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/gitea/skills/gitea-prs/references/pull-requests.md

@@ -7,7 +7,7 @@ source_keys:
 
 # Pull request read/write execution detail
 
-Parameter signatures below are cross-checked live against the deployed gitea-mcp server tool schemas at authoring time — not copied verbatim from the plugin's research doc for this domain, which has a known history of drifting from the deployed server (e.g. a prior `type` parameter that no longer exists on `list_issues`, and the `review_scomments` typo covered in `references/reviews.md`). Re-verify via `ToolSearch` before trusting this file if the gitea-mcp version changes.
+Parameter signatures below are cross-checked live against the deployed gitea-mcp server tool schemas at authoring time — not copied verbatim from the plugin's research doc for this domain, which has a known history of drifting from the deployed server. These files were last verified against gitea-mcp **v1.7.0**, as reported by `get_gitea_mcp_server_version`. Re-verify via `ToolSearch` before trusting this file if the deployed version differs — drift has bitten this skill in both directions, adding methods it does not list and fixing quirks it still warns about.
 
 ## `list_pull_requests`
 
@@ -29,14 +29,14 @@ List responses trim PRs down to summary fields — `head`/`base` are bare ref st
 - `owner` (string, required)
 - `repo` (string, required)
 - `pull_number` (number, required)
-- `review_id` (number, optional) — required for `"get_review"` and `"get_review_comments"`; see `references/reviews.md`
+- `review_id` (number, optional) — required for `"get_review"`, which errors with `review_id is required` without it. **Optional** for `"get_review_comments"`: omit it to list every inline comment on the PR in one call. See `references/reviews.md`
 - `binary` (boolean, optional) — include binary diff content for `"get_diff"`
 - `page` (number, optional, default 1)
 - `per_page` (number, optional, default 30)
 
 `"get"`, `"get_diff"`, `"get_files"`, and `"get_status"` are covered here. `"get_reviews"`, `"get_review"`, and `"get_review_comments"` are covered in `references/reviews.md`.
 
-- `"get"` returns the full PR object: state, draft, merged, mergeable flags; `head`/`base` as full objects (`{ref, sha, repo?}`); `milestone` as a bare title string (not `{id, title}`); `review_scomments` (typo, see `references/reviews.md`).
+- `"get"` returns the full PR object: state, draft, merged, mergeable flags; `head`/`base` as full objects (`{ref, sha, repo?}`); `milestone` as a bare title string (not `{id, title}`); and `review_comments`, *when present*, as an integer count rather than comment objects — it was absent from a live `"get"` on a PR with no inline comments, so verify the key before reading it (see `references/reviews.md`).
 - `"get_diff"` returns raw diff text.
 - `"get_files"` returns the list of changed file objects.
 - `"get_status"` returns the combined commit status for the PR's head commit — CI result only, not review/approval state (see `references/merging.md`).
@@ -68,7 +68,7 @@ List responses trim PRs down to summary fields — `head`/`base` are bare ref st
 
 Merge-specific parameters (`merge_style`, `delete_branch`, `force_merge`, `merge_when_checks_succeed`, `head_commit_id`, `message` as merge commit message) are covered in `references/merging.md`.
 
-**`"create"` silently drops most optional parameters.** `"create"` reads only `owner`, `repo`, `title`, `body`, `head`, `base`, `draft`, `labels`, and `deadline`. Every other optional parameter — including `assignee`, `assignees`, `milestone`, `reviewers`, `team_reviewers` and `remove_deadline` — is accepted without error and discarded. There is no error, no warning, and nothing in the response distinguishing a dropped parameter from one that was never passed: the response simply omits the key. Setting any of them requires a second call after the PR exists — `"update"` for `assignee`/`assignees`/`milestone`, `"add_reviewers"` for `reviewers`/`team_reviewers`.
+**`"create"` silently drops most optional parameters.** `"create"` reads only `owner`, `repo`, `title`, `body`, `head`, `base`, `draft`, `labels`, and `deadline`. Every other optional parameter — including `assignee`, `assignees`, `milestone`, `reviewers`, `team_reviewers` and `remove_deadline` — is accepted without error and discarded. Nothing marks the drop: no error, no warning, and nothing in the response distinguishing a dropped parameter from one that was never passed — the response simply omits the key. Setting any of them requires a second call after the PR exists — `"update"` for `assignee`/`assignees`/`milestone`, `"add_reviewers"` for `reviewers`/`team_reviewers`.
 
 Two things make this easy to miss: