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>

plugins/git/.apm/skills/pc-author/references/modify-config.md

@@ -0,0 +1,75 @@
+---
+source_keys:
+  - context7-pre-commit-com
+  - pre-commit-com
+---
+
+# Modifying an existing `.pre-commit-config.yaml`
+
+Reached from `SKILL.md`'s Route table when the repo already has a config. Self-contained — the
+create flow's file is not needed here. `SKILL.md`'s three common gates still apply.
+
+Read the existing `.pre-commit-config.yaml` before editing. Note any stale `rev` values (see
+**Rev staleness** below) but do not change them.
+
+## Adding a hook
+
+1. Run a shallow extension scan, so the addition is judged against the languages actually present:
+
+   ```bash
+   git ls-files | grep -oE '\.[a-z]+$' | sort | uniq -c | sort -rn
+   ```
+
+2. Read `references/hooks-by-language.md` for the correct repo URL, `rev` and recommended args
+   before writing anything.
+
+3. Check for duplicates. If the same hook ID, or an equivalent tool, is already configured, say so
+   and stop rather than adding a second one.
+
+4. To sanity-check a hook against the repo's real files before committing to it, smoke-test it:
+
+   ```bash
+   pre-commit try-repo <repo-url> <hook-id> --verbose
+   ```
+
+   Use a local path in place of the URL for a hook under development. This runs the hook without
+   writing anything.
+
+5. If the hook's source repo is already a block in the config, add the hook under that block.
+   Otherwise append a new repo block.
+
+6. State the proposed addition, wait for confirmation, write, and run `pre-commit validate-config`.
+   On a non-zero exit, show the error, fix it, and re-validate.
+
+## Removing a hook
+
+1. Identify the hook entry and its parent repo block.
+
+2. State what will be removed — the hook ID, and whether the parent repo block goes with it because
+   it would be left with zero hooks. Wait for confirmation.
+
+3. Remove the hook entry. If the repo block now has no hooks left, remove the whole block: an empty
+   `hooks: []` fails `validate-config`.
+
+4. Write, then run `pre-commit validate-config`. On a non-zero exit, **revert the edit**, show the
+   error, and stop. A removal is not safely fixable in place the way a malformed new hook block is,
+   so recovering the prior state beats patching forward.
+
+## Configuring top-level keys
+
+Only when the user explicitly asks. Valid keys: `fail_fast`, `default_stages`,
+`default_language_version`, `minimum_pre_commit_version`, `exclude`, `files`,
+`default_install_hook_types`.
+
+State the proposed change and wait for confirmation before writing.
+
+## Rev staleness
+
+For each repo in the config that also appears in `references/hooks-by-language.md`, compare the
+two `rev` values. Flag a mismatch as potentially outdated and tell the user to run `pc-run` to
+autoupdate. Repos absent from the reference cannot be checked — skip them silently. Do not modify
+any `rev` yourself.
+
+The reference table's own pins go stale between updates, so treat a mismatch as a prompt to check
+rather than proof of staleness. `pre-commit autoupdate`, via `pc-run`, is the authoritative answer
+to what the current `rev` actually is.