||
Passed having measured nothing. `tests/test-skill-frontmatter.sh` pins all of them:
|
||||
|
||||
- **Frontmatter-scoped, not whole-file.** The checks used to `grep` the entire file, so a `metadata:`
|
||||
or `name:` block quoted in a **body code fence** satisfied them — `skill-author`'s own docs quote
|
||||
exactly such a block.
|
||||
- **Bounded by the next top-level key, not by `-A10`.** The version check was
|
||||
`grep -A10 "^metadata:" | grep -q " version:"`, which ran ten lines past the end of the block: a
|
||||
`version:` belonging to a following `source:` list entry counted (`write-docs` and `research` both
|
||||
have a `source:` list immediately after `metadata:`), while a `metadata:` block with more than ten
|
||||
lines before its `version:` was reported missing.
|
||||
- **`^ version:` anchored.** `" version:"` was an unanchored substring, so a deeper-nested
|
||||
` version:` matched too.
|
||||
- **The value is asserted, not just the key.** `plugins/bin/.apm/skills/write-docs/SKILL.md` carried
|
||||
`version: "1.0"` — present, correctly nested, and not a version — through an entire PR under a
|
||||
presence-only check. Two-part `1.0` is a YAML float, not a version string.
|
||||
- **The call shape is pinned.** `entry: bash` with `args: ['-c', <script>, …]` needs an explicit
|
||||
arg0 placeholder after the script: without it `bash -c` puts pre-commit's **first** filename in
|
||||
`$0`, where `for f in "$@"` never sees it. A single-file commit — the normal case — therefore ran
|
||||
the loop body zero times and exited 0. The third `args` entry (`skill-frontmatter`) exists solely
|
||||
to absorb `$0`; do not remove it.
|
||||
- **An unreadable file is an error, not a pass.** A file with no closing `---` fails with "no closing
|
||||
YAML frontmatter block" rather than falling through to a green.
|
||||
|
||||
**It still overlaps ADR-0020's "description present and non-empty" FAIL, and the overlap is not
|
||||
clean.** The ADR (`:95-101`) requires that question be decided on the **YAML-folded value** and
|
||||
nowhere else, precisely because a line regex gets it wrong in both directions. Measured on fixtures:
|
||||
|
||||
| Frontmatter | `skill-frontmatter` | `skill-size-check` |
|
||||
|---|---|---|
|
||||
| `description:` with no value, then `model: sonnet` | passes — the key is on a line | ERROR, "missing or empty" |
|
||||
| `"description": …` (quoted key, valid YAML) | **fails** — `^description:` does not match | passes, description read normally |
|
||||
|
||||
So the grep is not a second opinion on presence. It is blind to the shape ADR-0020 was written
|
||||
against, and it is the only one of the two that objects to a quoted key. Neither disagreement is
|
||||
currently live in the corpus, and the honest reading is that presence is `skill-size-check`'s
|
||||
question — the grep's contribution to it is noise on one shape and silence on the other.
|
||||
|
||||
What the hook adds that **no** ADR-0020 check reads is two keys: `name:` and `metadata.version`. A
|
||||
`SKILL.md` missing either passes `skill-size-check` at exit 0. That is its unique coverage, and the
|
||||
reason not to fold it into the size gate on the grounds of redundancy.
|
||||
|
||||
#### Why this one stays a shell parser
|
||||
|
||||
[`python3` and PyYAML are hard requirements](#python3-and-pyyaml-are-hard-requirements) below records
|
||||
that a hand-rolled frontmatter reader on this exact `files:` scope was **deliberately deleted**,
|
||||
because "a reader that mis-parses an unfamiliar scalar shape reports a clean pass on a file it never
|
||||
measured." That reasoning is about `skill-size-check` and does **not** transfer here. Do not delete
|
||||
this hook citing it. Three differences:
|
||||
|
||||
1. **It answers a strictly narrower question.** `skill-size-check` must know the *folded value* of a
|
||||
`>`-block scalar to count its characters, which is where a line reader diverges from a parser —
|
||||
one corpus description measured 270 characters parsed and 412 unparsed. This hook asks only
|
||||
whether a key is on a line and whether one short **plain scalar** matches `N.N.N`. There is no
|
||||
folding, no multi-line value, and no measurement to get subtly wrong.
|
||||
2. **It is frontmatter-scoped.** The failure mode that killed the old fallback was silently reading
|
||||
past or short of the block. This one extracts the block explicitly and errors out when it cannot
|
||||
find a closing marker, so "could not parse" is a red, never a green.
|
||||
3. **It is pinned by tests.** `tests/test-skill-frontmatter.sh` drives the hook through pre-commit's
|
||||
real `bash -c <script> <arg0> <files…>` invocation and asserts each defect class above. The
|
||||
deleted fallback had no such suite; that is how its disagreement with a real parser survived.
|
||||
|
||||
The trade it buys is that the hook stays repo-local. Moving it to a script would change the
|
||||
externally exposed `.pre-commit-hooks.yaml` contract for consumers, for a check that has no need of a
|
||||
YAML parser.
|
||||
|
||||
### Two independent gate families, neither replaced the other
|
||||
|
||||
**Family 1 — agentskills.io spec backstop** (unchanged, conformance not quality):
|
||||
@@ -322,12 +245,9 @@ run it. Four cross-plugin targets here (`gitea-branches` → `git-branches`, `gi
|
||||
through `.claude/skills/` alone, so **the same commit measured 2 dangling targets on a developer
|
||||
machine and 6 on a fresh clone**. A gate shipping hot with no baseline cannot give two answers.
|
||||
|
||||
Verified fixed: running the hook over a tree holding only `plugins/` and the root `apm.yml`, with no
|
||||
`.claude/` or `.agents/` anywhere, produced findings identical to the working tree. The figures that
|
||||
reproduction recorded — 26 description FAILs, 9 body FAILs, 2 dangling targets, 0 missing references
|
||||
— are the pre-retrofit corpus as it stood when the experiment was run, kept here as the evidence for
|
||||
the install-independence claim. They are not current: the retrofit under #99 took the first three to
|
||||
zero. What the experiment establishes is that the two trees agree, not what either measured.
|
||||
Verified: running the hook over a tree holding only `plugins/` and the root `apm.yml`, with no
|
||||
`.claude/` or `.agents/` anywhere, produces findings identical to the working tree — confirming the
|
||||
two trees agree on the current corpus, independent of what happens to be installed locally.
|
||||
|
||||
### Boundary-clause detection: three outcomes, not two
|
||||
|
||||
@@ -468,14 +388,9 @@ reader that mis-parses an unfamiliar scalar shape reports a clean pass on a file
|
||||
which is the exact vacuous-green failure the `python3` check exists to avoid. `pip install pyyaml`
|
||||
(or `python3 -m pip install PyYAML`, or the distro's `python3-yaml`) if the hook reports it missing.
|
||||
|
||||
**Neither requirement generalises to every hook on this scope, and one deliberate exception sits
|
||||
right next to it.** [`skill-frontmatter`](#skill-frontmatter-the-other-hook-on-that-scope) runs on the
|
||||
same `files:` pattern as a **shell** parser, on purpose — it asks only whether a key is on a line and
|
||||
whether one short plain scalar matches `N.N.N`, with no folding to get wrong, and moving it to a
|
||||
script would change the externally exposed `.pre-commit-hooks.yaml` contract for consumers. That
|
||||
section carries the full argument. A reader arriving here first should not read this one as
|
||||
condemning it. `check-rtk-prefix` needs `python3` but **not** PyYAML: it reads the markdown body and
|
||||
never touches frontmatter, so it has no scalar to fold.
|
||||
**Neither requirement generalises to every hook in this repo.** `check-rtk-prefix` needs `python3`
|
||||
but **not** PyYAML: it reads the markdown body and never touches frontmatter, so it has no scalar to
|
||||
fold.
|
||||
|
||||
## Agent files take the description gates, not the body gate
|
||||
|
||||
@@ -515,52 +430,19 @@ knows the difference; doing so silently enforces a gate ADR-0020 declines to set
|
||||
|
||||
## Current retrofit status
|
||||
|
||||
**The ADR-0020 gates ship hot, with no baseline file.** A shrinking baseline recording each
|
||||
non-compliant skill's current numbers was considered and rejected in favour of hot gates.
|
||||
The ADR-0020 gates ship hot, with no baseline file — a shrinking baseline was considered and
|
||||
rejected. The corpus is currently clean on both: 0 of 39 descriptions/bodies exceed their FAIL tier,
|
||||
0 dangling targets, 0 `Kyberforge.CompositionNote` (Vale) errors. History: issue #99.
|
||||
|
||||
**The corpus is now clean on both gates.** Issue **#99** retrofitted all 39 skills plugin by plugin;
|
||||
`kyberforge` was the last wave, after which the corpus was swept as a whole rather than per plugin.
|
||||
Each sweep is followed by an **independent review round**: a fresh agent with no memory of the
|
||||
retrofit re-measures the corpus and files what it finds, and the round repeats until one lands no
|
||||
findings. The rounds are recorded as comments on **#99** — read the current state off that thread,
|
||||
which is why no round count is pinned here.
|
||||
|
||||
| Gate | Current findings |
|
||||
|---|---|
|
||||
| `skill-size-check` | **0 of 39** descriptions and **0 of 39** bodies exceed their FAIL tier; 0 dangling targets; SUGGESTIONs outstanding (count not pinned — see below) |
|
||||
| `Kyberforge.CompositionNote` (Vale) | **0 errors** — the four `gitea-*` carriers were all retrofitted |
|
||||
|
||||
**The SUGGESTION count is deliberately not recorded here.** It moves with every skill edit *and*
|
||||
with every change to the gate's own tiering, so any figure written down is stale by the next commit.
|
||||
Measure it instead:
|
||||
Nothing is grandfathered — a new skill, or an edit that crosses a FAIL tier, is blocked on first
|
||||
commit. SUGGESTION counts are not pinned here; they move with every edit. Measure and check both
|
||||
gates before starting work on a skill:
|
||||
|
||||
```
|
||||
bash scripts/skill-size-check.sh plugins/*/.apm/skills/*/SKILL.md | grep -c '^SUGGESTION'
|
||||
pre-commit run skill-size-check --all-files # same findings, via the hook
|
||||
pre-commit run --all-files # size AND Vale — skill-size-check alone can pass while Vale still blocks
|
||||
```
|
||||
|
||||
A non-zero count is the expected steady state, not a regression. SUGGESTIONs exit 0 and block
|
||||
nothing; only the two FAIL tiers, the dangling-target ERROR and the missing-`references/` ERROR do.
|
||||
Read the count as a work queue, and the FAIL columns above as the gate.
|
||||
|
||||
`Kyberforge.CompositionNote` is the ADR-0020 Vale rule banning composition and architecture prose
|
||||
from a description. Every Vale rule here is `level: error` with no ignorable tier, so a description
|
||||
that reintroduces one blocks the commit even though no skill carries one today.
|
||||
|
||||
Because nothing is grandfathered, the gates now bite on **first commit**: a new skill, or an edit
|
||||
that pushes a description past 400 characters or a body past 900 words, is blocked until it
|
||||
complies. That is the steady state the retrofit was for — it is no longer true that an unrelated
|
||||
one-line fix to a skill requires retrofitting that skill first.
|
||||
|
||||
Check where a skill stands before starting, and check **both** gates:
|
||||
|
||||
```
|
||||
pre-commit run skill-size-check --all-files # size/context only
|
||||
pre-commit run --all-files # size AND Vale
|
||||
```
|
||||
|
||||
Scoping a retrofit off `skill-size-check` output alone leaves you blocked at the second gate.
|
||||
|
||||
## The `rtk` prefix gate (ADR-0023)
|
||||
|
||||
`check-rtk-prefix` is a `repo: local` pre-commit hook running `scripts/check-rtk-prefix.sh` over
|
||||
@@ -1006,30 +888,12 @@ fix.
|
||||
|
||||
## Pushing without a network
|
||||
|
||||
Exactly **two** pre-push hooks need the network, for one shared reason: root `apm.yml`'s
|
||||
`marketplace.packages[]` contains exactly one remote entry — `mattpocock-skills`,
|
||||
`source: mattpocock/skills` — and resolving it needs a `git ls-remote`.
|
||||
No pre-push hook needs the network. Every entry in root `apm.yml`'s `marketplace.packages[]`
|
||||
resolves from a local `./plugins/<name>` path, so `apm-marketplace-check` and `apm-pack-check-clean`
|
||||
never call `git ls-remote`.
|
||||
|
||||
| Hook | Offline failure |
|
||||
|---|---|
|
||||
| `apm-marketplace-check` (`always_run`, resolves every entry) | `No cached refs (offline)` |
|
||||
| `apm-pack-check-clean` (re-resolves the same entry) | `Error: Git network timeout during ls-remote` |
|
||||
|
||||
Pinning the entry to an exact version does **not** remove the call — an exact pin still ls-remotes.
|
||||
`--offline` rescues neither.
|
||||
|
||||
To push without a network, skip both using pre-commit's own mechanism:
|
||||
|
||||
```
|
||||
SKIP=apm-marketplace-check,apm-pack-check-clean git push
|
||||
```
|
||||
|
||||
**Skip those two alone.** Verified under `unshare -rn`: the other twelve pre-push hooks pass offline
|
||||
because they are real local checks. (`check-executables-allow-sync` landed after that run, but reads
|
||||
two local manifests and makes no network call.) Adding any other hook to `SKIP` disarms it silently.
|
||||
|
||||
`apm-audit-ci` calls `apm` too but stays local: its org-policy discovery resolves nothing on this
|
||||
remote *before* any network call, so it does not join the pair above.
|
||||
`apm-audit-ci` calls `apm` too but was always local: its org-policy discovery resolves nothing on
|
||||
this remote before any network call.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# caveman
|
||||
|
||||
Ultra-compressed output mode: drop articles, filler and pleasantries, keep the technical substance exact.
|
||||
|
||||
## What it does
|
||||
|
||||
Switches the agent into a terse register — no articles, no hedging, no pleasantries, fragments allowed, arrows for causality — while leaving technical terms, code blocks and quoted error strings untouched. The mode is *sticky*: once turned on it stays on for every subsequent response until the user says "stop caveman" or "normal mode", rather than decaying back to normal prose after a few turns.
|
||||
|
||||
It carries one built-in escape hatch. Security warnings, confirmations for irreversible actions, multi-step sequences where fragment order could be misread, and any request to clarify are answered in normal prose, then the compressed register resumes.
|
||||
|
||||
## Hand-invoked only
|
||||
|
||||
`SKILL.md` sets `disable-model-invocation: true`. This is the single most important thing to know about this skill: **the model cannot route to it.** No other skill can hand off to it, and no phrasing in a user's request will cause it to be selected automatically. The only way in is the human typing `/caveman`.
|
||||
|
||||
That is deliberate — output style is the user's choice, not an inference the router should make on their behalf. It is also why the description reads as one plain human-facing sentence rather than carrying the trigger phrasing and boundary clause a routable skill needs.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/caveman
|
||||
```
|
||||
|
||||
Then keep working normally. To leave the mode, say "stop caveman" or "normal mode".
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — persistence rule, compression rules, worked examples, and the auto-clarity exception |
|
||||
@@ -1,35 +0,0 @@
|
||||
# diagnose
|
||||
|
||||
A six-phase discipline for hard bugs and performance regressions: feedback loop → reproduce → hypothesise → instrument → fix with a regression test → clean up.
|
||||
|
||||
## What it does
|
||||
|
||||
Imposes an order of operations on debugging so the agent cannot skip to guessing. The load-bearing phase is the first one: build a fast, deterministic, agent-runnable pass/fail signal for the bug. Everything downstream — bisection, hypothesis testing, instrumentation — just consumes that signal, so the skill refuses to advance to Phase 2 without one, and says so explicitly rather than hypothesising blind.
|
||||
|
||||
The remaining phases each carry a constraint worth knowing about: hypotheses are generated 3–5 at a time and must be falsifiable, so the first plausible idea cannot anchor the whole investigation; every debug log is tagged with a unique prefix (`[DEBUG-a4f2]`) so cleanup is a single grep; the regression test is written before the fix and only at a seam that exercises the real bug pattern; and the run closes by asking what would have prevented the bug, handing off to `improve-codebase-architecture` when the answer is architectural.
|
||||
|
||||
Performance regressions take a branch of their own inside Phase 4 — baseline measurement and bisection, not logs.
|
||||
|
||||
## Conditional reading
|
||||
|
||||
Neither reference file is read on every run; `SKILL.md` names the condition for each.
|
||||
|
||||
- `references/feedback-loops.md` is read when Phase 1 has no signal yet, or when the loop you have is slow or intermittent.
|
||||
- `references/regression-seams.md` is read when Phase 5 leaves you unsure whether the available seam is deep enough — or whether one exists at all.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/diagnose
|
||||
```
|
||||
|
||||
Describe the bug or the regression. For filing and triaging a reported bug rather than diagnosing it, use `triage`; for test-first feature work, use `tdd`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The six phases and their gates — what must be true before each one ends |
|
||||
| `references/feedback-loops.md` | Loaded when Phase 1 has no loop or the loop is too weak: ten ways to construct one ordered by cost, how to sharpen an existing loop, handling intermittent bugs, and what to ask the user for when the bug resists reproduction |
|
||||
| `references/regression-seams.md` | Loaded when Phase 5 is unsure about the seam: what makes a seam correct, the four shapes of a too-shallow seam, and what to do when no correct seam exists |
|
||||
| `assets/hitl-loop.template.sh` | Copy-and-edit bash template for the last-resort human-in-the-loop feedback loop, cited by `references/feedback-loops.md`. Provides `step` and `capture` helpers and prints captured values as `KEY=VALUE` for the agent to parse |
|
||||
@@ -5,14 +5,14 @@ description: >
|
||||
broken, throwing, or failing, or says something got slow. Not filing or
|
||||
triaging a reported bug -> `triage`. Not test-first feature work -> `tdd`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Diagnose
|
||||
|
||||
A discipline for hard bugs. Skip phases only when explicitly justified.
|
||||
|
||||
When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
|
||||
When exploring the codebase, use the domain glossary for a clear mental model of the relevant modules, and check ADRs in the area.
|
||||
|
||||
## Phase 1 — Build a feedback loop
|
||||
|
||||
|
||||
@@ -1,27 +0,0 @@
|
||||
# grill-me
|
||||
|
||||
Interview the user relentlessly about a plan or design until the decision tree is fully resolved.
|
||||
|
||||
## What it does
|
||||
|
||||
Turns the agent into an interviewer rather than an implementer. It walks the design tree branch by branch, resolving dependencies between decisions one at a time, and offers its own recommended answer alongside each question so the user has something concrete to push against. Two rules give it its shape: **one question at a time**, and **never ask what the codebase can answer** — if a question is settleable by reading the code, the agent goes and reads the code instead of spending the user's attention on it.
|
||||
|
||||
## Composition
|
||||
|
||||
This is the plain grilling loop, with no documentation side effects. The sibling `grill-with-docs` skill runs the same interview but additionally challenges answers against the project's `CONTEXT.md` glossary and existing ADRs, and writes decisions back into those files as they crystallise. Reach for that one when the project has a domain model worth defending; reach for this one when it does not, or when nothing should be written down yet.
|
||||
|
||||
`triage` composes the documented variant, not this one, when an issue needs fleshing out.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/grill-me
|
||||
```
|
||||
|
||||
Describe the plan or design to be stress-tested. Expect questions one at a time, each with a recommended answer.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — the interview instruction, the one-question-at-a-time rule, and the explore-instead-of-asking rule |
|
||||
@@ -1,37 +0,0 @@
|
||||
# grill-with-docs
|
||||
|
||||
The grilling interview, run against the project's domain model — and writing decisions back into `CONTEXT.md` and ADRs as they land.
|
||||
|
||||
## What it does
|
||||
|
||||
Runs the same relentless one-question-at-a-time interview as `grill-me`, with the project's own documentation as an active participant. During codebase exploration it also locates the domain documentation — a root `CONTEXT.md` and `docs/adr/`, or a `CONTEXT-MAP.md` pointing at per-context glossaries and ADR directories in a multi-context repo — and then uses it five ways:
|
||||
|
||||
- **Challenges terms against the glossary.** When the user's usage conflicts with what `CONTEXT.md` already defines, that is raised immediately rather than absorbed.
|
||||
- **Sharpens fuzzy language** by proposing a precise canonical term ("you're saying 'account' — do you mean the Customer or the User?").
|
||||
- **Stress-tests domain relationships with concrete scenarios**, inventing edge cases that force the user to be precise about where one concept ends and the next begins.
|
||||
- **Cross-references claims against the code**, and surfaces contradictions between what the user says happens and what the code does.
|
||||
- **Updates `CONTEXT.md` inline**, the moment a term is resolved, rather than batching changes to the end of the session where they get lost.
|
||||
|
||||
Files are created lazily — only when there is something real to write.
|
||||
|
||||
ADRs are offered *sparingly*, and only when all three tests pass: the decision is hard to reverse, it would surprise a future reader without the context, and it was a genuine trade-off with real alternatives. Missing any one of the three means no ADR.
|
||||
|
||||
## Composition
|
||||
|
||||
`grill-me` is the same interview without the documentation side effects — use it when there is no domain model to defend or nothing should be written down yet. `triage` composes this skill (not `grill-me`) at step 4 when an issue needs fleshing out. `improve-codebase-architecture` runs its own grilling loop and borrows this skill's `CONTEXT.md` and ADR discipline for the decisions that come out of it.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/grill-with-docs
|
||||
```
|
||||
|
||||
Describe the plan or design. Expect questions one at a time, each with a recommended answer, and expect `CONTEXT.md` to be edited during the session rather than after it.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The interview instruction plus the domain-awareness rules: file layout discovery, the five during-session behaviours, and the three-part ADR test |
|
||||
| `references/context-format.md` | Cited when a term is resolved: the structure of a `CONTEXT.md` and how to write a Language entry |
|
||||
| `references/adr-format.md` | Cited when an ADR is offered: `docs/adr/` naming, sequential numbering, and the ADR template |
|
||||
@@ -1,36 +0,0 @@
|
||||
# improve-codebase-architecture
|
||||
|
||||
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones.
|
||||
|
||||
## What it does
|
||||
|
||||
Looks for places where a codebase is hard to understand, hard to test, or hard for an agent to navigate, and proposes refactors that concentrate behaviour behind smaller interfaces. It runs in three stages:
|
||||
|
||||
1. **Explore.** Reads the domain glossary and any ADRs in the area first, then walks the codebase with an `Explore` sub-agent — organically, noting friction rather than applying fixed heuristics. The **deletion test** is the filter: imagine deleting the module; if complexity vanishes it was a pass-through, if complexity reappears across N callers it was earning its keep.
|
||||
2. **Present candidates.** A numbered list, each with files, problem, solution and benefits — benefits stated in terms of *locality* and *leverage* and of how tests would improve. No interfaces are proposed yet; the user picks one.
|
||||
3. **Grilling loop.** Walks the design tree for the chosen candidate, with documentation side effects landing inline as decisions crystallise.
|
||||
|
||||
The skill is opinionated about vocabulary, and that is the point: **module, interface, implementation, depth, seam, adapter, leverage, locality**, used exactly, with no drift into "component", "service", "API" or "boundary". Domain nouns come from `CONTEXT.md`, architecture nouns from `references/language.md` — so a proposal reads as "the Order intake module", never "the FooBarHandler".
|
||||
|
||||
ADRs are treated as decisions not to be re-litigated. A candidate that contradicts one is surfaced only when the friction is real enough to warrant reopening it, and is marked as such.
|
||||
|
||||
## Composition
|
||||
|
||||
`diagnose` hands off here when a bug's post-mortem concludes that no correct test seam exists, or that callers are tangled — the recommendation is made after the fix is in, not before. The grilling loop follows `grill-with-docs`'s discipline for `CONTEXT.md` entries and ADR offers, and `SKILL.md` names that skill's format documents directly.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/improve-codebase-architecture
|
||||
```
|
||||
|
||||
Point at a codebase or an area of one. Expect a numbered candidate list and a "which of these would you like to explore?" before any interface design happens.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Condensed glossary, key principles, and the three-stage process |
|
||||
| `references/language.md` | Cited throughout `SKILL.md`: full definitions of every term, the words each one replaces, and the full principle list |
|
||||
| `references/interface-design.md` | Read at stage 3 when the user wants alternative interfaces explored: the parallel sub-agent "Design It Twice" pattern, framing the problem space, and the per-agent design constraints |
|
||||
| `references/deepening.md` | Cited from `references/interface-design.md`: how to deepen a cluster of shallow modules safely, the four dependency categories (in-process, local-substitutable, remote-but-owned, true external), seam discipline, and the replace-don't-layer testing strategy |
|
||||
@@ -7,7 +7,7 @@ description: >
|
||||
into deep ones, informed by `CONTEXT.md` and `docs/adr/`. Not debugging a
|
||||
failure -> `diagnose`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Improve Codebase Architecture
|
||||
@@ -41,7 +41,7 @@ This skill is _informed_ by the project's domain model. The domain language give
|
||||
|
||||
### 1. Explore
|
||||
|
||||
Read the project's domain glossary and any ADRs in the area you're touching first.
|
||||
Read the domain glossary and any ADRs in the area first.
|
||||
|
||||
Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
|
||||
|
||||
|
||||
@@ -1,32 +0,0 @@
|
||||
# prototype
|
||||
|
||||
Build a throwaway prototype that answers one design question — either a runnable terminal app or several UI variations.
|
||||
|
||||
## What it does
|
||||
|
||||
Treats a prototype as **throwaway code that answers a question**, and lets the question decide the artifact. `SKILL.md` opens with a two-row dispatch table and the run resolves exactly one row before doing anything else:
|
||||
|
||||
- *"Does this logic / state model feel right?"* → a tiny interactive terminal app that pushes the state machine through the cases that are hard to reason about on paper.
|
||||
- *"What should this look like?"* → several radically different UI variations on one route, switchable from a floating bottom bar via a URL search param.
|
||||
|
||||
The two branches produce fundamentally different artifacts, so picking wrong wastes the whole prototype. When the question is genuinely ambiguous and the user is unreachable, the skill defaults on the shape of the surrounding code (backend module → logic, page or component → UI) and states the assumption at the top of the prototype rather than silently choosing.
|
||||
|
||||
Six rules apply to both branches: throwaway and visibly named as such, one command to run, no persistence by default, no polish, surface the full state after every action or variant switch, and delete or absorb the prototype when it is done. The *answer* is the only durable output — the skill captures it in a commit message, ADR, issue or `NOTES.md` before the code is deleted.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/prototype
|
||||
```
|
||||
|
||||
State the design question. For production code, use `tdd`; for talking a design through without building anything, use `grill-me`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The branch dispatch table and the rules that apply to both branches |
|
||||
| `references/logic.md` | The logic branch, read only when that row is selected: when it is the right shape, and how to build the interactive terminal app |
|
||||
| `references/ui.md` | The UI branch, read only when that row is selected: when it is the right shape, and how to build and switch between the variations |
|
||||
|
||||
Each reference is self-contained — a run reads one of the two, never both.
|
||||
@@ -1,31 +0,0 @@
|
||||
# research
|
||||
|
||||
Research a tool, library or API from canonical documentation into a directory of structured per-topic reference files.
|
||||
|
||||
## What it does
|
||||
|
||||
Runs a six-step pipeline: scope against the working directory (what version is actually in use, what is already documented), resolve the topic through Context7, websearch for canonical docs covering whatever Context7 missed, read those sources, deepen one level into the links worth following, then write one markdown file per topic area plus a `sources.md` provenance record.
|
||||
|
||||
Four gotchas at the top of `SKILL.md` shape the whole run, and each exists because of a specific failure: the output path is never inferred (a guessed destination scatters a directory's worth of files through someone's source tree); nothing is written outside that path; no empty topic file is ever written (a stub `troubleshooting.md` reads downstream as researched and closed); and a Context7 "no results", redirect or header-only response does not count as coverage. If no topic area has content, the run writes nothing at all — `sources.md` included — and reports what it searched.
|
||||
|
||||
The frontmatter pins `model: sonnet` and a closed `allowed-tools` list. Notably it grants no subagent tool, so every `WebFetch` is serial and each fetched page lands in the run's own context — which is why steps 4 and 5 insist on reducing each page to notes before fetching the next, and cap deepening at roughly ten extra pages.
|
||||
|
||||
## Composition
|
||||
|
||||
Both reference files are read on condition, never on every run — `SKILL.md` inlines the minimum each step needs (the seven default topic areas at step 1, the four `sources.md` field names and the topic-file frontmatter keys at step 6) and sends the run to the reference only for what it does not carry. Those four field names are matched literally by the downstream provenance validator, so prose written in their place parses as nothing and the check passes having verified nothing — which is why they are inlined rather than deferred.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/research
|
||||
```
|
||||
|
||||
Name the topic and the output path — the skill will stop and ask if the path is missing. Supplying starting URLs is treated as a deliberate source choice and skips Context7 resolution and discovery. For documentation derived from existing code or specs, use `write-docs`; for a bug or incident, use `diagnose`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The four gotchas and the six research steps |
|
||||
| `references/topics.md` | Read at Step 1 only when what belongs in a default topic is unclear or a custom topic is needed: the per-topic coverage table and the custom-topic naming rule |
|
||||
| `references/file-format.md` | Read at Step 6 only when the inlined field names do not settle the case: slug derivation, the Context7 slug and URL convention, and what belongs in a topic body |
|
||||
@@ -1,32 +0,0 @@
|
||||
# tdd
|
||||
|
||||
Test-driven development as a strict red-green-refactor loop, one behaviour at a time.
|
||||
|
||||
## What it does
|
||||
|
||||
Two convictions drive this skill. The first is about what a test is for: tests verify behaviour through public interfaces, not implementation details. A good test reads like a specification ("user can checkout with valid cart") and survives refactors because it does not care about internal structure. The warning sign for a bad one is precise — the test breaks when you refactor but behaviour has not changed.
|
||||
|
||||
The second is an explicit anti-pattern: **do not write all the tests first, then all the implementation.** Horizontal slicing treats RED as "write every test" and GREEN as "write every implementation", and it produces tests of *imagined* behaviour — tests of the shape of things, insensitive to real change, committed to before the implementation was understood. The correct shape is vertical: one test → one implementation → repeat, each cycle informed by what the last one taught you.
|
||||
|
||||
The workflow is four stages: plan (confirm the interface and which behaviours matter, with the user — you cannot test everything), fire a tracer bullet (one test proving the path works end to end), loop incrementally one behaviour at a time, then refactor once everything is green. Refactoring while RED is forbidden.
|
||||
|
||||
Codebase exploration uses the project's domain glossary, so test names and interface vocabulary match the project's language, and ADRs in the area are respected.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/tdd
|
||||
```
|
||||
|
||||
Describe the feature or bug. Expect the skill to ask what the public interface should look like and which behaviours matter most before any code is written. For diagnosing an existing bug rather than building test-first, use `diagnose`; for throwaway exploratory code, use `prototype`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Philosophy, the horizontal-slicing anti-pattern, the four-stage workflow, and the per-cycle checklist |
|
||||
| `references/tests.md` | Cited from Philosophy: worked good and bad test examples |
|
||||
| `references/mocking.md` | Cited from Philosophy: mock at system boundaries only, and what not to mock |
|
||||
| `references/deep-modules.md` | Cited from stage 1: what a deep module is (small interface, large implementation) and why it is the design to aim for |
|
||||
| `references/interface-design.md` | Cited from stage 1: designing interfaces for testability, starting with accepting dependencies rather than creating them |
|
||||
| `references/refactoring.md` | Cited from stage 4: the refactor-candidate checklist — duplication, long methods, shallow modules, feature envy, primitive obsession |
|
||||
@@ -5,7 +5,7 @@ description: >
|
||||
red-green-refactor loop, one behaviour at a time. Not diagnosing an existing
|
||||
bug -> `diagnose`. Not throwaway exploratory code -> `prototype`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Test-Driven Development
|
||||
@@ -49,7 +49,7 @@ RIGHT (vertical):
|
||||
|
||||
### 1. Planning
|
||||
|
||||
When exploring the codebase, use the project's domain glossary so that test names and interface vocabulary match the project's language, and respect ADRs in the area you're touching.
|
||||
When exploring the codebase, use the domain glossary so test names and interface vocabulary match the project's language, and respect ADRs in the area.
|
||||
|
||||
Before writing any code:
|
||||
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
# triage
|
||||
|
||||
Move issues on the project issue tracker through a small state machine of triage roles.
|
||||
|
||||
## What it does
|
||||
|
||||
Gives issue triage an explicit state model and a fixed set of moves. Every issue carries exactly one **category** role (`bug`, `enhancement`) and one **state** role (`needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`); conflicting state roles are flagged to the maintainer before anything else happens. Unlabeled issues normally enter at `needs-triage`; `needs-info` returns there once the reporter replies. The maintainer can override at any point, and unusual transitions are questioned rather than executed silently.
|
||||
|
||||
A run does one of three things depending on what the maintainer asks for:
|
||||
|
||||
- **Show what needs attention** — three buckets, oldest first: unlabeled, `needs-triage`, and `needs-info` with reporter activity since the last triage notes.
|
||||
- **Triage a specific issue** — gather context (including prior triage notes, so resolved questions are not re-asked, and `.out-of-scope/` records that resemble the issue), recommend a category and state with reasoning, attempt reproduction for bugs *before* any grilling, run a `grill-with-docs` session if the issue needs fleshing out, then apply the outcome.
|
||||
- **Quick state override** — "move #42 to ready-for-agent" is trusted and applied directly, skipping grilling, after confirming the exact changes.
|
||||
|
||||
Two hard rules: every comment or issue the skill posts during triage must open with the AI-generated disclaimer, and the canonical role names above are *not* necessarily the label strings in the tracker — each is resolved against the tracker's live label set before it is applied, and a name with no counterpart there is reported to the maintainer as a gap rather than guessed at.
|
||||
|
||||
## Composition
|
||||
|
||||
`grill-with-docs` is invoked at step 4 when an issue needs fleshing out; whatever that session establishes is carried into the triage notes so the work is not lost. The reverse direction also exists: `diagnose` names this skill as the place to send a *reported* bug that needs filing rather than debugging.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/triage
|
||||
```
|
||||
|
||||
Then describe what you want in natural language — "show me anything that needs my attention", "let's look at #42", "move #42 to ready-for-agent", "what's ready for agents to pick up?".
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The roles and state machine, the three invocation modes, the needs-info template, and how to resume a prior session |
|
||||
| `references/agent-brief.md` | Cited when an issue moves to `ready-for-agent` (and reused for `ready-for-human`): how to write a brief that stays durable for weeks while the codebase moves under it — describe interfaces and behavioural contracts, not line numbers |
|
||||
| `references/out-of-scope.md` | Cited when an enhancement is closed `wontfix` and when checking for prior rejections: how the `.out-of-scope/` knowledge base is laid out and what it is for — institutional memory, and deduplication against re-litigated requests |
|
||||
@@ -5,7 +5,7 @@ description: >
|
||||
tracker's triage states, or an issue prepared for an AFK agent. Not debugging
|
||||
the bug itself -> `diagnose`. Not fleshing out a design -> `grill-with-docs`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Triage
|
||||
@@ -65,7 +65,7 @@ Show counts and a one-line summary per issue. Let the maintainer pick.
|
||||
|
||||
## Triage a specific issue
|
||||
|
||||
1. **Gather context.** Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the project's domain glossary, respecting ADRs in the area. Read `.out-of-scope/*.md` and surface any prior rejection that resembles this issue.
|
||||
1. **Gather context.** Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the domain glossary, respecting ADRs in the area. Read `.out-of-scope/*.md` and surface any prior rejection that resembles this issue.
|
||||
|
||||
2. **Recommend.** Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the issue. Wait for direction.
|
||||
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
# write-docs
|
||||
|
||||
Produce technical documentation derived from code and spec, one section at a time, with a confirmation gate on every section.
|
||||
|
||||
## What it does
|
||||
|
||||
Casts the agent as a technical writer with one non-negotiable constraint: **every claim must be traceable to a source file line, a spec section, or an explicit user statement.** Nothing is invented, and behaviour that genuinely cannot be documented from the available sources is marked out-of-scope rather than explained away.
|
||||
|
||||
The process is eight steps — identify scope, read and extract, gap check, draft section by section, confirmation gate, delta summary, reader testing, finalise — and several of them are deliberately gated on the human:
|
||||
|
||||
- Files are read only after the user approves them by name. The skill may propose candidates; it waits.
|
||||
- The **gap check** presents what the code does say and asks the user to fill only what it does not: caller intent, error-handling rationale, non-obvious side effects.
|
||||
- No section is finalised until the full revised text has been shown. The skill never gates on output the user has not seen, and never reprints the whole document — all edits are surgical.
|
||||
- **Reader testing** predicts 5–10 questions a target reader would ask, then spawns a sub-agent that receives only the finished doc and the questions — no source files. If the doc cannot answer them, neither can the sub-agent, and the run loops back to drafting.
|
||||
|
||||
Summary and overview sections are written last, once the detail sections are stable.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/write-docs
|
||||
```
|
||||
|
||||
Name the files or modules to document, the target audience (developer / user / contributor / internal), and the documentation type (reference, guide, README section, inline comment, changelog entry). For a PRD, ADR or decision doc, use `grill-me` or `grill-with-docs` instead — those have dedicated handling.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — role, use/do-not-use boundaries, required inputs, constraints, the eight-step process, output format, failure handling, and a nine-item self-check |
|
||||
@@ -1,25 +0,0 @@
|
||||
# zoom-out
|
||||
|
||||
Ask the agent to go up a layer of abstraction and map the modules and callers around unfamiliar code.
|
||||
|
||||
## What it does
|
||||
|
||||
A single-purpose prompt for the moment you land in a part of the codebase you do not know. Instead of answering at the level of the file in front of it, the agent climbs one layer and produces a map of the relevant modules and their callers — and names them using the project's own domain glossary vocabulary, so the map lines up with the language the rest of the repo already uses.
|
||||
|
||||
## Hand-invoked only
|
||||
|
||||
`SKILL.md` sets `disable-model-invocation: true`, so the router never selects this skill on its own and no other skill can hand off to it. It runs when the human asks for it. That also means its description is written as one plain human-facing sentence — it carries no trigger phrasing or boundary clause, because nothing routes on it.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/zoom-out
|
||||
```
|
||||
|
||||
Best used with the unfamiliar code already in context — the skill widens the view around what you are looking at rather than picking a starting point for you.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — a single instruction, no supporting files |
|
||||
@@ -3,7 +3,7 @@ name: zoom-out
|
||||
description: Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
|
||||
disable-model-invocation: true
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary vocabulary.
|
||||
I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary.
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# caveman
|
||||
|
||||
Ultra-compressed output mode: drop articles, filler and pleasantries, keep the technical substance exact.
|
||||
|
||||
## What it does
|
||||
|
||||
Switches the agent into a terse register — no articles, no hedging, no pleasantries, fragments allowed, arrows for causality — while leaving technical terms, code blocks and quoted error strings untouched. The mode is *sticky*: once turned on it stays on for every subsequent response until the user says "stop caveman" or "normal mode", rather than decaying back to normal prose after a few turns.
|
||||
|
||||
It carries one built-in escape hatch. Security warnings, confirmations for irreversible actions, multi-step sequences where fragment order could be misread, and any request to clarify are answered in normal prose, then the compressed register resumes.
|
||||
|
||||
## Hand-invoked only
|
||||
|
||||
`SKILL.md` sets `disable-model-invocation: true`. This is the single most important thing to know about this skill: **the model cannot route to it.** No other skill can hand off to it, and no phrasing in a user's request will cause it to be selected automatically. The only way in is the human typing `/caveman`.
|
||||
|
||||
That is deliberate — output style is the user's choice, not an inference the router should make on their behalf. It is also why the description reads as one plain human-facing sentence rather than carrying the trigger phrasing and boundary clause a routable skill needs.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/caveman
|
||||
```
|
||||
|
||||
Then keep working normally. To leave the mode, say "stop caveman" or "normal mode".
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — persistence rule, compression rules, worked examples, and the auto-clarity exception |
|
||||
@@ -1,35 +0,0 @@
|
||||
# diagnose
|
||||
|
||||
A six-phase discipline for hard bugs and performance regressions: feedback loop → reproduce → hypothesise → instrument → fix with a regression test → clean up.
|
||||
|
||||
## What it does
|
||||
|
||||
Imposes an order of operations on debugging so the agent cannot skip to guessing. The load-bearing phase is the first one: build a fast, deterministic, agent-runnable pass/fail signal for the bug. Everything downstream — bisection, hypothesis testing, instrumentation — just consumes that signal, so the skill refuses to advance to Phase 2 without one, and says so explicitly rather than hypothesising blind.
|
||||
|
||||
The remaining phases each carry a constraint worth knowing about: hypotheses are generated 3–5 at a time and must be falsifiable, so the first plausible idea cannot anchor the whole investigation; every debug log is tagged with a unique prefix (`[DEBUG-a4f2]`) so cleanup is a single grep; the regression test is written before the fix and only at a seam that exercises the real bug pattern; and the run closes by asking what would have prevented the bug, handing off to `improve-codebase-architecture` when the answer is architectural.
|
||||
|
||||
Performance regressions take a branch of their own inside Phase 4 — baseline measurement and bisection, not logs.
|
||||
|
||||
## Conditional reading
|
||||
|
||||
Neither reference file is read on every run; `SKILL.md` names the condition for each.
|
||||
|
||||
- `references/feedback-loops.md` is read when Phase 1 has no signal yet, or when the loop you have is slow or intermittent.
|
||||
- `references/regression-seams.md` is read when Phase 5 leaves you unsure whether the available seam is deep enough — or whether one exists at all.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/diagnose
|
||||
```
|
||||
|
||||
Describe the bug or the regression. For filing and triaging a reported bug rather than diagnosing it, use `triage`; for test-first feature work, use `tdd`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The six phases and their gates — what must be true before each one ends |
|
||||
| `references/feedback-loops.md` | Loaded when Phase 1 has no loop or the loop is too weak: ten ways to construct one ordered by cost, how to sharpen an existing loop, handling intermittent bugs, and what to ask the user for when the bug resists reproduction |
|
||||
| `references/regression-seams.md` | Loaded when Phase 5 is unsure about the seam: what makes a seam correct, the four shapes of a too-shallow seam, and what to do when no correct seam exists |
|
||||
| `assets/hitl-loop.template.sh` | Copy-and-edit bash template for the last-resort human-in-the-loop feedback loop, cited by `references/feedback-loops.md`. Provides `step` and `capture` helpers and prints captured values as `KEY=VALUE` for the agent to parse |
|
||||
@@ -5,14 +5,14 @@ description: >
|
||||
broken, throwing, or failing, or says something got slow. Not filing or
|
||||
triaging a reported bug -> `triage`. Not test-first feature work -> `tdd`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Diagnose
|
||||
|
||||
A discipline for hard bugs. Skip phases only when explicitly justified.
|
||||
|
||||
When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
|
||||
When exploring the codebase, use the domain glossary for a clear mental model of the relevant modules, and check ADRs in the area.
|
||||
|
||||
## Phase 1 — Build a feedback loop
|
||||
|
||||
|
||||
@@ -1,27 +0,0 @@
|
||||
# grill-me
|
||||
|
||||
Interview the user relentlessly about a plan or design until the decision tree is fully resolved.
|
||||
|
||||
## What it does
|
||||
|
||||
Turns the agent into an interviewer rather than an implementer. It walks the design tree branch by branch, resolving dependencies between decisions one at a time, and offers its own recommended answer alongside each question so the user has something concrete to push against. Two rules give it its shape: **one question at a time**, and **never ask what the codebase can answer** — if a question is settleable by reading the code, the agent goes and reads the code instead of spending the user's attention on it.
|
||||
|
||||
## Composition
|
||||
|
||||
This is the plain grilling loop, with no documentation side effects. The sibling `grill-with-docs` skill runs the same interview but additionally challenges answers against the project's `CONTEXT.md` glossary and existing ADRs, and writes decisions back into those files as they crystallise. Reach for that one when the project has a domain model worth defending; reach for this one when it does not, or when nothing should be written down yet.
|
||||
|
||||
`triage` composes the documented variant, not this one, when an issue needs fleshing out.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/grill-me
|
||||
```
|
||||
|
||||
Describe the plan or design to be stress-tested. Expect questions one at a time, each with a recommended answer.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — the interview instruction, the one-question-at-a-time rule, and the explore-instead-of-asking rule |
|
||||
@@ -1,37 +0,0 @@
|
||||
# grill-with-docs
|
||||
|
||||
The grilling interview, run against the project's domain model — and writing decisions back into `CONTEXT.md` and ADRs as they land.
|
||||
|
||||
## What it does
|
||||
|
||||
Runs the same relentless one-question-at-a-time interview as `grill-me`, with the project's own documentation as an active participant. During codebase exploration it also locates the domain documentation — a root `CONTEXT.md` and `docs/adr/`, or a `CONTEXT-MAP.md` pointing at per-context glossaries and ADR directories in a multi-context repo — and then uses it five ways:
|
||||
|
||||
- **Challenges terms against the glossary.** When the user's usage conflicts with what `CONTEXT.md` already defines, that is raised immediately rather than absorbed.
|
||||
- **Sharpens fuzzy language** by proposing a precise canonical term ("you're saying 'account' — do you mean the Customer or the User?").
|
||||
- **Stress-tests domain relationships with concrete scenarios**, inventing edge cases that force the user to be precise about where one concept ends and the next begins.
|
||||
- **Cross-references claims against the code**, and surfaces contradictions between what the user says happens and what the code does.
|
||||
- **Updates `CONTEXT.md` inline**, the moment a term is resolved, rather than batching changes to the end of the session where they get lost.
|
||||
|
||||
Files are created lazily — only when there is something real to write.
|
||||
|
||||
ADRs are offered *sparingly*, and only when all three tests pass: the decision is hard to reverse, it would surprise a future reader without the context, and it was a genuine trade-off with real alternatives. Missing any one of the three means no ADR.
|
||||
|
||||
## Composition
|
||||
|
||||
`grill-me` is the same interview without the documentation side effects — use it when there is no domain model to defend or nothing should be written down yet. `triage` composes this skill (not `grill-me`) at step 4 when an issue needs fleshing out. `improve-codebase-architecture` runs its own grilling loop and borrows this skill's `CONTEXT.md` and ADR discipline for the decisions that come out of it.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/grill-with-docs
|
||||
```
|
||||
|
||||
Describe the plan or design. Expect questions one at a time, each with a recommended answer, and expect `CONTEXT.md` to be edited during the session rather than after it.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The interview instruction plus the domain-awareness rules: file layout discovery, the five during-session behaviours, and the three-part ADR test |
|
||||
| `references/context-format.md` | Cited when a term is resolved: the structure of a `CONTEXT.md` and how to write a Language entry |
|
||||
| `references/adr-format.md` | Cited when an ADR is offered: `docs/adr/` naming, sequential numbering, and the ADR template |
|
||||
@@ -1,36 +0,0 @@
|
||||
# improve-codebase-architecture
|
||||
|
||||
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones.
|
||||
|
||||
## What it does
|
||||
|
||||
Looks for places where a codebase is hard to understand, hard to test, or hard for an agent to navigate, and proposes refactors that concentrate behaviour behind smaller interfaces. It runs in three stages:
|
||||
|
||||
1. **Explore.** Reads the domain glossary and any ADRs in the area first, then walks the codebase with an `Explore` sub-agent — organically, noting friction rather than applying fixed heuristics. The **deletion test** is the filter: imagine deleting the module; if complexity vanishes it was a pass-through, if complexity reappears across N callers it was earning its keep.
|
||||
2. **Present candidates.** A numbered list, each with files, problem, solution and benefits — benefits stated in terms of *locality* and *leverage* and of how tests would improve. No interfaces are proposed yet; the user picks one.
|
||||
3. **Grilling loop.** Walks the design tree for the chosen candidate, with documentation side effects landing inline as decisions crystallise.
|
||||
|
||||
The skill is opinionated about vocabulary, and that is the point: **module, interface, implementation, depth, seam, adapter, leverage, locality**, used exactly, with no drift into "component", "service", "API" or "boundary". Domain nouns come from `CONTEXT.md`, architecture nouns from `references/language.md` — so a proposal reads as "the Order intake module", never "the FooBarHandler".
|
||||
|
||||
ADRs are treated as decisions not to be re-litigated. A candidate that contradicts one is surfaced only when the friction is real enough to warrant reopening it, and is marked as such.
|
||||
|
||||
## Composition
|
||||
|
||||
`diagnose` hands off here when a bug's post-mortem concludes that no correct test seam exists, or that callers are tangled — the recommendation is made after the fix is in, not before. The grilling loop follows `grill-with-docs`'s discipline for `CONTEXT.md` entries and ADR offers, and `SKILL.md` names that skill's format documents directly.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/improve-codebase-architecture
|
||||
```
|
||||
|
||||
Point at a codebase or an area of one. Expect a numbered candidate list and a "which of these would you like to explore?" before any interface design happens.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Condensed glossary, key principles, and the three-stage process |
|
||||
| `references/language.md` | Cited throughout `SKILL.md`: full definitions of every term, the words each one replaces, and the full principle list |
|
||||
| `references/interface-design.md` | Read at stage 3 when the user wants alternative interfaces explored: the parallel sub-agent "Design It Twice" pattern, framing the problem space, and the per-agent design constraints |
|
||||
| `references/deepening.md` | Cited from `references/interface-design.md`: how to deepen a cluster of shallow modules safely, the four dependency categories (in-process, local-substitutable, remote-but-owned, true external), seam discipline, and the replace-don't-layer testing strategy |
|
||||
@@ -7,7 +7,7 @@ description: >
|
||||
into deep ones, informed by `CONTEXT.md` and `docs/adr/`. Not debugging a
|
||||
failure -> `diagnose`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Improve Codebase Architecture
|
||||
@@ -41,7 +41,7 @@ This skill is _informed_ by the project's domain model. The domain language give
|
||||
|
||||
### 1. Explore
|
||||
|
||||
Read the project's domain glossary and any ADRs in the area you're touching first.
|
||||
Read the domain glossary and any ADRs in the area first.
|
||||
|
||||
Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
|
||||
|
||||
|
||||
@@ -1,32 +0,0 @@
|
||||
# prototype
|
||||
|
||||
Build a throwaway prototype that answers one design question — either a runnable terminal app or several UI variations.
|
||||
|
||||
## What it does
|
||||
|
||||
Treats a prototype as **throwaway code that answers a question**, and lets the question decide the artifact. `SKILL.md` opens with a two-row dispatch table and the run resolves exactly one row before doing anything else:
|
||||
|
||||
- *"Does this logic / state model feel right?"* → a tiny interactive terminal app that pushes the state machine through the cases that are hard to reason about on paper.
|
||||
- *"What should this look like?"* → several radically different UI variations on one route, switchable from a floating bottom bar via a URL search param.
|
||||
|
||||
The two branches produce fundamentally different artifacts, so picking wrong wastes the whole prototype. When the question is genuinely ambiguous and the user is unreachable, the skill defaults on the shape of the surrounding code (backend module → logic, page or component → UI) and states the assumption at the top of the prototype rather than silently choosing.
|
||||
|
||||
Six rules apply to both branches: throwaway and visibly named as such, one command to run, no persistence by default, no polish, surface the full state after every action or variant switch, and delete or absorb the prototype when it is done. The *answer* is the only durable output — the skill captures it in a commit message, ADR, issue or `NOTES.md` before the code is deleted.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/prototype
|
||||
```
|
||||
|
||||
State the design question. For production code, use `tdd`; for talking a design through without building anything, use `grill-me`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The branch dispatch table and the rules that apply to both branches |
|
||||
| `references/logic.md` | The logic branch, read only when that row is selected: when it is the right shape, and how to build the interactive terminal app |
|
||||
| `references/ui.md` | The UI branch, read only when that row is selected: when it is the right shape, and how to build and switch between the variations |
|
||||
|
||||
Each reference is self-contained — a run reads one of the two, never both.
|
||||
@@ -1,31 +0,0 @@
|
||||
# research
|
||||
|
||||
Research a tool, library or API from canonical documentation into a directory of structured per-topic reference files.
|
||||
|
||||
## What it does
|
||||
|
||||
Runs a six-step pipeline: scope against the working directory (what version is actually in use, what is already documented), resolve the topic through Context7, websearch for canonical docs covering whatever Context7 missed, read those sources, deepen one level into the links worth following, then write one markdown file per topic area plus a `sources.md` provenance record.
|
||||
|
||||
Four gotchas at the top of `SKILL.md` shape the whole run, and each exists because of a specific failure: the output path is never inferred (a guessed destination scatters a directory's worth of files through someone's source tree); nothing is written outside that path; no empty topic file is ever written (a stub `troubleshooting.md` reads downstream as researched and closed); and a Context7 "no results", redirect or header-only response does not count as coverage. If no topic area has content, the run writes nothing at all — `sources.md` included — and reports what it searched.
|
||||
|
||||
The frontmatter pins `model: sonnet` and a closed `allowed-tools` list. Notably it grants no subagent tool, so every `WebFetch` is serial and each fetched page lands in the run's own context — which is why steps 4 and 5 insist on reducing each page to notes before fetching the next, and cap deepening at roughly ten extra pages.
|
||||
|
||||
## Composition
|
||||
|
||||
Both reference files are read on condition, never on every run — `SKILL.md` inlines the minimum each step needs (the seven default topic areas at step 1, the four `sources.md` field names and the topic-file frontmatter keys at step 6) and sends the run to the reference only for what it does not carry. Those four field names are matched literally by the downstream provenance validator, so prose written in their place parses as nothing and the check passes having verified nothing — which is why they are inlined rather than deferred.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/research
|
||||
```
|
||||
|
||||
Name the topic and the output path — the skill will stop and ask if the path is missing. Supplying starting URLs is treated as a deliberate source choice and skips Context7 resolution and discovery. For documentation derived from existing code or specs, use `write-docs`; for a bug or incident, use `diagnose`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The four gotchas and the six research steps |
|
||||
| `references/topics.md` | Read at Step 1 only when what belongs in a default topic is unclear or a custom topic is needed: the per-topic coverage table and the custom-topic naming rule |
|
||||
| `references/file-format.md` | Read at Step 6 only when the inlined field names do not settle the case: slug derivation, the Context7 slug and URL convention, and what belongs in a topic body |
|
||||
@@ -1,32 +0,0 @@
|
||||
# tdd
|
||||
|
||||
Test-driven development as a strict red-green-refactor loop, one behaviour at a time.
|
||||
|
||||
## What it does
|
||||
|
||||
Two convictions drive this skill. The first is about what a test is for: tests verify behaviour through public interfaces, not implementation details. A good test reads like a specification ("user can checkout with valid cart") and survives refactors because it does not care about internal structure. The warning sign for a bad one is precise — the test breaks when you refactor but behaviour has not changed.
|
||||
|
||||
The second is an explicit anti-pattern: **do not write all the tests first, then all the implementation.** Horizontal slicing treats RED as "write every test" and GREEN as "write every implementation", and it produces tests of *imagined* behaviour — tests of the shape of things, insensitive to real change, committed to before the implementation was understood. The correct shape is vertical: one test → one implementation → repeat, each cycle informed by what the last one taught you.
|
||||
|
||||
The workflow is four stages: plan (confirm the interface and which behaviours matter, with the user — you cannot test everything), fire a tracer bullet (one test proving the path works end to end), loop incrementally one behaviour at a time, then refactor once everything is green. Refactoring while RED is forbidden.
|
||||
|
||||
Codebase exploration uses the project's domain glossary, so test names and interface vocabulary match the project's language, and ADRs in the area are respected.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/tdd
|
||||
```
|
||||
|
||||
Describe the feature or bug. Expect the skill to ask what the public interface should look like and which behaviours matter most before any code is written. For diagnosing an existing bug rather than building test-first, use `diagnose`; for throwaway exploratory code, use `prototype`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Philosophy, the horizontal-slicing anti-pattern, the four-stage workflow, and the per-cycle checklist |
|
||||
| `references/tests.md` | Cited from Philosophy: worked good and bad test examples |
|
||||
| `references/mocking.md` | Cited from Philosophy: mock at system boundaries only, and what not to mock |
|
||||
| `references/deep-modules.md` | Cited from stage 1: what a deep module is (small interface, large implementation) and why it is the design to aim for |
|
||||
| `references/interface-design.md` | Cited from stage 1: designing interfaces for testability, starting with accepting dependencies rather than creating them |
|
||||
| `references/refactoring.md` | Cited from stage 4: the refactor-candidate checklist — duplication, long methods, shallow modules, feature envy, primitive obsession |
|
||||
@@ -5,7 +5,7 @@ description: >
|
||||
red-green-refactor loop, one behaviour at a time. Not diagnosing an existing
|
||||
bug -> `diagnose`. Not throwaway exploratory code -> `prototype`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Test-Driven Development
|
||||
@@ -49,7 +49,7 @@ RIGHT (vertical):
|
||||
|
||||
### 1. Planning
|
||||
|
||||
When exploring the codebase, use the project's domain glossary so that test names and interface vocabulary match the project's language, and respect ADRs in the area you're touching.
|
||||
When exploring the codebase, use the domain glossary so test names and interface vocabulary match the project's language, and respect ADRs in the area.
|
||||
|
||||
Before writing any code:
|
||||
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
# triage
|
||||
|
||||
Move issues on the project issue tracker through a small state machine of triage roles.
|
||||
|
||||
## What it does
|
||||
|
||||
Gives issue triage an explicit state model and a fixed set of moves. Every issue carries exactly one **category** role (`bug`, `enhancement`) and one **state** role (`needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`); conflicting state roles are flagged to the maintainer before anything else happens. Unlabeled issues normally enter at `needs-triage`; `needs-info` returns there once the reporter replies. The maintainer can override at any point, and unusual transitions are questioned rather than executed silently.
|
||||
|
||||
A run does one of three things depending on what the maintainer asks for:
|
||||
|
||||
- **Show what needs attention** — three buckets, oldest first: unlabeled, `needs-triage`, and `needs-info` with reporter activity since the last triage notes.
|
||||
- **Triage a specific issue** — gather context (including prior triage notes, so resolved questions are not re-asked, and `.out-of-scope/` records that resemble the issue), recommend a category and state with reasoning, attempt reproduction for bugs *before* any grilling, run a `grill-with-docs` session if the issue needs fleshing out, then apply the outcome.
|
||||
- **Quick state override** — "move #42 to ready-for-agent" is trusted and applied directly, skipping grilling, after confirming the exact changes.
|
||||
|
||||
Two hard rules: every comment or issue the skill posts during triage must open with the AI-generated disclaimer, and the canonical role names above are *not* necessarily the label strings in the tracker — each is resolved against the tracker's live label set before it is applied, and a name with no counterpart there is reported to the maintainer as a gap rather than guessed at.
|
||||
|
||||
## Composition
|
||||
|
||||
`grill-with-docs` is invoked at step 4 when an issue needs fleshing out; whatever that session establishes is carried into the triage notes so the work is not lost. The reverse direction also exists: `diagnose` names this skill as the place to send a *reported* bug that needs filing rather than debugging.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/triage
|
||||
```
|
||||
|
||||
Then describe what you want in natural language — "show me anything that needs my attention", "let's look at #42", "move #42 to ready-for-agent", "what's ready for agents to pick up?".
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The roles and state machine, the three invocation modes, the needs-info template, and how to resume a prior session |
|
||||
| `references/agent-brief.md` | Cited when an issue moves to `ready-for-agent` (and reused for `ready-for-human`): how to write a brief that stays durable for weeks while the codebase moves under it — describe interfaces and behavioural contracts, not line numbers |
|
||||
| `references/out-of-scope.md` | Cited when an enhancement is closed `wontfix` and when checking for prior rejections: how the `.out-of-scope/` knowledge base is laid out and what it is for — institutional memory, and deduplication against re-litigated requests |
|
||||
@@ -5,7 +5,7 @@ description: >
|
||||
tracker's triage states, or an issue prepared for an AFK agent. Not debugging
|
||||
the bug itself -> `diagnose`. Not fleshing out a design -> `grill-with-docs`.
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
# Triage
|
||||
@@ -65,7 +65,7 @@ Show counts and a one-line summary per issue. Let the maintainer pick.
|
||||
|
||||
## Triage a specific issue
|
||||
|
||||
1. **Gather context.** Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the project's domain glossary, respecting ADRs in the area. Read `.out-of-scope/*.md` and surface any prior rejection that resembles this issue.
|
||||
1. **Gather context.** Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the domain glossary, respecting ADRs in the area. Read `.out-of-scope/*.md` and surface any prior rejection that resembles this issue.
|
||||
|
||||
2. **Recommend.** Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the issue. Wait for direction.
|
||||
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
# write-docs
|
||||
|
||||
Produce technical documentation derived from code and spec, one section at a time, with a confirmation gate on every section.
|
||||
|
||||
## What it does
|
||||
|
||||
Casts the agent as a technical writer with one non-negotiable constraint: **every claim must be traceable to a source file line, a spec section, or an explicit user statement.** Nothing is invented, and behaviour that genuinely cannot be documented from the available sources is marked out-of-scope rather than explained away.
|
||||
|
||||
The process is eight steps — identify scope, read and extract, gap check, draft section by section, confirmation gate, delta summary, reader testing, finalise — and several of them are deliberately gated on the human:
|
||||
|
||||
- Files are read only after the user approves them by name. The skill may propose candidates; it waits.
|
||||
- The **gap check** presents what the code does say and asks the user to fill only what it does not: caller intent, error-handling rationale, non-obvious side effects.
|
||||
- No section is finalised until the full revised text has been shown. The skill never gates on output the user has not seen, and never reprints the whole document — all edits are surgical.
|
||||
- **Reader testing** predicts 5–10 questions a target reader would ask, then spawns a sub-agent that receives only the finished doc and the questions — no source files. If the doc cannot answer them, neither can the sub-agent, and the run loops back to drafting.
|
||||
|
||||
Summary and overview sections are written last, once the detail sections are stable.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/write-docs
|
||||
```
|
||||
|
||||
Name the files or modules to document, the target audience (developer / user / contributor / internal), and the documentation type (reference, guide, README section, inline comment, changelog entry). For a PRD, ADR or decision doc, use `grill-me` or `grill-with-docs` instead — those have dedicated handling.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — role, use/do-not-use boundaries, required inputs, constraints, the eight-step process, output format, failure handling, and a nine-item self-check |
|
||||
@@ -1,25 +0,0 @@
|
||||
# zoom-out
|
||||
|
||||
Ask the agent to go up a layer of abstraction and map the modules and callers around unfamiliar code.
|
||||
|
||||
## What it does
|
||||
|
||||
A single-purpose prompt for the moment you land in a part of the codebase you do not know. Instead of answering at the level of the file in front of it, the agent climbs one layer and produces a map of the relevant modules and their callers — and names them using the project's own domain glossary vocabulary, so the map lines up with the language the rest of the repo already uses.
|
||||
|
||||
## Hand-invoked only
|
||||
|
||||
`SKILL.md` sets `disable-model-invocation: true`, so the router never selects this skill on its own and no other skill can hand off to it. It runs when the human asks for it. That also means its description is written as one plain human-facing sentence — it carries no trigger phrasing or boundary clause, because nothing routes on it.
|
||||
|
||||
## Usage
|
||||
|
||||
```text
|
||||
/zoom-out
|
||||
```
|
||||
|
||||
Best used with the unfamiliar code already in context — the skill widens the view around what you are looking at rather than picking a starting point for you.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | The whole skill — a single instruction, no supporting files |
|
||||
@@ -3,7 +3,7 @@ name: zoom-out
|
||||
description: Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
|
||||
disable-model-invocation: true
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.1"
|
||||
---
|
||||
|
||||
I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary vocabulary.
|
||||
I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary.
|
||||
|
||||
@@ -1,38 +0,0 @@
|
||||
# agentsmd-audit
|
||||
|
||||
Audit a target repo's AGENTS.md file(s) for embedded secrets, structural completeness, and drift.
|
||||
|
||||
## What it does
|
||||
|
||||
Runs a single combined pass across every AGENTS.md file in a repo (root and any nested monorepo files): flags embedded secrets/credentials, checks structure against the agents.md common-sections checklist, and resolves referenced commands/paths against the actual repo to catch stale documentation. Outputs a compact findings report — findings only, grouped by dimension, each with Why and Fix. Never inspects provider-specific adapter files (CLAUDE.md, etc.) and never writes or fixes anything.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/agentsmd-audit
|
||||
```
|
||||
|
||||
Provide the path to the repo root to audit when invoking.
|
||||
|
||||
Also invoke it proactively after `agentsmd-author` creates or updates an AGENTS.md, or after a
|
||||
hand-edit made outside `agentsmd-author` — the audit is what confirms the result is safe to commit.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `scripts/validate-secrets.sh` | Scans AGENTS.md files for embedded secrets, API keys, tokens, connection strings |
|
||||
| `scripts/validate-structure.sh` | Checks for empty/placeholder content, common-sections checklist, nested-vs-root duplication |
|
||||
| `scripts/validate-drift.sh` | Resolves referenced npm/make commands and file paths against the repo |
|
||||
| `references/sources.md` | Provenance record — sources that informed this skill and which files each contributed to |
|
||||
| `scripts/README.md` | Directory documentation for `scripts/` |
|
||||
| `tests/README.md` | (source-only) Bats test dependency and run instructions |
|
||||
| `tests/validate-secrets.bats` | (source-only) Bats test suite for `scripts/validate-secrets.sh` |
|
||||
| `tests/validate-structure.bats` | (source-only) Bats test suite for `scripts/validate-structure.sh` |
|
||||
| `tests/validate-drift.bats` | (source-only) Bats test suite for `scripts/validate-drift.sh` |
|
||||
|
||||
Rows marked **(source-only)** exist in the authoring source (`.apm/skills/agentsmd-audit/`) but are
|
||||
not present in an installed plugin: the repo's `scripts/sync-plugin-content.sh` strips
|
||||
`<category>/<name>/tests` when it generates the flat mirror, because these are dev-time fixtures no
|
||||
plugin host needs to discover (ADR-0017). Run them from a repo checkout, not from an install.
|
||||
@@ -1,27 +0,0 @@
|
||||
# agentsmd-author
|
||||
|
||||
Create or update a target repo's AGENTS.md file(s) by exploring the repo for real conventions.
|
||||
|
||||
## What it does
|
||||
|
||||
Explores a target repo (package manager scripts, Makefile/task runner, CI config, linter config, existing docs) and writes or updates `AGENTS.md` with only verified commands and conventions — never invented ones. Supports nested monorepo placement, following the agents.md standard's nearest-file-wins precedence. Closes every run by invoking `agentsmd-audit` inline, and hands off to `provider-adapter-author` when an existing provider-specific file (CLAUDE.md, etc.) now duplicates content AGENTS.md owns.
|
||||
|
||||
## Before you start
|
||||
|
||||
The `agentsmd-audit` skill must be available (co-installed in the `core` plugin) — this skill invokes it as a mandatory closeout step.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/agentsmd-author
|
||||
```
|
||||
|
||||
Provide the target repo root (defaults to the current directory) and, if relevant, which subdirectory should get a nested AGENTS.md.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/content-guide.md` | Section-by-section AGENTS.md content guidance, a worked example, and monorepo/nested-file precedence rules |
|
||||
| `references/sources.md` | Provenance record — sources that informed this skill and which files each contributed to |
|
||||
@@ -1,36 +0,0 @@
|
||||
# provider-adapter-author
|
||||
|
||||
Convert a target repo's provider-specific instruction file (CLAUDE.md, .cursor/rules, copilot-instructions.md, etc.) into a thin adapter over AGENTS.md.
|
||||
|
||||
## What it does
|
||||
|
||||
Detects a provider-specific AI instruction file in a target repo, diffs it against the repo's `AGENTS.md`, and rewrites it down to a minimal reference — an `@AGENTS.md`-style import for providers that support one, or a text pointer for those that don't — plus only genuinely provider-specific additions. Self-validates its own output with a bundled deterministic script (no LLM judgment, no separate audit skill) before finishing.
|
||||
|
||||
## Before you start
|
||||
|
||||
The target repo must already have an `AGENTS.md`. If it doesn't, run `agentsmd-author` first — this skill never creates or edits `AGENTS.md` itself.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/provider-adapter-author
|
||||
```
|
||||
|
||||
Provide the path to the provider-specific file to convert (and the target repo root, if not inferable). Can be invoked directly, or composed into by `agentsmd-author` when it detects an existing provider file with content overlapping AGENTS.md.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/provider-matrix.md` | Loaded at Step 1 before searching, unless the target is already a known root `CLAUDE.md`: known files per provider, which ones resolve a cross-file import, the validator flag each needs, and the rule that a standalone run and a run composed into by `agentsmd-author` behave identically |
|
||||
| `references/sources.md` | Provenance record — the in-repo ADR precedent this skill's design is modeled on |
|
||||
| `scripts/validate-adapter.sh` | Self-check gate: reference to AGENTS.md present, no excessive duplication, adapter stays thin |
|
||||
| `scripts/README.md` | Directory documentation for `scripts/` |
|
||||
| `tests/README.md` | (source-only) Bats test dependency and run instructions |
|
||||
| `tests/validate-adapter.bats` | (source-only) Bats test suite for `scripts/validate-adapter.sh` |
|
||||
|
||||
Rows marked **(source-only)** exist in the authoring source (`.apm/skills/provider-adapter-author/`)
|
||||
but are not present in an installed plugin: the repo's `scripts/sync-plugin-content.sh` strips
|
||||
`<category>/<name>/tests` when it generates the flat mirror, because these are dev-time fixtures no
|
||||
plugin host needs to discover (ADR-0017). Run them from a repo checkout, not from an install.
|
||||
@@ -1,38 +0,0 @@
|
||||
# agentsmd-audit
|
||||
|
||||
Audit a target repo's AGENTS.md file(s) for embedded secrets, structural completeness, and drift.
|
||||
|
||||
## What it does
|
||||
|
||||
Runs a single combined pass across every AGENTS.md file in a repo (root and any nested monorepo files): flags embedded secrets/credentials, checks structure against the agents.md common-sections checklist, and resolves referenced commands/paths against the actual repo to catch stale documentation. Outputs a compact findings report — findings only, grouped by dimension, each with Why and Fix. Never inspects provider-specific adapter files (CLAUDE.md, etc.) and never writes or fixes anything.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/agentsmd-audit
|
||||
```
|
||||
|
||||
Provide the path to the repo root to audit when invoking.
|
||||
|
||||
Also invoke it proactively after `agentsmd-author` creates or updates an AGENTS.md, or after a
|
||||
hand-edit made outside `agentsmd-author` — the audit is what confirms the result is safe to commit.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `scripts/validate-secrets.sh` | Scans AGENTS.md files for embedded secrets, API keys, tokens, connection strings |
|
||||
| `scripts/validate-structure.sh` | Checks for empty/placeholder content, common-sections checklist, nested-vs-root duplication |
|
||||
| `scripts/validate-drift.sh` | Resolves referenced npm/make commands and file paths against the repo |
|
||||
| `references/sources.md` | Provenance record — sources that informed this skill and which files each contributed to |
|
||||
| `scripts/README.md` | Directory documentation for `scripts/` |
|
||||
| `tests/README.md` | (source-only) Bats test dependency and run instructions |
|
||||
| `tests/validate-secrets.bats` | (source-only) Bats test suite for `scripts/validate-secrets.sh` |
|
||||
| `tests/validate-structure.bats` | (source-only) Bats test suite for `scripts/validate-structure.sh` |
|
||||
| `tests/validate-drift.bats` | (source-only) Bats test suite for `scripts/validate-drift.sh` |
|
||||
|
||||
Rows marked **(source-only)** exist in the authoring source (`.apm/skills/agentsmd-audit/`) but are
|
||||
not present in an installed plugin: the repo's `scripts/sync-plugin-content.sh` strips
|
||||
`<category>/<name>/tests` when it generates the flat mirror, because these are dev-time fixtures no
|
||||
plugin host needs to discover (ADR-0017). Run them from a repo checkout, not from an install.
|
||||
@@ -1,27 +0,0 @@
|
||||
# agentsmd-author
|
||||
|
||||
Create or update a target repo's AGENTS.md file(s) by exploring the repo for real conventions.
|
||||
|
||||
## What it does
|
||||
|
||||
Explores a target repo (package manager scripts, Makefile/task runner, CI config, linter config, existing docs) and writes or updates `AGENTS.md` with only verified commands and conventions — never invented ones. Supports nested monorepo placement, following the agents.md standard's nearest-file-wins precedence. Closes every run by invoking `agentsmd-audit` inline, and hands off to `provider-adapter-author` when an existing provider-specific file (CLAUDE.md, etc.) now duplicates content AGENTS.md owns.
|
||||
|
||||
## Before you start
|
||||
|
||||
The `agentsmd-audit` skill must be available (co-installed in the `core` plugin) — this skill invokes it as a mandatory closeout step.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/agentsmd-author
|
||||
```
|
||||
|
||||
Provide the target repo root (defaults to the current directory) and, if relevant, which subdirectory should get a nested AGENTS.md.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/content-guide.md` | Section-by-section AGENTS.md content guidance, a worked example, and monorepo/nested-file precedence rules |
|
||||
| `references/sources.md` | Provenance record — sources that informed this skill and which files each contributed to |
|
||||
@@ -1,36 +0,0 @@
|
||||
# provider-adapter-author
|
||||
|
||||
Convert a target repo's provider-specific instruction file (CLAUDE.md, .cursor/rules, copilot-instructions.md, etc.) into a thin adapter over AGENTS.md.
|
||||
|
||||
## What it does
|
||||
|
||||
Detects a provider-specific AI instruction file in a target repo, diffs it against the repo's `AGENTS.md`, and rewrites it down to a minimal reference — an `@AGENTS.md`-style import for providers that support one, or a text pointer for those that don't — plus only genuinely provider-specific additions. Self-validates its own output with a bundled deterministic script (no LLM judgment, no separate audit skill) before finishing.
|
||||
|
||||
## Before you start
|
||||
|
||||
The target repo must already have an `AGENTS.md`. If it doesn't, run `agentsmd-author` first — this skill never creates or edits `AGENTS.md` itself.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/provider-adapter-author
|
||||
```
|
||||
|
||||
Provide the path to the provider-specific file to convert (and the target repo root, if not inferable). Can be invoked directly, or composed into by `agentsmd-author` when it detects an existing provider file with content overlapping AGENTS.md.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/provider-matrix.md` | Loaded at Step 1 before searching, unless the target is already a known root `CLAUDE.md`: known files per provider, which ones resolve a cross-file import, the validator flag each needs, and the rule that a standalone run and a run composed into by `agentsmd-author` behave identically |
|
||||
| `references/sources.md` | Provenance record — the in-repo ADR precedent this skill's design is modeled on |
|
||||
| `scripts/validate-adapter.sh` | Self-check gate: reference to AGENTS.md present, no excessive duplication, adapter stays thin |
|
||||
| `scripts/README.md` | Directory documentation for `scripts/` |
|
||||
| `tests/README.md` | (source-only) Bats test dependency and run instructions |
|
||||
| `tests/validate-adapter.bats` | (source-only) Bats test suite for `scripts/validate-adapter.sh` |
|
||||
|
||||
Rows marked **(source-only)** exist in the authoring source (`.apm/skills/provider-adapter-author/`)
|
||||
but are not present in an installed plugin: the repo's `scripts/sync-plugin-content.sh` strips
|
||||
`<category>/<name>/tests` when it generates the flat mirror, because these are dev-time fixtures no
|
||||
plugin host needs to discover (ADR-0017). Run them from a repo checkout, not from an install.
|
||||
@@ -40,7 +40,7 @@ Sub-skills carry their own local copies of these rules for humans who invoke the
|
||||
|
||||
When invoked, you:
|
||||
1. Parse the incoming workflow request (operation type, parameters, context overrides)
|
||||
2. Check safety gates: if the operation is destructive (force-push, branch deletion, rebase with history loss, force-checkout) and the request lacks explicit `confirm: true`, fail immediately with "requires explicit confirmation"; force-push to `main`/`master` is refused outright regardless of `confirm`
|
||||
2. Check safety gates: a destructive operation (force-push, branch deletion, history-losing rebase, force-checkout) without `confirm: true` fails immediately with "requires explicit confirmation"; force-push to `main`/`master` is refused outright regardless of `confirm`
|
||||
3. Route to the appropriate domain skill: `git-commits`, `git-branches`, `git-history`, `git-submodules`, `git-worktrees`, `git-remotes`
|
||||
4. Manage session context: carry forward the current branch, workflow intent, and configuration, passing explicitly to each skill
|
||||
5. Handle error recovery: for recoverable failures (merge conflicts, push rejections, auth issues), attempt automatic recovery; if unrecoverable, fail gracefully with actionable diagnostics
|
||||
@@ -63,11 +63,10 @@ When invoked, you:
|
||||
1. Validate the request structure and check if operation is known
|
||||
2. Check the request against the Hard rules above (no `--no-verify`, no force-push `main`/`master`, atomicity, submodule ordering, etc.) — refuse outright on violation, independent of `confirm`
|
||||
3. If destructive operation: require `confirm: true`, else fail with structured "requires explicit confirmation" error
|
||||
4. Read plugin config from `.claude/plugins/git/config.json` if present — see `config.example.json` in the plugin root for the expected shape (`branching_pattern`, `commit_style`, `rebase_strategy`) — or fall back to sensible defaults
|
||||
5. Invoke the appropriate skill via `Skill` or direct bash call with the operation, parameters, context, and config. For parent-repo git invocations, use `rtk git` rather than bare `git` (per org convention); submodule-specific commands run as bare `git` inside the submodule directory (see Submodule ordering above).
|
||||
6. Catch and handle git errors: attempt automatic recovery (offer rebase strategies for conflicts, suggest `--force-with-lease` for rejections)
|
||||
7. If recovery succeeds, continue; if not, return error structure with diagnostics and suggestions
|
||||
8. Aggregate all outputs and return as structured JSON
|
||||
4. Invoke the appropriate skill via `Skill` or direct bash call with the operation, parameters, and context — each domain skill infers its own branching pattern and conventions (e.g. `git-branches` from `develop`/`release/*` branch presence) rather than reading shared config. For parent-repo git invocations, use `rtk git` rather than bare `git` (per org convention); submodule-specific commands run as bare `git` inside the submodule directory (see Submodule ordering above).
|
||||
5. Catch and handle git errors: attempt automatic recovery (offer rebase strategies for conflicts, suggest `--force-with-lease` for rejections)
|
||||
6. If recovery succeeds, continue; if not, return error structure with diagnostics and suggestions
|
||||
7. Aggregate all outputs and return as structured JSON
|
||||
|
||||
## Output
|
||||
|
||||
@@ -77,8 +76,7 @@ When invoked, you:
|
||||
"operation": "<operation_name>",
|
||||
"result": {
|
||||
"output": "<command output or result>",
|
||||
"context": { "current_branch": "...", "workflow_intent": "..." },
|
||||
"applied_config": { "commit_style": "...", "rebase_strategy": "..." }
|
||||
"context": { "current_branch": "...", "workflow_intent": "..." }
|
||||
},
|
||||
"error": {
|
||||
"message": "<human-readable error>",
|
||||
|
||||
@@ -1,34 +0,0 @@
|
||||
# git-branches
|
||||
|
||||
Manage the full lifecycle of git branches — create, switch, delete, rename, track, merge, and compare feature/hotfix/release branches under GitHub Flow or Gitflow.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles branch operations within the git workflow suite. It creates branches following GitHub Flow or Gitflow conventions (configurable), switches and tracks branches, handles safe deletion with unmerged-work checks, and retrieves branch intent metadata for use by other skills (e.g., commit message context). It returns structured results suitable for agent composition.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-branches
|
||||
```
|
||||
|
||||
Describe your branch task: create a feature/hotfix/release branch, switch, delete, rename, track, merge, or compare two branches. The skill will determine the branching pattern (GitHub Flow or Gitflow) from config or repo state and handle safety checks for destructive operations.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/branch-patterns.md` | Loaded when a branch's base, name prefix, or merge rule depends on GitHub Flow vs. Gitflow |
|
||||
| `references/branch-operations.md` | Loaded when running a create/switch/delete/rename/track/list/stash action, or resolving `get-intent` |
|
||||
| `references/merging.md` | Loaded when merging one branch into another or resolving merge conflicts |
|
||||
| `references/comparing-branches.md` | Loaded when comparing two branches or finding where they diverged |
|
||||
| `references/orchestrator-contract.md` | Loaded when `git-orchestrate` or another calling agent supplies a structured request rather than prose |
|
||||
| `references/sources.md` | Research sources backing the branching/gitflow guidance |
|
||||
|
||||
## Composition
|
||||
|
||||
`git-orchestrate` calls this skill for the branch step of a multi-step workflow and parses its
|
||||
structured result. Revert is `git-history`'s; commit authoring, rebase, reset and cherry-pick are
|
||||
`git-commits`'; deleting a remote branch is `git-remotes`'; branch operations against a
|
||||
Gitea-hosted remote are `gitea-branches`'.
|
||||
@@ -9,7 +9,7 @@ description: >
|
||||
Not a Gitea remote's branches -> `gitea-branches`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.4"
|
||||
category: git
|
||||
source_keys:
|
||||
- context7-git-htmldocs
|
||||
@@ -21,12 +21,12 @@ metadata:
|
||||
## Gotchas
|
||||
|
||||
- **Uncommitted changes abort a switch.** `git switch` refuses rather than clobbering conflicting local edits. Offer to stash and retry — forcing the checkout past it is how work disappears.
|
||||
- **A branch and a tag can carry the same name.** Detect it before acting — `git branch --list <name>` (bare, not `rtk`: rtk prints a phantom `* ` line even on no match, which reports every name as ambiguous — ADR-0023) and `rtk git tag --list <name>`; output from both means the name is ambiguous. Prefer `git switch` over `git checkout`, and where a command accepts either ref, disambiguate with `refs/heads/<name>` or `refs/tags/<name>`.
|
||||
- **`main` and `master` are a refusal, not a gate.** Force-pushing, force-deleting, or renaming them is rejected even when the caller passes `confirm: true` — no flag makes the remote's history recoverable. Offer a new branch instead.
|
||||
- **A branch and a tag can carry the same name.** Detect it before acting — `git branch --list <name>` (bare, not `rtk`: rtk prints a phantom `* ` line even on no match, which reports every name as ambiguous) and `rtk git tag --list <name>`; output from both means the name is ambiguous. Prefer `git switch` over `git checkout`, and where a command accepts either ref, disambiguate with `refs/heads/<name>` or `refs/tags/<name>`.
|
||||
- **`main`/`master` are a refusal, not a gate.** Force-pushing, force-deleting, or renaming either is rejected even with `confirm: true` — no flag recovers the remote's history. Offer a new branch instead.
|
||||
|
||||
## Step 1 — Determine the branching pattern
|
||||
|
||||
Read `branching_pattern` from the git plugin config (`.claude/plugins/git/config.json`; the plugin root's `config.example.json` shows the shape). Default: `github-flow`. With no config, infer Gitflow from the presence of a `develop` or `release/*` branch, and GitHub Flow otherwise.
|
||||
Infer the branching pattern from the repo: Gitflow if a `develop` or `release/*` branch exists, GitHub Flow otherwise (the default).
|
||||
|
||||
The two patterns are not mixable, and the wrong merge rule silently damages history. If the action touches a base branch, a name prefix, or a merge rule, read `references/branch-patterns.md`.
|
||||
|
||||
|
||||
@@ -45,10 +45,10 @@ past it: it shelves the working tree and index so the branch pointer can move.
|
||||
reports `No local changes to save` and stashes nothing. Bare `git stash` is `push` with no message.
|
||||
- **restore** — `git stash pop` applies the newest entry and deletes it. Bare, not `rtk`: on a
|
||||
conflict rtk prints only `FAILED: git stash pop` and swallows the conflict report the paragraph
|
||||
below tells you to read (ADR-0023). `rtk git stash apply stash@{n}`
|
||||
below tells you to read. `rtk git stash apply stash@{n}`
|
||||
applies without deleting, for replaying one shelf onto more than one branch.
|
||||
- **list** — `git stash list` — bare, not `rtk`: rtk prints `No stashes` where git prints nothing,
|
||||
so an empty-output test misfires (ADR-0023). `rtk git stash show -p stash@{n}` prints that entry's diff.
|
||||
so an empty-output test misfires. `rtk git stash show -p stash@{n}` prints that entry's diff.
|
||||
- **drop** — `rtk git stash drop stash@{n}` deletes one entry. `rtk git stash clear` deletes all of them
|
||||
and nothing recovers them — confirm before running it.
|
||||
- **branch from a stash** — `rtk git stash branch <branch> stash@{n}` creates a branch at the commit the
|
||||
|
||||
@@ -27,5 +27,5 @@ list the conflicted files, edit each to resolve its markers, then `rtk git add <
|
||||
|
||||
- `rtk git merge --abort` restores the pre-merge state.
|
||||
- `git mergetool` opens the configured merge tool — bare, not `rtk`: it hands control to an
|
||||
interactive child process, and a token filter has nothing to offer there (ADR-0023).
|
||||
interactive child process, and a token filter has nothing to offer there.
|
||||
- `rtk git diff --diff-filter=U` shows only the still-conflicted files.
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
# git-commits
|
||||
|
||||
Create, amend, squash, and cherry-pick commits with Conventional Commits formatting and validation.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles commit operations within the git workflow suite. It generates well-formatted commit messages following the Conventional Commits spec, validates against commitlint config-conventional constraints, and communicates SemVer impact. It enforces confirmation gates for history-altering operations (amend, rebase, squash) and returns structured JSON output for agent consumption.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-commits
|
||||
```
|
||||
|
||||
Describe your commit task: create a new commit, amend, squash, or cherry-pick. The skill will guide message formatting and handle confirmation for destructive operations.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Loaded when |
|
||||
|------|-------------|
|
||||
| `SKILL.md` | Always — gotchas, the flow dispatch table, the gates common to every flow, and the output shape |
|
||||
| `references/create-commit.md` | Composing a new commit from staged changes |
|
||||
| `references/rewrite-history.md` | Amending, squashing, or folding a `fixup!`/`squash!` commit into an earlier one |
|
||||
| `references/cherry-pick.md` | Replaying an existing commit onto the current branch |
|
||||
| `references/conventional-commits-spec.md` | A type, footer, or breaking-change edge case is not obvious — full spec, 11-type set, commitlint constraint table |
|
||||
| `references/commit-template.md` | Writing a body for a non-trivial commit — Why / Implementation Notes / Impact structure and the full trailer list |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
|
||||
## Composition
|
||||
|
||||
Part of the git plugin's domain suite. This skill owns commit authoring and history-rewriting operations only; `git-history` inspects history, `git-branches` owns branch lifecycle, and `git-workflow` is the conversational entry point that routes between them.
|
||||
@@ -8,7 +8,7 @@ description: >
|
||||
Not branch lifecycle -> `git-branches`.
|
||||
|
||||
metadata:
|
||||
version: "0.1.4"
|
||||
version: "0.1.6"
|
||||
category: git
|
||||
source_keys:
|
||||
- conventional-commits-spec
|
||||
@@ -21,8 +21,8 @@ allowed-tools: Bash
|
||||
|
||||
## Gotchas
|
||||
|
||||
- **Run git as `rtk git <subcommand>`, never bare `git`** — org convention, in `&&` chains too. Exceptions: ADR-0023 clause 3.
|
||||
- **Refuse to force-push `main`/`master`** — a rewrite leaves the branch diverged and the reflex is to force it back; safe only where nobody else has based work on it.
|
||||
- **Run git as `rtk git <subcommand>`, never bare `git`** — org convention, in `&&` chains too, except where a skill's Gotchas name a specific bare-git case (interactive rebase here).
|
||||
- **Refuse to force-push `main`/`master`.** A rewrite diverges the branch and the reflex is to force it back — safe only where nobody else has based work on it.
|
||||
- **`reset --hard` is a confirmation gate, not a default.** It overwrites the working tree, and uncommitted edits it discards were never in git, so no reflog recovers them. Name what will be lost and offer a stash first.
|
||||
- **Never add `--no-verify`** — using it when a hook fails bypasses the QA gate the pipeline depends on. Only on the user's explicit demand, with a warning.
|
||||
|
||||
|
||||
@@ -6,14 +6,14 @@ source_keys:
|
||||
|
||||
# Rewriting existing commits
|
||||
|
||||
Every flow on this page rewrites history. None of them runs before the caller has explicitly approved it, and none is followed by a force-push to `main`/`master` — refuse that and explain why instead.
|
||||
Every flow here rewrites history. None runs without explicit approval, and none ends in a force-push to `main`/`master` — refuse that and explain why.
|
||||
|
||||
## Amend the last commit
|
||||
|
||||
1. Stage the new changes, or the changes that undo something.
|
||||
2. Run `rtk git commit --amend`, adding `--no-edit` when the message stays as it is.
|
||||
3. If the message should change, show the current one and prompt for the replacement.
|
||||
4. The branch has now diverged from its remote. Amending is safe only on a branch nobody else has based work on; on `main`/`master`, refuse the force-push and explain, rather than warning and proceeding.
|
||||
4. The branch has diverged from its remote. Amending is safe only where nobody else has based work on it; on `main`/`master`, refuse the force-push and explain rather than warn and proceed.
|
||||
|
||||
## Fold a commit into an earlier one (autosquash — preferred)
|
||||
|
||||
@@ -21,7 +21,7 @@ Prefer this whenever a commit is written to be folded, because git does the mark
|
||||
|
||||
1. `rtk git commit --fixup=<commit>` keeps the target's message; `rtk git commit --squash=<commit>` lets you edit the combined message later. Both prefix the message with `fixup!`/`squash!` and name the target commit.
|
||||
2. Get explicit approval — the rebase still rewrites history.
|
||||
3. Run `git rebase -i --autosquash HEAD~N` — bare, not `rtk`: `-i` opens an interactive sequence editor (ADR-0023). Git pre-fills the todo list with the tagged commits already reordered against their targets; save it unchanged to apply.
|
||||
3. Run `git rebase -i --autosquash HEAD~N` — bare, not `rtk`: `-i` opens an interactive sequence editor. Git pre-fills the todo list with the tagged commits already reordered against their targets; save it unchanged to apply.
|
||||
|
||||
**`-i` is not optional here.** On Git 2.39.5, `git rebase --autosquash HEAD~N` without `-i` prints `Successfully rebased and updated refs/heads/<branch>.` and exits 0 while leaving the `fixup!` commit in place at its original SHA — `--autosquash` is honoured only by the interactive machinery, and the false success is the trap: the fold is reported as done, and the surviving `fixup!` subject then fails the Conventional Commits `commit-msg` hook. Later Git versions taught the non-interactive rebase to honour the flag, but `-i --autosquash` is correct on every version, so always write that.
|
||||
|
||||
@@ -50,9 +50,8 @@ date without a merge commit.
|
||||
4. `rtk git rebase <newbase>` — for example `rtk git rebase main`. Use
|
||||
`rtk git rebase --onto <newbase> <upstream> <branch>` to replay only the commits after
|
||||
`<upstream>`, which is how a branch started from the wrong base gets moved.
|
||||
5. The branch has now diverged from its remote. It needs
|
||||
`--force-with-lease --force-if-includes` to push, never a bare `--force`, and never on
|
||||
`main`/`master` — refuse that and explain.
|
||||
5. The branch has diverged from its remote. Push needs `--force-with-lease --force-if-includes`,
|
||||
never a bare `--force` — and never on `main`/`master`; refuse that and explain.
|
||||
|
||||
## Move the branch pointer back (`git reset`)
|
||||
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# git-history
|
||||
|
||||
Inspect git history — log queries, bisect, and locating problematic commits.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles history inspection within the git workflow suite. It queries logs with pickaxe/line-range/custom formats, runs bisect to find bug-introducing commits, and locates commits for downstream cherry-picking or reverting. It returns structured results for agent composition. Rebase, squash, fixup, and other history-rewriting operations are owned by git-commits, not this skill.
|
||||
|
||||
## Composition
|
||||
|
||||
`git-branches` delegates revert here (see `git-branches`'s `references/merging.md`), which is why this skill carries that operation rather than treating it as out of scope; it is general git knowledge, not drawn from the `history-inspection.md` research corpus. Cherry-pick is **not** this skill's: `git-commits` owns it, and this skill's job ends at locating the SHA to hand over. Server-side commit history on a Gitea-hosted repository belongs to `gitea-branches`; this skill reads the local working copy.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-history
|
||||
```
|
||||
|
||||
Describe your history task: search logs, bisect for a regression, or locate a specific commit. The skill will query history and return structured results.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/bisect.md` | Loaded when the entry procedure is bisect: manual and automated flows, exit codes, skip, replay, narrowing, custom terms |
|
||||
| `references/git-log-format.md` | Loaded when a log or diff flag needs looking up: format placeholders, presets, diff-filter letters, `-L` syntax, ancestry filters, pickaxe binary-file behaviour, diff output-control flags |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
| `references/README.md` | Index of the references directory |
|
||||
@@ -8,7 +8,7 @@ description: >
|
||||
`git-commits`. Not a Gitea server's history -> `gitea-branches`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.2"
|
||||
category: git
|
||||
source_keys:
|
||||
- git-scm-bisect-docs
|
||||
@@ -38,7 +38,7 @@ allowed-tools: Bash
|
||||
Default to `rtk git log --oneline`, then narrow by whatever is known:
|
||||
|
||||
- **Content**: `rtk git log -S"string"`, or `-G"regex"` to match any diff line. `--pickaxe-regex` makes the `-S` argument a POSIX ERE; `--pickaxe-all` shows every file in a matching changeset.
|
||||
- **A line or function**: `git log -L <start>,<end>:<file>` or `git log -L :<function>:<file>` — bare, not `rtk`: rtk truncates each diff line at ~72 characters (ADR-0023). Confirm the range resolves before reporting on it — an off-by-one silently omits the target.
|
||||
- **A line or function**: `git log -L <start>,<end>:<file>` or `git log -L :<function>:<file>` — bare, not `rtk`: rtk truncates each diff line at ~72 characters. Confirm the range resolves before reporting on it — an off-by-one silently omits the target.
|
||||
- **A file across renames**: `rtk git log --follow -- <file>`. Without `--follow` the history stops at the rename boundary.
|
||||
- **Mainline only**: `--first-parent` follows the integration branch and skips commits merged in from side branches.
|
||||
- **Structured output**: `rtk git log --format="%h | %s | %an (%ar)"`.
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-bisect-docs
|
||||
- git-scm-log-docs
|
||||
- git-scm-diff-docs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
This directory contains provenance metadata and research sources for the `git-history` skill.
|
||||
|
||||
## Files
|
||||
|
||||
- `sources.md` — Extracted research sources and their contributing documents
|
||||
- `bisect.md` — The full `git bisect` procedure: manual and automated flows, exit-code semantics, skip and replay, narrowing options, and custom good/bad terms
|
||||
- `git-log-format.md` — Full `git log` format placeholder catalogue, named format presets, `--diff-filter` letters, `-L` line-range syntax, ancestry filters, pickaxe binary-file behaviour, and `git diff` output-control flags
|
||||
@@ -166,10 +166,10 @@ line at roughly 72 characters with an ellipsis, on the one query whose whole poi
|
||||
is showing line content.
|
||||
|
||||
```bash
|
||||
git log -L 10,20:file.txt # bare per ADR-0023
|
||||
git log -L /start_pattern/,/end_pattern/:file.txt # bare per ADR-0023
|
||||
git log -L :myfunction:src/app.c # bare per ADR-0023
|
||||
git log -L /init/,+15:config.py # bare per ADR-0023; 15 lines after first /init/ match
|
||||
git log -L 10,20:file.txt # bare (ADR-0023)
|
||||
git log -L /start_pattern/,/end_pattern/:file.txt # bare (ADR-0023)
|
||||
git log -L :myfunction:src/app.c # bare (ADR-0023)
|
||||
git log -L /init/,+15:config.py # bare (ADR-0023); 15 lines after first /init/ match
|
||||
```
|
||||
|
||||
Range formats:
|
||||
@@ -213,8 +213,8 @@ Bare `git`, not `rtk git`: rtk appends a blank line and a `Changes:` trailer, so
|
||||
the output is no longer one record per line.
|
||||
|
||||
```bash
|
||||
git diff --name-only # bare per ADR-0023; only filenames, one per line
|
||||
git diff --name-status # bare per ADR-0023; status letter + filename per line
|
||||
git diff --name-only # bare (ADR-0023); only filenames, one per line
|
||||
git diff --name-status # bare (ADR-0023); status letter + filename per line
|
||||
```
|
||||
|
||||
`--name-status` uses the same status letters as `--diff-filter`.
|
||||
@@ -225,10 +225,10 @@ Bare `git`, not `rtk git`: rtk replaces the word-diff with its own diffstat
|
||||
renderer and emits none of the `[-removed-] {+added+}` markers.
|
||||
|
||||
```bash
|
||||
git diff --word-diff # bare per ADR-0023; inline word-level diff, [-removed-] {+added+} markers
|
||||
git diff --word-diff=color # bare per ADR-0023; color only, no markers
|
||||
git diff --word-diff=porcelain # bare per ADR-0023; machine-readable: +/- prefixed lines, ~ for newlines
|
||||
git diff --word-diff-regex=<re> # bare per ADR-0023; define what counts as a "word"
|
||||
git diff --word-diff # bare (ADR-0023); inline word-level diff, [-removed-] {+added+} markers
|
||||
git diff --word-diff=color # bare (ADR-0023); color only, no markers
|
||||
git diff --word-diff=porcelain # bare (ADR-0023); machine-readable: +/- prefixed lines, ~ for newlines
|
||||
git diff --word-diff-regex=<re> # bare (ADR-0023); define what counts as a "word"
|
||||
```
|
||||
|
||||
### Whitespace Flags
|
||||
|
||||
@@ -1,34 +0,0 @@
|
||||
# git-remotes
|
||||
|
||||
Manage git remote repositories — add/remove/configure remotes, push/pull with safety checks, fetch with pruning, and multi-remote workflows.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles remote operations within the git workflow suite. It manages remote configuration (add, remove, rename), fetch operations with pruning, push operations with force-push safety (`--force-with-lease --force-if-includes`), and pull strategies (fast-forward, rebase, merge). It returns structured results suitable for agent composition.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-remotes
|
||||
```
|
||||
|
||||
Describe your remote operation: add a remote, push, pull, fetch, or configure tracking. The skill will handle the operation with appropriate safety checks and return results.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents — force-push gate, dispatch table, return format |
|
||||
| `references/README.md` | Describes the references directory contents |
|
||||
| `references/remote-config.md` | Read when adding, removing, renaming, inspecting or re-pointing a remote, or configuring tracking, mirroring, or `set-url` |
|
||||
| `references/fetch.md` | Read when fetching or pruning remote-tracking refs, or doing a shallow or partial fetch |
|
||||
| `references/push.md` | Read when pushing branches or tags, writing refspecs, or force-pushing |
|
||||
| `references/pull.md` | Read when integrating remote changes into the current branch, including the divergence rule |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
|
||||
## Composition
|
||||
|
||||
Callers that need submodule initialization after a `--recurse-submodules` pull hand off to
|
||||
`git-submodules`; local-only work (commits, branches, history) belongs to `git-commits`,
|
||||
`git-branches`, and `git-history`. The `git-workflow` skill routes humans here for any
|
||||
remote-touching request.
|
||||
@@ -10,7 +10,7 @@ description: >
|
||||
Not submodule pointers -> `git-submodules`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.3"
|
||||
category: git
|
||||
source_keys:
|
||||
- git-scm-remote-docs
|
||||
@@ -28,7 +28,7 @@ metadata:
|
||||
|
||||
## Step 1 — Clear the force-push gate
|
||||
|
||||
`main` and `master` are a hard refusal: decline a force-push targeting either, whatever confirmation accompanies it, because no local approval can restore what the remote loses. On any other branch, `rtk git push --force` and `-f` run only after the caller passes `confirm: true` for that specific push — for a human caller, prompt instead of failing.
|
||||
`main`/`master` are a hard refusal: decline a force-push to either regardless of confirmation — no local approval restores what the remote loses. Elsewhere, `rtk git push --force`/`-f` run only after `confirm: true` for that specific push; for a human caller, prompt instead of failing.
|
||||
|
||||
## Step 2 — Dispatch
|
||||
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-remote-docs
|
||||
- git-scm-fetch-docs
|
||||
- git-scm-push-docs
|
||||
- git-scm-pull-docs
|
||||
- context7-git-htmldocs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
This directory contains provenance metadata and research sources for the `git-remotes` skill.
|
||||
|
||||
## Files
|
||||
|
||||
- `sources.md` — Extracted research sources and their contributing documents
|
||||
- `remote-config.md` — Remote add/remove/rename/inspect, tracking and mirror options, housekeeping, and the full `set-url` form
|
||||
- `fetch.md` — Fetch and prune options, shallow and partial fetch, the default fetch refspec
|
||||
- `push.md` — Push options, refspec syntax, force-push safety in full, server-side deny policies
|
||||
- `pull.md` — Pull strategies, submodule caveat, the divergence rule, and pull config precedence
|
||||
@@ -50,7 +50,7 @@ Two mitigations:
|
||||
# poisoned by an unrelated fetch.
|
||||
# The inner `git config` is bare: its stdout becomes a remote URL, so any
|
||||
# output rewriting would poison the remote silently.
|
||||
rtk git remote add origin-push $(git config remote.origin.url) # inner bare per ADR-0023
|
||||
rtk git remote add origin-push $(git config remote.origin.url) # inner bare (ADR-0023)
|
||||
rtk git push --force-with-lease origin-push
|
||||
|
||||
# Option 2 — explicit SHA via a local tag, unaffected by tracking-branch state
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
# git-submodules
|
||||
|
||||
Add, initialize, update, pin, inspect, and remove git submodules in multi-repository projects.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles submodule operations within the git workflow suite: cloning a superproject with
|
||||
its nested repositories, adding a dependency as a submodule, initializing and updating with
|
||||
pinning or branch tracking, parallel and recursive traversal, rebinding URLs and tracked branches,
|
||||
and the full removal sequence including the `.git/modules/` cleanup git leaves behind. It returns
|
||||
structured results suitable for agent composition.
|
||||
|
||||
It sits alongside the other git skills rather than duplicating them: `git-worktrees` covers
|
||||
multiple checkouts of a single repository, and `git-remotes` covers the superproject's own remotes.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-submodules
|
||||
```
|
||||
|
||||
Describe the submodule task. The skill applies the shared working rules, dispatches to the
|
||||
reference for that task, and returns structured results (operation, status, per-submodule details,
|
||||
conflicts, and a recovery `next_step` when applicable).
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents — gotchas, shared working rules, and the task dispatch table |
|
||||
| `references/README.md` | Describes contents of references/ |
|
||||
| `references/setup-and-update.md` | Loaded when cloning a superproject, adding a submodule, initializing, updating, or re-pinning one, or running a command across all of them — includes the full `add` and `update` flag tables, the pinning workflows, and the `foreach` shell-variable table |
|
||||
| `references/urls-and-config.md` | Loaded when changing where a submodule points or how it is configured — `.gitmodules` vs `.git/config` anatomy, both key tables, `sync`/`set-url`/`set-branch`, local mirror overrides, relative URLs, the custom-`update` security gate, and `absorbgitdirs` |
|
||||
| `references/removal.md` | Loaded when removing or deinitializing a submodule — why `deinit` is not removal, and the four-step removal sequence |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
@@ -1,31 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-submodule-docs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
One file per task branch in SKILL.md's dispatch table. Load only the one that matches the request.
|
||||
|
||||
## setup-and-update.md
|
||||
|
||||
Cloning a superproject that has submodules, adding a dependency as a submodule, initializing
|
||||
without cloning, updating or re-pinning, and running one command across every submodule. Carries
|
||||
the `add` and `update` flag tables, the keep-pinned and move-the-pin-forward workflows, and the
|
||||
`foreach` shell-variable table (`$name`, `$sm_path`, `$displaypath`, `$sha1`, `$toplevel`).
|
||||
|
||||
## urls-and-config.md
|
||||
|
||||
Where a submodule points and how it is configured: the `.gitmodules` vs `.git/config` split, both
|
||||
key tables, `sync` / `set-url` / `set-branch`, local mirror overrides, relative URL resolution, the
|
||||
security gate on custom `update` commands, and `absorbgitdirs`.
|
||||
|
||||
## removal.md
|
||||
|
||||
Removing a submodule, and why `deinit` alone does not remove one. Carries the full four-step
|
||||
removal sequence including the manual `.git/modules/<name>/` cleanup.
|
||||
|
||||
## sources.md
|
||||
|
||||
Research sources that informed this skill — provenance chain for git-scm-submodule-docs reference
|
||||
material.
|
||||
@@ -1,25 +0,0 @@
|
||||
# git-workflow
|
||||
|
||||
Human-friendly interface for interactive git workflows with conversational prompts, progress guidance, and safety confirmations.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill wraps the `git-orchestrate` agent to provide an interactive, educational interface for humans performing git workflows. It is the router for the six local-git domain skills — `git-commits`, `git-branches`, `git-history`, `git-remotes`, `git-submodules` and `git-worktrees` — and `SKILL.md` carries a table mapping each of them to the requests it owns, so an ambiguous request resolves to exactly one domain before anything runs. The skill parses user intent, gathers session context, invokes the orchestrator, and presents results in plain language with inline help, progress updates, and explanations of what's happening. It enforces confirmation gates for destructive operations (force-push, branch deletion, rebasing with history loss, force-checkout) and provides best-practices guidance throughout. The org's non-negotiable git rules live in `references/hard-rules.md` and are loaded only when a request could conflict with one.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-workflow
|
||||
```
|
||||
|
||||
Describe your git workflow: commit, create a branch, rebase, inspect history, manage submodules, switch worktrees, or manage remotes. The skill will prompt for any missing details and guide you through the workflow.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents — the six-domain routing table, the workflow steps, and the interaction style |
|
||||
| `README.md` | This file |
|
||||
| `references/hard-rules.md` | The org's non-negotiable git rules; read when a request creates, amends, or rewrites a commit, pushes, or touches hooks, config, or credentials |
|
||||
| `references/README.md` | Describes the references directory contents |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
@@ -8,7 +8,7 @@ description: >
|
||||
agent caller -> `git-orchestrate`. Not Gitea -> `gitea-workflow`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.0"
|
||||
version: "1.0.2"
|
||||
category: git
|
||||
source_keys:
|
||||
- nvie-gitflow-post
|
||||
@@ -55,12 +55,12 @@ owns the request.
|
||||
touches hooks, config, or credentials, read `references/hard-rules.md`. Raise the relevant rule
|
||||
before acting, not after.
|
||||
3. **Read the repo** — current branch, working-tree state, and which branching model the repo
|
||||
follows (the orchestrator reads `branching_pattern` from plugin config; infer from branch names
|
||||
if absent); the last of those decides which tips are worth offering.
|
||||
follows (`git-branches` infers this from branch names: Gitflow if `develop`/`release/*` exists,
|
||||
GitHub Flow otherwise); the last of those decides which tips are worth offering.
|
||||
4. **Gate destructive operations** — before force-push, branch deletion, rebase, or
|
||||
force-checkout, show what will happen and ask "Proceed?". Cancel gracefully if the user
|
||||
declines. Never supply the confirmation on the user's behalf. Some operations are refusals, not
|
||||
confirmations: never offer "Proceed?" for a force-push of `main` or `master`.
|
||||
confirmations — never offer "Proceed?" for a force-push of `main`/`master`.
|
||||
5. **Invoke the `git-orchestrate` agent** with `operation`, `parameters` (user-provided or
|
||||
inferred), `context` (step 3 plus the session context), and `confirm: true` only for a
|
||||
destructive op the user approved in step 4.
|
||||
|
||||
@@ -1,19 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- nvie-gitflow-post
|
||||
- atlassian-gitflow-tutorial
|
||||
- gitflow-cheatsheet
|
||||
- context7-git-htmldocs
|
||||
- org-git-conventions
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
This directory contains the org git rules and the provenance metadata for the `git-workflow`
|
||||
skill.
|
||||
|
||||
## Files
|
||||
|
||||
- `hard-rules.md` — The org's non-negotiable git rules, loaded when a request creates, amends, or
|
||||
rewrites a commit, pushes, or touches hooks, config, or credentials
|
||||
- `sources.md` — Extracted research sources and their contributing documents
|
||||
@@ -1,24 +0,0 @@
|
||||
# git-worktrees
|
||||
|
||||
Manage git worktrees to enable multi-branch parallel development across isolated directories.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles worktree operations within the git workflow suite. It creates, lists, locks/unlocks, moves, removes, prunes, and repairs worktrees — letting an agent work on multiple branches simultaneously without stashing. It returns structured results (paths, branches, lock status) suitable for agent composition. For multi-step flows spanning branch strategy plus worktree setup, `git-workflow` handles the broader orchestration and delegates the worktree mechanics here.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-worktrees
|
||||
```
|
||||
|
||||
Describe your worktree task: create a worktree for a branch, list existing worktrees, lock one for removable media, move, remove, prune, or repair. The skill will handle the operation with appropriate safety checks and return results.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Dispatch table, per-operation gates, and the report format |
|
||||
| `references/README.md` | Describes the references directory contents |
|
||||
| `references/worktrees.md` | Read when an operation needs more than the dispatch table: shared vs. per-worktree state, the `add` command forms, the full `add` flag table, orphan branches, sparse-checkout, removable-media locking, remote disambiguation, where to run `repair` from, config keys, and the emergency-fix and PR-review patterns |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
@@ -8,7 +8,7 @@ description: >
|
||||
Not interactive multi-step git guidance -> `git-workflow`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.2"
|
||||
category: git
|
||||
source_keys:
|
||||
- git-scm-worktree-docs
|
||||
@@ -32,7 +32,7 @@ metadata:
|
||||
| Create a local branch tracking a remote one | `rtk git worktree add --track -b <branch> <path> <remote>/<branch>` — always correct. `git worktree add <path> <branch>` expands to exactly this, but **only** under the conditions in `references/worktrees.md` |
|
||||
| Throwaway experiment, no branch | `rtk git worktree add -d <path>` — detached HEAD |
|
||||
| **Never** `git worktree add <path> <remote>/<branch>` | That ref resolves, so the shortcut never fires and you get **a detached HEAD, no branch, no upstream**. Commits there go unreachable once HEAD moves, and `git push` needs an explicit refspec. Use the tracking row above |
|
||||
| List | `git worktree list -v` to read, or `git worktree list --porcelain -z` to parse — both bare per ADR-0023: rtk re-renders the output and drops the porcelain flags |
|
||||
| List | `git worktree list -v` to read, or `git worktree list --porcelain -z` to parse — both bare (ADR-0023): rtk re-renders the output and drops the porcelain flags |
|
||||
| Lock or unlock | `rtk git worktree lock [--reason <str>] <path>` / `rtk git worktree unlock <path>` |
|
||||
| Move | `rtk git worktree move <from> <to>` |
|
||||
| Remove | `rtk git worktree remove <path>` |
|
||||
@@ -63,6 +63,6 @@ worktrees:
|
||||
```
|
||||
|
||||
Derive those fields from `git worktree list --porcelain -z` — bare, not `rtk`:
|
||||
rtk drops both flags and never emits `locked`/`lock_reason` (ADR-0023). For a single
|
||||
rtk drops both flags and never emits `locked`/`lock_reason`. For a single
|
||||
operation, report its outcome instead — `created: true`, `moved: true`,
|
||||
`removed: true`.
|
||||
|
||||
@@ -1,13 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-worktree-docs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
This directory contains provenance metadata and research sources for the `git-worktrees` skill.
|
||||
|
||||
## Files
|
||||
|
||||
- `sources.md` — Extracted research sources and their contributing documents
|
||||
- `worktrees.md` — Shared vs. per-worktree state, the `add` command forms, the full `add` flag table, orphan branches, sparse-checkout setup, removable-media locking, remote-branch disambiguation, where to run `repair` from, the config key reference, and the emergency-fix and PR-review workflow patterns
|
||||
@@ -1,26 +0,0 @@
|
||||
# pc-author
|
||||
|
||||
Create, add, remove, update, and configure `.pre-commit-config.yaml`.
|
||||
|
||||
## What it does
|
||||
|
||||
Manages the pre-commit configuration file in any git repo. When invoked, it scans the repo for languages, proposes appropriate hooks with rationale, and writes or modifies `.pre-commit-config.yaml`. It validates every write with `pre-commit validate-config` and flags stale revision pins. It does not run hooks or install them into `.git/hooks/` — use `pc-run` for that.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/pc-author
|
||||
```
|
||||
|
||||
Invoke with no arguments. The skill determines from context whether to create a new config or modify an existing one.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/create-config.md` | Loaded when the repo has no `.pre-commit-config.yaml` — the create-from-scratch flow |
|
||||
| `references/modify-config.md` | Loaded when a `.pre-commit-config.yaml` already exists — add, remove, top-level keys, rev staleness |
|
||||
| `references/hooks-by-language.md` | Hook recommendations by detected language/extension |
|
||||
| `references/README.md` | Index of files in references/ |
|
||||
| `references/sources.md` | Provenance — research sources that informed this skill |
|
||||
@@ -1,16 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- context7-pre-commit-com
|
||||
- pre-commit-com
|
||||
- context7-pre-commit-hooks
|
||||
- pre-commit-hooks-github
|
||||
---
|
||||
|
||||
# references/
|
||||
|
||||
| File | Purpose |
|
||||
|---|---|
|
||||
| `create-config.md` | The create flow — read when the repo has no `.pre-commit-config.yaml` |
|
||||
| `modify-config.md` | The modify flow — read when a `.pre-commit-config.yaml` already exists |
|
||||
| `hooks-by-language.md` | Hook recommendations by language/context — repo, rev, and rationale for adding hooks |
|
||||
| `sources.md` | Provenance: research sources that informed this skill |
|
||||
@@ -1,32 +0,0 @@
|
||||
# pc-run
|
||||
|
||||
Runs, installs, updates, and maintains pre-commit hooks in a local git clone.
|
||||
|
||||
## What it does
|
||||
|
||||
`pc-run` handles everything that happens *after* `.pre-commit-config.yaml` exists: wiring hooks into git, running them, bumping their versions, and maintaining the cache. When hooks fail, it identifies the cause and suggests a concrete fix — it does not auto-fix files or edit the config. For creating or editing `.pre-commit-config.yaml`, use `pc-author` instead.
|
||||
|
||||
## Before you start
|
||||
|
||||
- `pre-commit` must be installed and available on `PATH`
|
||||
- A `.pre-commit-config.yaml` must exist at the repo root (use `pc-author` to create one)
|
||||
|
||||
## Usage
|
||||
|
||||
Common invocations:
|
||||
- `/pc-run` — run all hooks against all files (default)
|
||||
- `/pc-run install` — wire hooks into `.git/hooks/`
|
||||
- `/pc-run autoupdate` — bump all `rev` values to latest
|
||||
- `/pc-run clean` — wipe the pre-commit cache (requires confirmation)
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/install.md` | The install flow — loaded when the user asks to install or set up hooks |
|
||||
| `references/autoupdate.md` | The autoupdate flow — loaded when the user asks to bump hook revs |
|
||||
| `references/clean.md` | The clean flow — loaded when the user asks to wipe the cache or rebuild environments |
|
||||
| `references/failure-patterns.md` | Hook failure causes and concrete fix suggestions — loaded when a hook fails or never fires |
|
||||
| `references/sources.md` | Provenance: research sources that informed this skill |
|
||||
| `references/README.md` | Directory index for references/ |
|
||||
@@ -1,17 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- context7-pre-commit-com
|
||||
- pre-commit-com
|
||||
- context7-pre-commit-hooks
|
||||
- pre-commit-hooks-github
|
||||
---
|
||||
|
||||
# references/
|
||||
|
||||
| File | Purpose |
|
||||
|---|---|
|
||||
| `install.md` | The install flow — read when the user asks to install or set up hooks |
|
||||
| `autoupdate.md` | The autoupdate flow — read when the user asks to bump hook revs |
|
||||
| `clean.md` | The clean flow — read when the user asks to wipe the cache or rebuild environments |
|
||||
| `failure-patterns.md` | Hook failure causes and concrete fix suggestions — read when a hook fails or never fires |
|
||||
| `sources.md` | Provenance: research sources that informed this skill |
|
||||
@@ -40,7 +40,7 @@ Sub-skills carry their own local copies of these rules for humans who invoke the
|
||||
|
||||
When invoked, you:
|
||||
1. Parse the incoming workflow request (operation type, parameters, context overrides)
|
||||
2. Check safety gates: if the operation is destructive (force-push, branch deletion, rebase with history loss, force-checkout) and the request lacks explicit `confirm: true`, fail immediately with "requires explicit confirmation"; force-push to `main`/`master` is refused outright regardless of `confirm`
|
||||
2. Check safety gates: a destructive operation (force-push, branch deletion, history-losing rebase, force-checkout) without `confirm: true` fails immediately with "requires explicit confirmation"; force-push to `main`/`master` is refused outright regardless of `confirm`
|
||||
3. Route to the appropriate domain skill: `git-commits`, `git-branches`, `git-history`, `git-submodules`, `git-worktrees`, `git-remotes`
|
||||
4. Manage session context: carry forward the current branch, workflow intent, and configuration, passing explicitly to each skill
|
||||
5. Handle error recovery: for recoverable failures (merge conflicts, push rejections, auth issues), attempt automatic recovery; if unrecoverable, fail gracefully with actionable diagnostics
|
||||
@@ -63,11 +63,10 @@ When invoked, you:
|
||||
1. Validate the request structure and check if operation is known
|
||||
2. Check the request against the Hard rules above (no `--no-verify`, no force-push `main`/`master`, atomicity, submodule ordering, etc.) — refuse outright on violation, independent of `confirm`
|
||||
3. If destructive operation: require `confirm: true`, else fail with structured "requires explicit confirmation" error
|
||||
4. Read plugin config from `.claude/plugins/git/config.json` if present — see `config.example.json` in the plugin root for the expected shape (`branching_pattern`, `commit_style`, `rebase_strategy`) — or fall back to sensible defaults
|
||||
5. Invoke the appropriate skill via `Skill` or direct bash call with the operation, parameters, context, and config. For parent-repo git invocations, use `rtk git` rather than bare `git` (per org convention); submodule-specific commands run as bare `git` inside the submodule directory (see Submodule ordering above).
|
||||
6. Catch and handle git errors: attempt automatic recovery (offer rebase strategies for conflicts, suggest `--force-with-lease` for rejections)
|
||||
7. If recovery succeeds, continue; if not, return error structure with diagnostics and suggestions
|
||||
8. Aggregate all outputs and return as structured JSON
|
||||
4. Invoke the appropriate skill via `Skill` or direct bash call with the operation, parameters, and context — each domain skill infers its own branching pattern and conventions (e.g. `git-branches` from `develop`/`release/*` branch presence) rather than reading shared config. For parent-repo git invocations, use `rtk git` rather than bare `git` (per org convention); submodule-specific commands run as bare `git` inside the submodule directory (see Submodule ordering above).
|
||||
5. Catch and handle git errors: attempt automatic recovery (offer rebase strategies for conflicts, suggest `--force-with-lease` for rejections)
|
||||
6. If recovery succeeds, continue; if not, return error structure with diagnostics and suggestions
|
||||
7. Aggregate all outputs and return as structured JSON
|
||||
|
||||
## Output
|
||||
|
||||
@@ -77,8 +76,7 @@ When invoked, you:
|
||||
"operation": "<operation_name>",
|
||||
"result": {
|
||||
"output": "<command output or result>",
|
||||
"context": { "current_branch": "...", "workflow_intent": "..." },
|
||||
"applied_config": { "commit_style": "...", "rebase_strategy": "..." }
|
||||
"context": { "current_branch": "...", "workflow_intent": "..." }
|
||||
},
|
||||
"error": {
|
||||
"message": "<human-readable error>",
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
{
|
||||
"branching_pattern": "github-flow",
|
||||
"commit_style": "conventional",
|
||||
"rebase_strategy": "interactive"
|
||||
}
|
||||
@@ -157,20 +157,6 @@ pre-commit run --from-ref origin/main --to-ref HEAD
|
||||
files: \.env(\..+)?$
|
||||
```
|
||||
|
||||
### Validate a generated file
|
||||
|
||||
```yaml
|
||||
- repo: local
|
||||
hooks:
|
||||
- id: validate-manifest
|
||||
name: Validate plugin manifest
|
||||
entry: bash scripts/check-manifests.sh
|
||||
language: unsupported_script
|
||||
files: ^\.claude-plugin/
|
||||
pass_filenames: false
|
||||
always_run: false
|
||||
```
|
||||
|
||||
### Run full test suite pre-push
|
||||
|
||||
```yaml
|
||||
@@ -185,29 +171,6 @@ pre-commit run --from-ref origin/main --to-ref HEAD
|
||||
stages: [pre-push]
|
||||
```
|
||||
|
||||
### Validate SKILL.md frontmatter (inline bash, as used in this repo)
|
||||
|
||||
```yaml
|
||||
- repo: local
|
||||
hooks:
|
||||
- id: skill-frontmatter
|
||||
name: SKILL.md frontmatter validation
|
||||
entry: bash
|
||||
language: system
|
||||
files: 'SKILL\.md$'
|
||||
args:
|
||||
- -c
|
||||
- |
|
||||
for f in "$@"; do
|
||||
if [[ -f "$f" ]]; then
|
||||
if ! grep -q "^name:" "$f" || ! grep -q "^description:" "$f"; then
|
||||
echo "ERROR: $f missing required frontmatter (name: and description:)"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
done
|
||||
```
|
||||
|
||||
## Adding meta-validation
|
||||
|
||||
Add after all other repos to catch dead hooks/excludes:
|
||||
|
||||
@@ -168,7 +168,5 @@ Local hooks in this repo:
|
||||
| Hook | Stage | Entry |
|
||||
|------|-------|-------|
|
||||
| `run-tests` | pre-push | `bash tests/run-tests.sh` |
|
||||
| `check-manifests` | pre-push | `bash scripts/check-manifests.sh` |
|
||||
| `validate-plugins` | pre-push | `claude plugin validate --strict` per plugin dir |
|
||||
| `validate-marketplace` | pre-push | `claude plugin validate --strict .claude-plugin/marketplace.json` |
|
||||
| `skill-frontmatter` | pre-commit | Validates SKILL.md has `name:` and `description:` |
|
||||
|
||||
@@ -1,34 +0,0 @@
|
||||
# git-branches
|
||||
|
||||
Manage the full lifecycle of git branches — create, switch, delete, rename, track, merge, and compare feature/hotfix/release branches under GitHub Flow or Gitflow.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles branch operations within the git workflow suite. It creates branches following GitHub Flow or Gitflow conventions (configurable), switches and tracks branches, handles safe deletion with unmerged-work checks, and retrieves branch intent metadata for use by other skills (e.g., commit message context). It returns structured results suitable for agent composition.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-branches
|
||||
```
|
||||
|
||||
Describe your branch task: create a feature/hotfix/release branch, switch, delete, rename, track, merge, or compare two branches. The skill will determine the branching pattern (GitHub Flow or Gitflow) from config or repo state and handle safety checks for destructive operations.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/branch-patterns.md` | Loaded when a branch's base, name prefix, or merge rule depends on GitHub Flow vs. Gitflow |
|
||||
| `references/branch-operations.md` | Loaded when running a create/switch/delete/rename/track/list/stash action, or resolving `get-intent` |
|
||||
| `references/merging.md` | Loaded when merging one branch into another or resolving merge conflicts |
|
||||
| `references/comparing-branches.md` | Loaded when comparing two branches or finding where they diverged |
|
||||
| `references/orchestrator-contract.md` | Loaded when `git-orchestrate` or another calling agent supplies a structured request rather than prose |
|
||||
| `references/sources.md` | Research sources backing the branching/gitflow guidance |
|
||||
|
||||
## Composition
|
||||
|
||||
`git-orchestrate` calls this skill for the branch step of a multi-step workflow and parses its
|
||||
structured result. Revert is `git-history`'s; commit authoring, rebase, reset and cherry-pick are
|
||||
`git-commits`'; deleting a remote branch is `git-remotes`'; branch operations against a
|
||||
Gitea-hosted remote are `gitea-branches`'.
|
||||
@@ -9,7 +9,7 @@ description: >
|
||||
Not a Gitea remote's branches -> `gitea-branches`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.4"
|
||||
category: git
|
||||
source_keys:
|
||||
- context7-git-htmldocs
|
||||
@@ -21,12 +21,12 @@ metadata:
|
||||
## Gotchas
|
||||
|
||||
- **Uncommitted changes abort a switch.** `git switch` refuses rather than clobbering conflicting local edits. Offer to stash and retry — forcing the checkout past it is how work disappears.
|
||||
- **A branch and a tag can carry the same name.** Detect it before acting — `git branch --list <name>` (bare, not `rtk`: rtk prints a phantom `* ` line even on no match, which reports every name as ambiguous — ADR-0023) and `rtk git tag --list <name>`; output from both means the name is ambiguous. Prefer `git switch` over `git checkout`, and where a command accepts either ref, disambiguate with `refs/heads/<name>` or `refs/tags/<name>`.
|
||||
- **`main` and `master` are a refusal, not a gate.** Force-pushing, force-deleting, or renaming them is rejected even when the caller passes `confirm: true` — no flag makes the remote's history recoverable. Offer a new branch instead.
|
||||
- **A branch and a tag can carry the same name.** Detect it before acting — `git branch --list <name>` (bare, not `rtk`: rtk prints a phantom `* ` line even on no match, which reports every name as ambiguous) and `rtk git tag --list <name>`; output from both means the name is ambiguous. Prefer `git switch` over `git checkout`, and where a command accepts either ref, disambiguate with `refs/heads/<name>` or `refs/tags/<name>`.
|
||||
- **`main`/`master` are a refusal, not a gate.** Force-pushing, force-deleting, or renaming either is rejected even with `confirm: true` — no flag recovers the remote's history. Offer a new branch instead.
|
||||
|
||||
## Step 1 — Determine the branching pattern
|
||||
|
||||
Read `branching_pattern` from the git plugin config (`.claude/plugins/git/config.json`; the plugin root's `config.example.json` shows the shape). Default: `github-flow`. With no config, infer Gitflow from the presence of a `develop` or `release/*` branch, and GitHub Flow otherwise.
|
||||
Infer the branching pattern from the repo: Gitflow if a `develop` or `release/*` branch exists, GitHub Flow otherwise (the default).
|
||||
|
||||
The two patterns are not mixable, and the wrong merge rule silently damages history. If the action touches a base branch, a name prefix, or a merge rule, read `references/branch-patterns.md`.
|
||||
|
||||
|
||||
@@ -45,10 +45,10 @@ past it: it shelves the working tree and index so the branch pointer can move.
|
||||
reports `No local changes to save` and stashes nothing. Bare `git stash` is `push` with no message.
|
||||
- **restore** — `git stash pop` applies the newest entry and deletes it. Bare, not `rtk`: on a
|
||||
conflict rtk prints only `FAILED: git stash pop` and swallows the conflict report the paragraph
|
||||
below tells you to read (ADR-0023). `rtk git stash apply stash@{n}`
|
||||
below tells you to read. `rtk git stash apply stash@{n}`
|
||||
applies without deleting, for replaying one shelf onto more than one branch.
|
||||
- **list** — `git stash list` — bare, not `rtk`: rtk prints `No stashes` where git prints nothing,
|
||||
so an empty-output test misfires (ADR-0023). `rtk git stash show -p stash@{n}` prints that entry's diff.
|
||||
so an empty-output test misfires. `rtk git stash show -p stash@{n}` prints that entry's diff.
|
||||
- **drop** — `rtk git stash drop stash@{n}` deletes one entry. `rtk git stash clear` deletes all of them
|
||||
and nothing recovers them — confirm before running it.
|
||||
- **branch from a stash** — `rtk git stash branch <branch> stash@{n}` creates a branch at the commit the
|
||||
|
||||
@@ -27,5 +27,5 @@ list the conflicted files, edit each to resolve its markers, then `rtk git add <
|
||||
|
||||
- `rtk git merge --abort` restores the pre-merge state.
|
||||
- `git mergetool` opens the configured merge tool — bare, not `rtk`: it hands control to an
|
||||
interactive child process, and a token filter has nothing to offer there (ADR-0023).
|
||||
interactive child process, and a token filter has nothing to offer there.
|
||||
- `rtk git diff --diff-filter=U` shows only the still-conflicted files.
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
# git-commits
|
||||
|
||||
Create, amend, squash, and cherry-pick commits with Conventional Commits formatting and validation.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles commit operations within the git workflow suite. It generates well-formatted commit messages following the Conventional Commits spec, validates against commitlint config-conventional constraints, and communicates SemVer impact. It enforces confirmation gates for history-altering operations (amend, rebase, squash) and returns structured JSON output for agent consumption.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-commits
|
||||
```
|
||||
|
||||
Describe your commit task: create a new commit, amend, squash, or cherry-pick. The skill will guide message formatting and handle confirmation for destructive operations.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Loaded when |
|
||||
|------|-------------|
|
||||
| `SKILL.md` | Always — gotchas, the flow dispatch table, the gates common to every flow, and the output shape |
|
||||
| `references/create-commit.md` | Composing a new commit from staged changes |
|
||||
| `references/rewrite-history.md` | Amending, squashing, or folding a `fixup!`/`squash!` commit into an earlier one |
|
||||
| `references/cherry-pick.md` | Replaying an existing commit onto the current branch |
|
||||
| `references/conventional-commits-spec.md` | A type, footer, or breaking-change edge case is not obvious — full spec, 11-type set, commitlint constraint table |
|
||||
| `references/commit-template.md` | Writing a body for a non-trivial commit — Why / Implementation Notes / Impact structure and the full trailer list |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
|
||||
## Composition
|
||||
|
||||
Part of the git plugin's domain suite. This skill owns commit authoring and history-rewriting operations only; `git-history` inspects history, `git-branches` owns branch lifecycle, and `git-workflow` is the conversational entry point that routes between them.
|
||||
@@ -8,7 +8,7 @@ description: >
|
||||
Not branch lifecycle -> `git-branches`.
|
||||
|
||||
metadata:
|
||||
version: "0.1.4"
|
||||
version: "0.1.6"
|
||||
category: git
|
||||
source_keys:
|
||||
- conventional-commits-spec
|
||||
@@ -21,8 +21,8 @@ allowed-tools: Bash
|
||||
|
||||
## Gotchas
|
||||
|
||||
- **Run git as `rtk git <subcommand>`, never bare `git`** — org convention, in `&&` chains too. Exceptions: ADR-0023 clause 3.
|
||||
- **Refuse to force-push `main`/`master`** — a rewrite leaves the branch diverged and the reflex is to force it back; safe only where nobody else has based work on it.
|
||||
- **Run git as `rtk git <subcommand>`, never bare `git`** — org convention, in `&&` chains too, except where a skill's Gotchas name a specific bare-git case (interactive rebase here).
|
||||
- **Refuse to force-push `main`/`master`.** A rewrite diverges the branch and the reflex is to force it back — safe only where nobody else has based work on it.
|
||||
- **`reset --hard` is a confirmation gate, not a default.** It overwrites the working tree, and uncommitted edits it discards were never in git, so no reflog recovers them. Name what will be lost and offer a stash first.
|
||||
- **Never add `--no-verify`** — using it when a hook fails bypasses the QA gate the pipeline depends on. Only on the user's explicit demand, with a warning.
|
||||
|
||||
|
||||
@@ -6,14 +6,14 @@ source_keys:
|
||||
|
||||
# Rewriting existing commits
|
||||
|
||||
Every flow on this page rewrites history. None of them runs before the caller has explicitly approved it, and none is followed by a force-push to `main`/`master` — refuse that and explain why instead.
|
||||
Every flow here rewrites history. None runs without explicit approval, and none ends in a force-push to `main`/`master` — refuse that and explain why.
|
||||
|
||||
## Amend the last commit
|
||||
|
||||
1. Stage the new changes, or the changes that undo something.
|
||||
2. Run `rtk git commit --amend`, adding `--no-edit` when the message stays as it is.
|
||||
3. If the message should change, show the current one and prompt for the replacement.
|
||||
4. The branch has now diverged from its remote. Amending is safe only on a branch nobody else has based work on; on `main`/`master`, refuse the force-push and explain, rather than warning and proceeding.
|
||||
4. The branch has diverged from its remote. Amending is safe only where nobody else has based work on it; on `main`/`master`, refuse the force-push and explain rather than warn and proceed.
|
||||
|
||||
## Fold a commit into an earlier one (autosquash — preferred)
|
||||
|
||||
@@ -21,7 +21,7 @@ Prefer this whenever a commit is written to be folded, because git does the mark
|
||||
|
||||
1. `rtk git commit --fixup=<commit>` keeps the target's message; `rtk git commit --squash=<commit>` lets you edit the combined message later. Both prefix the message with `fixup!`/`squash!` and name the target commit.
|
||||
2. Get explicit approval — the rebase still rewrites history.
|
||||
3. Run `git rebase -i --autosquash HEAD~N` — bare, not `rtk`: `-i` opens an interactive sequence editor (ADR-0023). Git pre-fills the todo list with the tagged commits already reordered against their targets; save it unchanged to apply.
|
||||
3. Run `git rebase -i --autosquash HEAD~N` — bare, not `rtk`: `-i` opens an interactive sequence editor. Git pre-fills the todo list with the tagged commits already reordered against their targets; save it unchanged to apply.
|
||||
|
||||
**`-i` is not optional here.** On Git 2.39.5, `git rebase --autosquash HEAD~N` without `-i` prints `Successfully rebased and updated refs/heads/<branch>.` and exits 0 while leaving the `fixup!` commit in place at its original SHA — `--autosquash` is honoured only by the interactive machinery, and the false success is the trap: the fold is reported as done, and the surviving `fixup!` subject then fails the Conventional Commits `commit-msg` hook. Later Git versions taught the non-interactive rebase to honour the flag, but `-i --autosquash` is correct on every version, so always write that.
|
||||
|
||||
@@ -50,9 +50,8 @@ date without a merge commit.
|
||||
4. `rtk git rebase <newbase>` — for example `rtk git rebase main`. Use
|
||||
`rtk git rebase --onto <newbase> <upstream> <branch>` to replay only the commits after
|
||||
`<upstream>`, which is how a branch started from the wrong base gets moved.
|
||||
5. The branch has now diverged from its remote. It needs
|
||||
`--force-with-lease --force-if-includes` to push, never a bare `--force`, and never on
|
||||
`main`/`master` — refuse that and explain.
|
||||
5. The branch has diverged from its remote. Push needs `--force-with-lease --force-if-includes`,
|
||||
never a bare `--force` — and never on `main`/`master`; refuse that and explain.
|
||||
|
||||
## Move the branch pointer back (`git reset`)
|
||||
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# git-history
|
||||
|
||||
Inspect git history — log queries, bisect, and locating problematic commits.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles history inspection within the git workflow suite. It queries logs with pickaxe/line-range/custom formats, runs bisect to find bug-introducing commits, and locates commits for downstream cherry-picking or reverting. It returns structured results for agent composition. Rebase, squash, fixup, and other history-rewriting operations are owned by git-commits, not this skill.
|
||||
|
||||
## Composition
|
||||
|
||||
`git-branches` delegates revert here (see `git-branches`'s `references/merging.md`), which is why this skill carries that operation rather than treating it as out of scope; it is general git knowledge, not drawn from the `history-inspection.md` research corpus. Cherry-pick is **not** this skill's: `git-commits` owns it, and this skill's job ends at locating the SHA to hand over. Server-side commit history on a Gitea-hosted repository belongs to `gitea-branches`; this skill reads the local working copy.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-history
|
||||
```
|
||||
|
||||
Describe your history task: search logs, bisect for a regression, or locate a specific commit. The skill will query history and return structured results.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents |
|
||||
| `references/bisect.md` | Loaded when the entry procedure is bisect: manual and automated flows, exit codes, skip, replay, narrowing, custom terms |
|
||||
| `references/git-log-format.md` | Loaded when a log or diff flag needs looking up: format placeholders, presets, diff-filter letters, `-L` syntax, ancestry filters, pickaxe binary-file behaviour, diff output-control flags |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
| `references/README.md` | Index of the references directory |
|
||||
@@ -8,7 +8,7 @@ description: >
|
||||
`git-commits`. Not a Gitea server's history -> `gitea-branches`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.2"
|
||||
category: git
|
||||
source_keys:
|
||||
- git-scm-bisect-docs
|
||||
@@ -38,7 +38,7 @@ allowed-tools: Bash
|
||||
Default to `rtk git log --oneline`, then narrow by whatever is known:
|
||||
|
||||
- **Content**: `rtk git log -S"string"`, or `-G"regex"` to match any diff line. `--pickaxe-regex` makes the `-S` argument a POSIX ERE; `--pickaxe-all` shows every file in a matching changeset.
|
||||
- **A line or function**: `git log -L <start>,<end>:<file>` or `git log -L :<function>:<file>` — bare, not `rtk`: rtk truncates each diff line at ~72 characters (ADR-0023). Confirm the range resolves before reporting on it — an off-by-one silently omits the target.
|
||||
- **A line or function**: `git log -L <start>,<end>:<file>` or `git log -L :<function>:<file>` — bare, not `rtk`: rtk truncates each diff line at ~72 characters. Confirm the range resolves before reporting on it — an off-by-one silently omits the target.
|
||||
- **A file across renames**: `rtk git log --follow -- <file>`. Without `--follow` the history stops at the rename boundary.
|
||||
- **Mainline only**: `--first-parent` follows the integration branch and skips commits merged in from side branches.
|
||||
- **Structured output**: `rtk git log --format="%h | %s | %an (%ar)"`.
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-bisect-docs
|
||||
- git-scm-log-docs
|
||||
- git-scm-diff-docs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
This directory contains provenance metadata and research sources for the `git-history` skill.
|
||||
|
||||
## Files
|
||||
|
||||
- `sources.md` — Extracted research sources and their contributing documents
|
||||
- `bisect.md` — The full `git bisect` procedure: manual and automated flows, exit-code semantics, skip and replay, narrowing options, and custom good/bad terms
|
||||
- `git-log-format.md` — Full `git log` format placeholder catalogue, named format presets, `--diff-filter` letters, `-L` line-range syntax, ancestry filters, pickaxe binary-file behaviour, and `git diff` output-control flags
|
||||
@@ -166,10 +166,10 @@ line at roughly 72 characters with an ellipsis, on the one query whose whole poi
|
||||
is showing line content.
|
||||
|
||||
```bash
|
||||
git log -L 10,20:file.txt # bare per ADR-0023
|
||||
git log -L /start_pattern/,/end_pattern/:file.txt # bare per ADR-0023
|
||||
git log -L :myfunction:src/app.c # bare per ADR-0023
|
||||
git log -L /init/,+15:config.py # bare per ADR-0023; 15 lines after first /init/ match
|
||||
git log -L 10,20:file.txt # bare (ADR-0023)
|
||||
git log -L /start_pattern/,/end_pattern/:file.txt # bare (ADR-0023)
|
||||
git log -L :myfunction:src/app.c # bare (ADR-0023)
|
||||
git log -L /init/,+15:config.py # bare (ADR-0023); 15 lines after first /init/ match
|
||||
```
|
||||
|
||||
Range formats:
|
||||
@@ -213,8 +213,8 @@ Bare `git`, not `rtk git`: rtk appends a blank line and a `Changes:` trailer, so
|
||||
the output is no longer one record per line.
|
||||
|
||||
```bash
|
||||
git diff --name-only # bare per ADR-0023; only filenames, one per line
|
||||
git diff --name-status # bare per ADR-0023; status letter + filename per line
|
||||
git diff --name-only # bare (ADR-0023); only filenames, one per line
|
||||
git diff --name-status # bare (ADR-0023); status letter + filename per line
|
||||
```
|
||||
|
||||
`--name-status` uses the same status letters as `--diff-filter`.
|
||||
@@ -225,10 +225,10 @@ Bare `git`, not `rtk git`: rtk replaces the word-diff with its own diffstat
|
||||
renderer and emits none of the `[-removed-] {+added+}` markers.
|
||||
|
||||
```bash
|
||||
git diff --word-diff # bare per ADR-0023; inline word-level diff, [-removed-] {+added+} markers
|
||||
git diff --word-diff=color # bare per ADR-0023; color only, no markers
|
||||
git diff --word-diff=porcelain # bare per ADR-0023; machine-readable: +/- prefixed lines, ~ for newlines
|
||||
git diff --word-diff-regex=<re> # bare per ADR-0023; define what counts as a "word"
|
||||
git diff --word-diff # bare (ADR-0023); inline word-level diff, [-removed-] {+added+} markers
|
||||
git diff --word-diff=color # bare (ADR-0023); color only, no markers
|
||||
git diff --word-diff=porcelain # bare (ADR-0023); machine-readable: +/- prefixed lines, ~ for newlines
|
||||
git diff --word-diff-regex=<re> # bare (ADR-0023); define what counts as a "word"
|
||||
```
|
||||
|
||||
### Whitespace Flags
|
||||
|
||||
@@ -1,34 +0,0 @@
|
||||
# git-remotes
|
||||
|
||||
Manage git remote repositories — add/remove/configure remotes, push/pull with safety checks, fetch with pruning, and multi-remote workflows.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles remote operations within the git workflow suite. It manages remote configuration (add, remove, rename), fetch operations with pruning, push operations with force-push safety (`--force-with-lease --force-if-includes`), and pull strategies (fast-forward, rebase, merge). It returns structured results suitable for agent composition.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-remotes
|
||||
```
|
||||
|
||||
Describe your remote operation: add a remote, push, pull, fetch, or configure tracking. The skill will handle the operation with appropriate safety checks and return results.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents — force-push gate, dispatch table, return format |
|
||||
| `references/README.md` | Describes the references directory contents |
|
||||
| `references/remote-config.md` | Read when adding, removing, renaming, inspecting or re-pointing a remote, or configuring tracking, mirroring, or `set-url` |
|
||||
| `references/fetch.md` | Read when fetching or pruning remote-tracking refs, or doing a shallow or partial fetch |
|
||||
| `references/push.md` | Read when pushing branches or tags, writing refspecs, or force-pushing |
|
||||
| `references/pull.md` | Read when integrating remote changes into the current branch, including the divergence rule |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
|
||||
## Composition
|
||||
|
||||
Callers that need submodule initialization after a `--recurse-submodules` pull hand off to
|
||||
`git-submodules`; local-only work (commits, branches, history) belongs to `git-commits`,
|
||||
`git-branches`, and `git-history`. The `git-workflow` skill routes humans here for any
|
||||
remote-touching request.
|
||||
@@ -10,7 +10,7 @@ description: >
|
||||
Not submodule pointers -> `git-submodules`.
|
||||
|
||||
metadata:
|
||||
version: "1.0.1"
|
||||
version: "1.0.3"
|
||||
category: git
|
||||
source_keys:
|
||||
- git-scm-remote-docs
|
||||
@@ -28,7 +28,7 @@ metadata:
|
||||
|
||||
## Step 1 — Clear the force-push gate
|
||||
|
||||
`main` and `master` are a hard refusal: decline a force-push targeting either, whatever confirmation accompanies it, because no local approval can restore what the remote loses. On any other branch, `rtk git push --force` and `-f` run only after the caller passes `confirm: true` for that specific push — for a human caller, prompt instead of failing.
|
||||
`main`/`master` are a hard refusal: decline a force-push to either regardless of confirmation — no local approval restores what the remote loses. Elsewhere, `rtk git push --force`/`-f` run only after `confirm: true` for that specific push; for a human caller, prompt instead of failing.
|
||||
|
||||
## Step 2 — Dispatch
|
||||
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-remote-docs
|
||||
- git-scm-fetch-docs
|
||||
- git-scm-push-docs
|
||||
- git-scm-pull-docs
|
||||
- context7-git-htmldocs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
This directory contains provenance metadata and research sources for the `git-remotes` skill.
|
||||
|
||||
## Files
|
||||
|
||||
- `sources.md` — Extracted research sources and their contributing documents
|
||||
- `remote-config.md` — Remote add/remove/rename/inspect, tracking and mirror options, housekeeping, and the full `set-url` form
|
||||
- `fetch.md` — Fetch and prune options, shallow and partial fetch, the default fetch refspec
|
||||
- `push.md` — Push options, refspec syntax, force-push safety in full, server-side deny policies
|
||||
- `pull.md` — Pull strategies, submodule caveat, the divergence rule, and pull config precedence
|
||||
@@ -50,7 +50,7 @@ Two mitigations:
|
||||
# poisoned by an unrelated fetch.
|
||||
# The inner `git config` is bare: its stdout becomes a remote URL, so any
|
||||
# output rewriting would poison the remote silently.
|
||||
rtk git remote add origin-push $(git config remote.origin.url) # inner bare per ADR-0023
|
||||
rtk git remote add origin-push $(git config remote.origin.url) # inner bare (ADR-0023)
|
||||
rtk git push --force-with-lease origin-push
|
||||
|
||||
# Option 2 — explicit SHA via a local tag, unaffected by tracking-branch state
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
# git-submodules
|
||||
|
||||
Add, initialize, update, pin, inspect, and remove git submodules in multi-repository projects.
|
||||
|
||||
## What it does
|
||||
|
||||
This skill handles submodule operations within the git workflow suite: cloning a superproject with
|
||||
its nested repositories, adding a dependency as a submodule, initializing and updating with
|
||||
pinning or branch tracking, parallel and recursive traversal, rebinding URLs and tracked branches,
|
||||
and the full removal sequence including the `.git/modules/` cleanup git leaves behind. It returns
|
||||
structured results suitable for agent composition.
|
||||
|
||||
It sits alongside the other git skills rather than duplicating them: `git-worktrees` covers
|
||||
multiple checkouts of a single repository, and `git-remotes` covers the superproject's own remotes.
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
/git-submodules
|
||||
```
|
||||
|
||||
Describe the submodule task. The skill applies the shared working rules, dispatches to the
|
||||
reference for that task, and returns structured results (operation, status, per-submodule details,
|
||||
conflicts, and a recovery `next_step` when applicable).
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `SKILL.md` | Skill instructions for agents — gotchas, shared working rules, and the task dispatch table |
|
||||
| `references/README.md` | Describes contents of references/ |
|
||||
| `references/setup-and-update.md` | Loaded when cloning a superproject, adding a submodule, initializing, updating, or re-pinning one, or running a command across all of them — includes the full `add` and `update` flag tables, the pinning workflows, and the `foreach` shell-variable table |
|
||||
| `references/urls-and-config.md` | Loaded when changing where a submodule points or how it is configured — `.gitmodules` vs `.git/config` anatomy, both key tables, `sync`/`set-url`/`set-branch`, local mirror overrides, relative URLs, the custom-`update` security gate, and `absorbgitdirs` |
|
||||
| `references/removal.md` | Loaded when removing or deinitializing a submodule — why `deinit` is not removal, and the four-step removal sequence |
|
||||
| `references/sources.md` | Research sources and provenance |
|
||||
@@ -1,31 +0,0 @@
|
||||
---
|
||||
source_keys:
|
||||
- git-scm-submodule-docs
|
||||
---
|
||||
|
||||
# References
|
||||
|
||||
One file per task branch in SKILL.md's dispatch table. Load only the one that matches the request.
|
||||
|
||||
## setup-and-update.md
|
||||
|
||||
Cloning a superproject that has submodules, adding a dependency as a submodule, initializing
|
||||
without cloning, updating or re-pinning, and running one command across every submodule. Carries
|
||||
the `add` and `update` flag tables, the keep-pinned and move-the-pin-forward workflows, and the
|
||||
`foreach` shell-variable table (`$name`, `$sm_path`, `$displaypath`, `$sha1`, `$toplevel`).
|
||||
|
||||
## urls-and-config.md
|
||||
|
||||
Where a submodule points and how it is configured: the `.gitmodules` vs `.git/config` split, both
|
||||
key tables, `sync` / `set-url` / `set-branch`, local mirror overrides, relative URL resolution, the
|
||||
security gate on custom `update` commands, and `absorbgitdirs`.
|
||||
|
||||
## removal.md
|
||||
|
||||
Removing a submodule, and why `deinit` alone does not remove one. Carries the full four-step
|
||||
removal sequence including the manual `.git/modules/<name>/` cleanup.
|
||||
|
||||
## sources.md
|
||||
|
||||
Research sources that informed this skill — provenance chain for git-scm-submodule-docs reference
|
||||
material.
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user