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/skills/git-workflow/SKILL.md

@@ -2,12 +2,10 @@
 name: git-workflow
 
 description: >
-  Use when a human user wants to perform git workflows interactively — commits, branch management,
-  history inspection, submodules, worktrees, or remotes. Provides a friendly, conversational
-  interface with clarification prompts ("Which branch base?"), progress updates, inline help,
-  best practices guidance, and confirmation dialogs for destructive operations. Guides users
-  through complex git patterns even if they don't mention every detail. Do not use when the
-  caller is an agent—agents should invoke git-orchestrate directly for deterministic, composable execution.
+  Use when a human's local git request is general or ambiguous — it routes to the owning
+  domain skill: `git-commits`, `git-branches`, `git-history`, `git-remotes`, `git-submodules`
+  or `git-worktrees`. An unambiguous request goes straight to its domain skill instead. Not an
+  agent caller -> `git-orchestrate`. Not Gitea -> `gitea-workflow`.
 
 metadata:
   category: git
@@ -21,45 +19,61 @@ metadata:
 
 ## Gotchas
 
-- This skill is specifically for **human interaction**. If the caller is an agent, invoke `git-orchestrate` directly instead—this skill adds UI overhead agents don't need.
-- Session context from previous git operations (branch names, commit strategy) persists during a single multi-step user request, then clears. Users don't need to re-provide decisions within one workflow.
-- Destructive operations require explicit confirmation: force-push, branch deletion, rebase with history loss, force-checkout. Users must confirm interactively; the skill never proceeds without their approval on destructive ops.
-- Run git commands through `rtk git <command>` rather than bare `git <command>` for parent-repo operations — this is a mandated org wrapper, not an optional style choice. Drop into a submodule's own directory for submodule-specific commands (see `git-submodules`).
+- Session context built during one multi-step request — branch names, the chosen base, the commit
+  strategy — persists for that request and then clears. Do not re-ask the user for a decision they
+  already gave you earlier in the same workflow.
+- Run parent-repo commands through `rtk git <command>`, never bare `git <command>`. This is a
+  mandated org wrapper, not a style preference. Submodule-specific commands run from inside the
+  submodule's own directory instead.
 
-### Hard rules
+## Domains
 
-These are non-negotiable regardless of what the user asks for — surface them proactively rather than waiting for the user to hit them (`org-git-conventions`; sub-skills invoked directly by humans, like this one, carry their own local copy of these rules for readers who won't chain through `git-orchestrate`, so state them plainly rather than assuming the user already knows them):
+Route to the domain that owns the operation, and in sequence when a request spans two — a rebase
+that ends in a force-push is `git-commits`, then `git-remotes`. An unambiguous request should have
+gone straight to the domain skill; this one exists for the ones that did not.
 
-- Never skip hooks with `--no-verify` — hooks are the automated QA gate, and bypassing them breaks the pipeline for everyone downstream.
-- Never force-push `main` or `master`.
-- Keep commits atomic — each commit should represent one logical, independently reviewable and reversible change.
-- Every commit must leave the repository in a working state (buildable/testable where practical).
-- Commit messages explain **why**, not **what** — the diff already documents what changed.
-- Never commit secrets, credentials, or environment-specific config.
-- Use Conventional Commits (`feat:`, `fix:`, `docs:`, `chore:`, `refactor:`, `test:`, etc.).
-- Reference related issues, ADRs, or design documents using Git trailers when applicable.
+| The request is about | Domain |
+|---|---|
+| Writing, amending, squashing, or cherry-picking a commit, and its message | `git-commits` |
+| Rebasing onto a new base, or undoing a commit with `reset` | `git-commits` |
+| Creating, switching, deleting, renaming, tracking, or merging a local branch | `git-branches` |
+| Stashing work in progress to move between branches | `git-branches` |
+| When a change landed, which commit broke something, what to revert or backport | `git-history` |
+| Anything touching a remote — remote config, fetch, push, pull — even unnamed | `git-remotes` |
+| A nested repository pinned inside this one by a recorded commit | `git-submodules` |
+| Several branches checked out at once, in separate directories, without stashing | `git-worktrees` |
 
-If a user's request conflicts with a hard rule (e.g. "force-push main to fix this"), explain the rule and propose a safe alternative instead of complying.
+`git-orchestrate` executes whatever this resolves to (step 5); the table only decides which domain
+owns the request.
 
 ## Workflow
 
-When a user wants to perform git workflows:
-
-1. **Parse the user's intent** — extract the high-level task (commit, create branch, rebase, inspect history, etc.) and any explicit options they mentioned.
-2. **Build session context** — gather repo state, current branch, any prior decisions in this workflow (branch intent for commit messages, base branch for rebasing, etc.).
-3. **Invoke git-orchestrate agent** — call it with:
-   - `operation`: the git operation (e.g., "commit", "create-branch", "rebase")
-   - `parameters`: user-provided or inferred options
-   - `context`: decisions and repo state from prior steps in this workflow
-   - `confirm`: `true` if a destructive op and the user confirmed, otherwise omit
-4. **Handle the response** — if orchestrator succeeds, present results in plain language with progress updates and explanations. If it fails, show the error reason and suggest recovery actions.
-5. **Clarification prompts** — if the orchestrator needs more information (e.g., "Which branch should this be based on?"), prompt the user conversationally and loop back with the user's input.
-6. **Confirmation gates** — before executing any destructive op (force-push, branch deletion, rebase, force-checkout), show what will happen and ask "Proceed?" If the user declines, cancel gracefully.
+1. **Parse intent** — extract the operation and, from the table above, the domain that owns it,
+   plus any options the user named.
+2. **Check the hard rules** — if the request creates, amends, or rewrites a commit, pushes, or
+   touches hooks, config, or credentials, read `references/hard-rules.md`. Raise the relevant rule
+   before acting, not after.
+3. **Read the repo** — current branch, working-tree state, and which branching model the repo
+   follows (the orchestrator reads `branching_pattern` from plugin config; infer from branch names
+   if absent); the last of those decides which tips are worth offering.
+4. **Gate destructive operations** — before force-push, branch deletion, rebase, or
+   force-checkout, show what will happen and ask "Proceed?". Cancel gracefully if the user
+   declines. Never supply the confirmation on the user's behalf. Some operations are refusals, not
+   confirmations: never offer "Proceed?" for a force-push of `main` or `master`.
+5. **Invoke the `git-orchestrate` agent** with `operation`, `parameters` (user-provided or
+   inferred), `context` (step 3 plus the session context), and `confirm: true` only for a
+   destructive op the user approved in step 4.
+6. **Clarify when the orchestrator asks for more** — put its question to the user in plain
+   language ("Which branch should this be based on?") and loop back to step 5 with the answer.
+7. **Report the outcome** — on success, the result and what changed, in plain language; on
+   failure, the error reason and a recovery action.
 
 ## Interaction style
 
-- **Conversational**: Use natural language, not technical jargon. "Let me rebase your changes onto main" not "Running git rebase --interactive main".
-- **Pedagogical**: Explain what each step does and why. "I'm squashing your last 3 commits into one clean commit" not just "Squashing commits".
-- **Guided**: Offer inline help. When users mention ambiguous steps, suggest best practices. Match the tip to the repo's branching model: for Gitflow-style repos, "Tip: Feature branches branch off `develop`, not `main` — `main` only tracks released code." For trunk-based/GitHub Flow repos, "Tip: Short-lived feature branches off `main` keep merges small and reviewable."
-- **Transparent**: Show progress. "Creating branch feature/user-auth..." then "✓ Branch created. Ready to commit." Humans benefit from seeing workflow state.
-- **Safe**: Always confirm before destructive ops. Never silently rewrite history or force-push without explicit user approval.
+The caller is a human, so the interaction is the point. Explain each step and why it happens ("I'm
+squashing your last 3 commits into one clean commit" beats "Squashing commits"), show progress as
+you go, and prefer natural language to raw command lines.
+
+Match tips to the repo's branching model rather than offering generic advice: on a Gitflow repo,
+feature branches come off `develop` and `main` tracks only released code; on a trunk-based or
+GitHub Flow repo, short-lived branches off `main` keep merges small and reviewable.