## Why
The manifest-fields tables in both skills used imprecise labels ("CC-only",
"Copilot-only") that conflated two distinct reasons a field appears in only
one manifest: platform constraint (the other tool does not support the field
at all) versus repo convention (both tools support it, but the scaffold places
it in one manifest by design). This caused agents to treat convention
boundaries as hard platform constraints, producing unnecessary errors when
updating manifests for dual-tool repos.
Provenance was also incomplete: sources.md files were missing entries for
sources that had been consulted and were already contributing to SKILL.md
and manifest-fields.md content, making the evidence chain unverifiable.
## Implementation Notes
Field classification now uses three explicit categories — shared, platform
(one tool does not support the field), and convention (both tools support it;
scaffold places it in one manifest by design). The distinction matters because
convention fields may legitimately appear in the other manifest when there is
a deliberate reason; platform fields may not.
New gotchas added to plugin-author: agent files silently ignore hooks,
mcpServers, and permissionMode frontmatter; claude plugin tag --push requires
a clean working tree; --dry-run preview before tagging; --strict flag on
validate. New gotchas in marketplace-author: metadata object as Copilot CLI
canonical location for top-level fields; strict: false for dual-tool plugins;
sha takes precedence over ref for pinning; --strict flag on validate.
tests/ removed from plugin-author because new-plugin.sh has no branching
logic warranting a bats suite at this stage.
## Impact
Skill prompt changes only — no runtime code affected. Agents using these
skills will now correctly distinguish convention from constraint when deciding
which manifest to update for a given field.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
Plugin and marketplace management had no governed authoring path. Creating or
updating a plugin required knowing the dual-manifest convention, version parity
rules, and directory skeleton by memory — nothing enforced consistency or guided
the process.
`/plugin-author` closes that gap by owning the full plugin scaffold lifecycle:
create, update, rename, and release. `/marketplace-author` handles the
marketplace-facing side: register, deregister, and update plugin entries in
`marketplace.json`.
ADR-0016 codifies the version parity convention (identical `version` in both
`plugin.json` and `.claude-plugin/plugin.json`) that `/plugin-author` now
enforces. The two plugin.json files in this repo are backfilled to comply
(keys also sorted to pass the pretty-format-json hook). CONTEXT.md gains
glossary entries for "plugin scaffold" and "version parity" so future agents
have shared vocabulary for these concepts.
## Implementation Notes
`/plugin-author` ships a `scripts/new-plugin.sh` scaffold script that generates
the directory skeleton and both manifests in one shot; the skill calls the script
rather than generating files ad hoc so the scaffold is reviewable and repeatable.
Version parity is an invariant, not a suggestion — the skill will fail loudly
on create/update if the two versions would diverge.
ADR: docs/adr/0016-plugin-version-parity.md
## Why
Five gap areas were identified when auditing the config against tracked file extensions and the hooks reference:
- No TOML validator despite 2 `.toml` files tracked
- No Python AST check despite 10 `.py` files tracked
- No merge-conflict marker detection
- No PEM private key block detection (gitleaks covers high-entropy strings but not raw PEM)
- No meta-validation to catch hooks that match no files or useless exclude patterns
## Impact
All five new hooks pass on `--all-files` run.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P87CiC58Ru2PPWYTeXtjHT
Installing kyberforge via the holocron marketplace caches the plugin at a
specific version. After every push, the marketplace clone and plugin cache
need to be refreshed manually — otherwise new skills added since the last
install are invisible until the user runs `claude plugin update` manually.
Adds a post-push git hook that pulls the holocron marketplace clone and
updates the kyberforge cache automatically after every push, eliminating
the manual refresh step.
## Implementation Notes
- `scripts/git-hooks/post-push` is the canonical source; `install.sh` now
copies all files in `scripts/git-hooks/` into `.git/hooks/` on fresh
checkouts, making the pattern extensible for future hooks.
- Hook exits 0 on all failures (warns to stderr) — a stale cache refresh
never blocks a completed push.
- 11 bats tests cover both the hook and the install.sh copy block, using
mocked binaries and a temp-tree fixture to avoid touching real state.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P87CiC58Ru2PPWYTeXtjHT
## Why
Plugin cache is keyed by version string. Adding pc-author and pc-run
skills requires a version bump so claude plugin update resolves a new
cache directory and picks up the new skills.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P87CiC58Ru2PPWYTeXtjHT
## Why
Pre-commit config management was entirely manual — no skill existed to
help create, modify, or validate `.pre-commit-config.yaml`, or to run,
install, and maintain the pre-commit setup. These two skills close that
gap with clear scope separation: authoring vs. execution.
## Implementation Notes
- `pc-author` owns `.pre-commit-config.yaml` only (no hook publishing,
no install). Runs `pre-commit validate-config` after every write.
Shallow file-extension scan drives proactive hook recommendations;
rev staleness is flagged against `references/hooks-by-language.md`
rather than hardcoded versions. Remove path reverts on failure.
- `pc-run` owns install, run, autoupdate, gc, and clean. Defaults to
`--all-files`. Install warns about existing `.git/hooks/` files being
overwritten by `-f`. Clean requires HITL confirmation. Failure
interpretation delegates to `references/failure-patterns.md`.
- Provenance wired to `plugins/kyberforge/docs/research/docs/pre-commit/`.
- Both skills resolve via the existing `"skills/"` glob in `plugin.json`.
## Impact
Two new slash commands available after `claude plugin install kyberforge@holocron`:
`/pc-author` and `/pc-run`.
Refs: #12
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P87CiC58Ru2PPWYTeXtjHT
## Why
The root marketplace.json is the index that ties all plugins together.
claude plugin validate --strict covers schema-level checks that
check-manifests.sh does not, so it warrants its own hook alongside
validate-plugins.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
`claude plugin validate --strict` catches structural issues in plugin
manifests that `check-manifests.sh` does not cover (e.g. schema
violations, unrecognised fields). Running it at pre-push ensures all
plugins in `plugins/*/` stay valid before reaching the remote.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Set 'ignore = dirty' for tests/bats and test_helper submodules to prevent accidental
staging of test-time modifications. These submodules should never be committed with
changes — they're only for running the test suite locally.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Update docs to reflect pre-commit migration and cleanup:
- spec/overview.md: removed phantom test file references
- ROADMAP.md: removed references to non-existent test files
- LESSONS.md: removed reference to setup-hooks.sh bug
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Removed .git/hooks/pre-commit.legacy and scripts/setup-hooks.sh — fully replaced by .pre-commit-config.yaml.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
## Why
The initial research pass focused on agent definitions. An audit identified
critical and minor gaps in both doc sets around plugin publishing, marketplace
registration, and the Copilot extensibility model.
## Implementation Notes
Claude Code gaps filled: end-to-end publish walkthrough (scaffold → validate →
tag → host → register), CLI vs in-session command surface equivalence, all six
marketplace source URL formats, plugin update/upgrade lifecycle, interactive
plugin manager UI, private marketplace auth, `commands` vs `skills/` distinction.
Copilot gaps filled: discovered that the GitHub App-based Copilot Extensions
track was sunset November 2025. Created copilot-extensions.md as historical
reference (deprecated, with MCP servers as the current replacement path).
Documented the agent vs. skillset extension type distinction, OAuth install
flow, and VS Code Chat Participants as the surviving @mention mechanism.
overview.md updated with a "Which Track to Use" decision table covering all
four active tracks plus the deprecated one.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
Two recurring failure modes surfaced during the agent-author workstream
that are worth capturing before they repeat: biased forks producing
false-PASS audits, and parallel forks producing conflicting fixes on
the same file.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
The convention requires living spec files to be updated in the same
commit as any behaviour change. Adding agent-author to kyberforge
without updating overview.md would leave the spec stale.
## Impact
kyberforge plugin entry now accurately reflects its three current skills
(skill-author, skill-audit, agent-author) and drops the outdated
reference to create-plugin, marketplace-architect, write-skill, and
write-eval which are no longer in the plugin.
---
Refs: #10
ADR: docs/adr/0015-agent-author-dual-provider-scaffold.md
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
skill-author explicitly excludes agent definition files ("Do not use to author
agent definition files"). No factory skill existed to create or improve the
.md / .agent.md files that define Claude Code subagents and Copilot CLI agents
in a plugin, project, or user scope. This fills that gap.
## Implementation Notes
Single-root scaffold convention: new-agent.sh <name> <root> derives both
provider file paths from the root by convention — plugin scope (plugin.json
present) writes both files into <root>/agents/; non-plugin scope writes
.claude/agents/<name>.md and .github/agents/<name>.agent.md. This keeps
input minimal while always generating both provider files. See ADR-0015.
Routing is file-level (not directory-level like skill-author): neither file
exists → create flow; at least one exists → improve flow; scaffold is a
file-by-file no-op so retries are safe.
No companion agent-audit skill — inline validation in the close step covers
the simpler agent field contract. agent-audit is tracked as a follow-on.
## Impact
Closes the skill-author gap for agent definitions. Follow-ons tracked in
Gitea #11: agent-audit skill and --copilot-dest override flag for non-standard
Copilot project paths.
---
ADR: docs/adr/0015-agent-author-dual-provider-scaffold.md
Refs: #10
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
Parallel research track to the Claude Code plugins research already
committed. Needed to understand GitHub Copilot's extensibility model
before designing cross-tool plugin compatibility for the kyberforge
plugin system.
## Implementation Notes
Three distinct Copilot extension tracks are covered: CLI plugins
(plugin.json + marketplaces), cloud/IDE custom agents (frontmatter .md
files committed to repos), and the SDK programmatic API. The SDK track
got its own topic file (sdk.md) because the content doesn't fit neatly
into the default topic list. Sources include Context7 (/websites/github_en_copilot),
both user-provided reference URLs, and four additional deepened pages.
## Impact
Provides a reference baseline for evaluating .claude-plugin/ / plugin.json
compatibility between Claude Code and Copilot CLI — the two formats share
a manifest discovery path and the strict:false field enables cross-tool
plugin distribution.
---
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
`core/AGENTS.md` referenced a non-existent path (`~/.claude/core/commits.md`)
instead of the correct `~/.claude/core/instructions/commits.md`, and contained a
typo ("commiting" → "committing"). `core/instructions/commits.md` was wrapped in
an erroneous markdown code fence that caused agents reading the file to see it as
a raw text block rather than a live template with usable HTML comment sections.
## Impact
Agents following the content index in AGENTS.md will now resolve the correct path
for commit conventions. The commits template is now properly structured so its
comment-gated sections render as intended.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
The existing git.md was thin — missing atomicity, working-state, and
trailer guidance that belong in any professional git workflow. No commit
message template existed, making the expected format implicit and
inconsistent across sessions.
## Impact
- git.md is now the canonical reference for commit hygiene rules
- commits.md provides a structured template (Why / Implementation Notes /
Impact / Git Trailers) that agents and humans can follow
- AGENTS.md cross-references commits.md so it is discoverable at session
start
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
The Obsidian MCP server (mcpvault) wasn't wired up in this repo's local
config, making obsidian tools unavailable. The bin@holocron plugin was
added to settings but not yet listed in the allowed plugins.
## Impact
- Obsidian MCP tools are now available when working in this repo
- bin@holocron plugin is enabled in .claude/settings.json
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Research from official docs (code.claude.com) and Context7, covering
plugin manifest schema, agent definition frontmatter spec, scope
priority, marketplace distribution, and plugin subagent restrictions.
Foundation for writing an agent-author skill.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
skill-audit description understated its coverage by omitting three audit
dimensions (patterns, scripts, provenance); README carried the same stale
list. skill-author had an unconditional reference trigger that should be
conditional on whether a script is being added.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds behavior rule to always prefer subagents (clean or with session context)
for well-bounded actions that require no human interaction, keeping the parent
context lean and enabling parallel execution.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove implementation-focused sentence from description (was not user-intent
language per agentskills.io spec)
- Move source_keys template comment under metadata: block to match Step 5's
instruction; contradicted agents scaffolding before reading Step 5
- Add Step 6 to new-skill.sh next-steps (populate references/sources.md);
renumber validate step to 7 — script was missing the sources step entirely
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
references/sources.md Research doc: fields are development-only provenance
pointers, not runtime references — they intentionally target paths outside the
skill directory and are expected to be non-resolvable after plugin install.
validate-provenance.sh degrades gracefully when they don't resolve.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Record the decision to add INFO as a third skill-audit finding level
(observational, non-actionable, does not affect pass/fail). Add
Provenance chain and INFO (finding level) to CONTEXT.md glossary.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add Research doc: pointer to all 7 agentskillsio entries so the new
validate-provenance.sh upstream checks resolve correctly for this skill.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Step 5 now records a Research doc: path per entry in references/sources.md,
pointing to the upstream plugin-level research file the slug was drawn from.
Updates the sources.md template to include the new required field, formalise
comma-separated Contributing files, and document the (none) convention.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add Research doc: pointer to all 7 agentskillsio entries so the new
validate-provenance.sh upstream checks can resolve the research source.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add validate-provenance.sh and validate-provenance.bats to enforce the
sources provenance chain introduced by skill-author. Eight checks cover
slug cross-references, Contributing files existence, bidirectional
source_keys linkage, Research doc: field presence, and upstream research
doc alignment (forward INFO, reverse FAIL). Adds a new Provenance report
dimension and INFO finding level (observational, exit-0, counted
separately as · P info in the result block).
Closes#8
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Records the upstream agentskills.io sources that informed skill-audit,
continuing the research → docs → skill provenance chain.
- New references/sources.md with 7 extracted sources attributed to skill files;
agentskills-llms-txt demoted to discovery-only comment per skill-author precedent
- source_keys frontmatter added to SKILL.md (5 slugs), references/body-discipline.md
(agentskills-spec, agentskills-best-practices), and references/description-quality.md
(agentskills-spec, agentskills-optimizing-descriptions)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- script: new-skill.sh now exits 0 when target already exists (idempotent
retry-safe) instead of exit 1; --help updated to reflect narrowed error cases
- test: updated bats test to assert success and "nothing to do" output
- body: removed speculative "Extract the skill from a real task" advice
(human-targeted, not agent-actionable)
- formatting: converted H4 headings in Step 2 to bold text (H2/H3 two-tier model)
- provenance: removed orphan agentskills-llms-txt entry from references/sources.md;
added discovery-only comment
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Records the upstream agentskills.io sources that informed skill-author,
completing the research → docs → skill provenance chain introduced in
the previous commit.
- New references/sources.md with all 7 extracted agentskillsio sources,
Contributing files attributed per-source to SKILL.md, references/deployment-modes.md,
and references/scripts.md
- source_keys frontmatter added to SKILL.md (all 7 slugs), references/deployment-modes.md
(agentskills-spec), and references/scripts.md (agentskills-using-scripts)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a sources provenance step to the skill creation workflow so the
chain from research output to skill content is traceable. Closes#4.
- New scaffold template `assets/templates/references/sources.md` mirroring
the research skill's sources.md format (slug → URL, description,
contributing files, status)
- `source_keys` commented-out optional field added to the SKILL.md
template, mirroring how research topic files link back to sources
- New Step 5 in the creation workflow: populate references/sources.md
from research input (attributing contributing skill files) or delete it
if no research was provided; add source_keys to SKILL.md and any
references/*.md files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Push submodule before parent, check for -dirty flag, use rtk git
only for parent repo operations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@CONTEXT.md was deliberately removed from repo CLAUDE.md to reduce
token usage; the test enforcing its presence was no longer valid.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove @CONTEXT.md directive from CLAUDE.md (stale reference) and
reorder settings.json to put hooks before enabledPlugins for consistency.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
run-tests.sh calls run-bats.sh which picks up .bats files — testing
run-tests.sh from within bats creates an infinite loop. Shell runner
scripts (run-tests.sh, run-bats.sh) are not bats-tested by design.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
