Files
holocron/plugins/git/skills/git-commits/SKILL.md
Claude Code AI - Gitea MCP 598a7c326a refactor(skills): retrofit the corpus to the ADR-0020 context contract (#129)
Retrofits all 39 skills to ADR-0020's description/body context contract, then fixes what six rounds of independent review found in that retrofit — including four ways the hot gate itself failed open.

Closes #99, #107, #108, #110, #111, #114, #115, #120.

## The retrofit (waves 1-5)

| | Start | Now |
|---|---|---|
| Description FAILs (>400 chars) | 26 | **0** |
| Body FAILs (>900 words, body-only) | 9 | **0** |
| Dangling routing targets | 2 | **0** |
| `Kyberforge.CompositionNote` | 10 | **0** |
| Preload tax | 21,005 chars | **~10,500** |

Under the 12,000-char success criterion. Per-wave detail is on #99.

## The review fixes

**The gate failed open four ways, three of them found after the retrofit shipped.** An unrecognised follower token made a dangling target vanish. A skill directory with no `SKILL.md` resolved as a valid target, so a commit could be green locally and red in a fresh clone — three existing fixtures were relying on that, one of which made the install-leak A/B pass vacuously. Then the free-standing `/name` sweep turned out to be gated on the sentence carrying a boundary marker, so route notation in any other sentence was invisible — not an ERROR, not a SUGGESTION, not an INFO — which left the documented "`/name` always blocks" promise false from a second direction. All four fixed and pinned.

**Two checks were silently not running.** `validate-provenance.sh` checks 7-8 were dead across nine skills. Waking them exposed a deeper problem: they assume `Research doc:` names a source index, but 30 of 121 entries point at topic content documents, so every new check-7 INFO was a false positive and check 8 was saved from a false-FAIL flood only by an *unannounced* skip. Checks 7/8 are now scoped to source indexes and every skip announces itself (#121).

**The retrofit's own anti-goal, four times.** ADR-0020 warns that a blunt gate gets satisfied by deleting content rather than relocating it. `diagnose` and `skill-audit` relocated prose and then read it unconditionally; `prototype` and `vale-config` deleted rules outright that survived nowhere. All four addressed.

## Verification

- `bash tests/run-tests.sh --strict` — 24 suites, 0 skipped, 0 failed
- `bash tests/run-bats.sh` — 325 tests, 0 failures
- `pre-commit run --all-files` — 17/17
- `pre-commit run --hook-stage pre-push --all-files` — 16/16, with `apm marketplace check` and `apm pack --check-clean` run against the remote, not skipped
- `scripts/skill-size-check.sh` over all 39 skills — rc 0, 0 ERROR/FAIL, SUGGESTION-only
- Preload tax measured at **10,498 chars**, max description 390 — both inside budget
- Every new test proven non-vacuous by a deliberate mutation of the behaviour it covers

**Per-commit sync, stated accurately:** the ten commits from the latest review round each pass `check-plugin-content-sync` in isolation, verified by checking each out in a detached worktree with a clean between. The earlier gitea window (`dfacf05..bedbd1d`, nine commits) does **not** — its mirror was regenerated in one batch at `bbc7300`. An earlier revision of this description claimed the property held for every commit; it does not, and a bisect through that window lands on a red commit. **Squash-merge** to collapse it, or accept that this range is not bisectable.

## Version bump

Six plugins and the catalog take a **patch**, not a minor. The branch is **89 commits — 40 `fix` / 30 `refactor` / 12 `docs` / 5 `chore` / 2 `test` — zero `feat`, zero `!`, zero `BREAKING CHANGE`** — and adds no skill, agent, command or hook. (Two earlier revisions of this section cited a stale histogram, most recently 78 commits; the figures above are measured at HEAD.) Both rules this repo ships (`forge/references/version-bump.md`, landing in this PR, and `git-commits/references/conventional-commits-spec.md`) make that a patch, and the catalog set is unchanged at 7 entries.

Not settled by that: four published files were removed from the installed tree, three moved, and `caveman` gained `disable-model-invocation`, retiring its old triggers. Under a strict reading those are major-class and currently ship under `refactor:` with no marker. Whether the deployed skill surface is a public contract is written down nowhere — worth deciding, but it outlives this PR.

## Deliberately not in scope

#112 (cherry-pick ownership, now resolved in favour of `git-commits`), #113 (`rtk git` normalisation), #116 (research fan-out), #101 (audit-skill merge), #122 (non-spec skill-root files), #123 (no PRD producer) stay open. #117 is the one worth reading: the contract's remedy is to move prose into `references/`, which is exactly where neither the size gate nor Vale looks — and the blind spot is wider than #117 currently records, since there is no root `.vale.ini` at all, so every ADR, `CONTEXT.md` and `README.md` is unlinted too.

That blind spot let this branch carry two `level: error` `Kyberforge.SentenceOpenerThereIs` violations into `references/` files it created — `provider-adapter-author/references/provider-matrix.md:31` and `agent-audit/references/finding-criteria.md:95`. Both are reworded in `afadaae`, confirmed by routing each file through the audit's own `vale-wrap.sh` (1 error each before, 0 after). Five further occurrences sit in `references/` files already on `main`; those are the pre-existing corpus and stay with #117, which is the real fix.

Also unfixed and not this PR's: `apm install` appends a duplicate `SessionStart` entry to `.claude/settings.json`, so a fresh clone cannot get pre-push green without an edit AGENTS.md warns against. Reproduces identically on `main`.

Co-authored-by: Defame1297 <gitea@rkdr.net>
Reviewed-on: https://git.dev.rkdr.net/Defame1297/holocron/pulls/129
Co-authored-by: Claude Code AI - Gitea MCP <claude@noreply.git.dev.rkdr.net>
Co-committed-by: Claude Code AI - Gitea MCP <claude@noreply.git.dev.rkdr.net>
2026-09-01 13:47:46 +00:00

3.6 KiB

name, description, metadata, allowed-tools
name description metadata allowed-tools
git-commits Use when creating, amending, squashing, or cherry-picking commits, including writing and validating the Conventional Commits message. Not history inspection -> `git-history`. Not branch lifecycle -> `git-branches`.
version category source_keys
0.1.3 git
conventional-commits-spec
commitlint-config-conventional
org-commit-conventions
context7-git-htmldocs
Bash

Gotchas

  • Run git as rtk git <subcommand>, never bare git — org convention, in && chains too.
  • 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.
  • 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.

Dispatch

Read exactly one flow file. Each is self-contained.

Condition Flow Read
Composing a new commit from staged changes create references/create-commit.md
Amending, squashing, folding a fixup, rebasing onto a new base, or resetting HEAD rewrite references/rewrite-history.md
Replaying an existing commit onto the current branch cherry-pick references/cherry-pick.md

Gates on every flow

  1. Confirmation. No history rewrite executes without explicit approval from the user or the calling agent. Cherry-pick needs the destination branch confirmed first.
  2. Atomicity. The result must be one logical, independently reviewable and reversible change that leaves the repository buildable and testable. This binds an amend or a squashed result as much as a fresh commit — say so before writing it, not after.
  3. Secrets. Before any commit or amend, scan the staged diff for anything resembling an API key, token, password, connection string, or environment-specific config. Stop and flag it rather than committing it.
  4. Validation. Check the message against commitlint config-conventional before committing. If a type, footer, or breaking-change edge case is not obvious, read references/conventional-commits-spec.md — it carries the constraint table, the 11-type set, and the footer token rules.
  5. SemVer impact. Report the bump the commit implies: feat → MINOR, fix/perf/revert → PATCH, any breaking change → MAJOR, everything else → none. Callers decide releases from this, so never omit it.
  6. Conflicts. If a rebase or cherry-pick halts, offer resolution or an abort. Do not resolve automatically without confirmation.

Output

For an agent caller, return:

{
  "operation": "create|amend|squash|cherry-pick",
  "status": "success|conflict|rejected",
  "message": "commit message or error description",
  "commit_hash": "abc1234",
  "semver_impact": "MAJOR|MINOR|PATCH|none",
  "breaking_change": false,
  "confirmation_required": false,
  "details": {
    "type": "feat",
    "scope": "api",
    "description": "add user authentication",
    "body": "optional body text, or null",
    "footers": ["Fixes: #123", "Refs: #456", "Co-authored-by: Bob <bob@example.com>"]
  }
}

details.footers is an array of the resolved trailer lines, empty when there are none — never a single joined string, and never omitted. Downstream agents index it.

For a human caller, show the same fields as a prose preview with a confirmation prompt.