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/.apm/skills/gitea-labels-milestones/references/labels.md

@@ -3,6 +3,7 @@ topic: labels
 source_keys:
   - gitea-mcp-repo
   - gitea-mcp-slim-go
+  - context7-websites-gitea
 ---
 
 # Label operations
@@ -37,7 +38,7 @@ or **org-scoped** labels — never both in one call. Pick the method family (`*_
 | `name` | string | required for create |
 | `color` | string | hex `#RRGGBB`, required for create |
 | `description` | string | optional |
-| `exclusive` | boolean | org labels only |
+| `exclusive` | boolean | accepted as a *write* param on org creates only — repo labels still carry and enforce `exclusive`, set outside this tool surface |
 | `is_archived` | boolean | repo labels only |
 
 Note: unlike `milestone_read`/`milestone_write`, `owner`/`repo`/`org` are **not** schema-required on
@@ -46,29 +47,50 @@ runtime error from Gitea rather than a client-side validation error.
 
 ## List repo labels
 
-```
+```text
 label_read  method: "list_repo_labels"  owner: <owner>  repo: <repo>  per_page: 50
 ```
 
 Paginate (`page: 1, 2, ...`) until the returned count is less than `per_page`. This is the only way
 to build a complete name → ID map — there is no lookup-by-name endpoint.
 
+Every returned repo label carries its own `exclusive` boolean, so exclusivity is always *readable*
+per repo label. That does not contradict `label_write`'s schema, which annotates `exclusive` as
+"(org only)": reading and setting are different questions, and only the setting half is org-scoped
+(see "Create a label" below). Where the field is `true` Gitea enforces one-label-per-scope
+server-side; where it is `false` labels in that scope stack legitimately. Read the field — never
+infer exclusivity from the `/` in a name, and never carry another repo's map over.
+
+On the instance this skill was authored against (`Defame1297/holocron`) the split ran: every
+`Priority/*`, `Reviewed/*` and `Status/*` label `exclusive: true`, every `Kind/*` label and
+`Compat/Breaking` `exclusive: false`. That is one repo's configuration at one point in time, recorded
+as a worked example of what the field looks like in practice — it is not a property of the taxonomy
+and says nothing about the repo you are called against.
+
 ## Get one label
 
-```
+```text
 label_read  method: "get_repo_label"  owner: <owner>  repo: <repo>  id: <id>
 ```
 
 ## Resolve a name to an ID
 
-There is no direct name lookup. List all repo labels (paginating if needed), scan for a
-case-insensitive name match, and extract `id`. This is the required first step before any label
-application on an issue or PR — the actual `add_labels`/`replace_labels`/`remove_label` call lives
-in `gitea-issues`/`gitea-prs` via `issue_write`/`pull_request_write`, which take numeric IDs only.
+The tool surface carries no lookup-by-name method. List all repo labels (paginating if needed),
+scan for a case-insensitive name match, and extract `id`. Both pools can apply to one issue: if the
+name is not in `list_repo_labels`, also check `list_org_labels` before reporting it unresolved. That method
+takes `org`, not `owner`/`repo` — pass the repo's `owner` as `org`, which is what it means when the
+owner is an organisation. Its failure modes are not interchangeable. `token does not have at least
+one of required scope(s), required=[read:organization]` means the org pool was never queried — report
+that missing scope rather than reporting the label unresolved. Only a not-found response means the
+owner is a user account with no org pool, making the miss a real miss.
+
+Resolution is the required first step before any label application on an issue or PR — the actual
+`add_labels`/`replace_labels`/`remove_label` call lives in `gitea-issues`/`gitea-prs` via
+`issue_write`/`pull_request_write`, which take numeric IDs only.
 
 ## Create a label
 
-```
+```text
 label_write  method: "create_repo_label"
   owner: <owner>  repo: <repo>
   name: "Kind/Bug"
@@ -77,11 +99,14 @@ label_write  method: "create_repo_label"
 ```
 
 For an org label, use `method: "create_org_label"` with `org:` instead of `owner`/`repo`, and
-`exclusive: true` if the label belongs to a mutually-exclusive scope group.
+`exclusive: true` if the label belongs to a mutually-exclusive scope group. `label_write` accepts
+`exclusive` on org methods only, so a repo label's exclusivity cannot be set or cleared through this
+tool — it is set in the Gitea UI or against the REST API directly, and read back via
+`list_repo_labels`.
 
 ## Edit a label
 
-```
+```text
 label_write  method: "edit_repo_label"  owner: <owner>  repo: <repo>  id: <id>  color: "#ff0000"
 ```
 
@@ -89,7 +114,7 @@ Only pass the fields being changed — `id` plus any of `name`/`color`/`descript
 
 ## Delete a label
 
-```
+```text
 label_write  method: "delete_repo_label"  owner: <owner>  repo: <repo>  id: <id>
 ```