Defame1297/holocron
0
0
Fork 0
Code Issues 14 Pull Requests Actions Packages Projects Releases 3 Wiki Activity

refactor(skills): retrofit the corpus to the ADR-0020 context contract (#129)

Browse Source 
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>
This commit was merged in pull request #129.
This commit is contained in:
Claude Code AI - Gitea MCP
2026-09-01 13:47:46 +00:00
committed by Defame1297
parent 0e91a3ae66
commit 598a7c326a
420 changed files with 15303 additions and 4740 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
plugins/git/.apm/skills/git-worktrees/references/worktrees.md
View File

@@ -4,6 +4,48 @@ source_keys:
- git-scm-worktree-docs
---
# Git worktrees
## Shared vs. per-worktree state
All worktrees share one object store, one config, and most refs under `refs/`. Each worktree keeps
its own `HEAD`, index, and per-worktree metadata (`ORIG_HEAD`, `MERGE_HEAD`, `refs/bisect/`,
`refs/worktree/`, `refs/rewritten/`) under `$GIT_DIR/worktrees/<name>/`. Exactly one **main
worktree** exists per repo — the one `git init` or `git clone` produced — and it cannot be removed
or moved. Every other worktree is a **linked worktree** created by `git worktree add`.
## Identifying a worktree
`lock`, `move`, `remove` and `repair` accept a full path, a unique basename, or a unique partial
path. An ambiguous name errors rather than picking one; `git worktree list` shows the identifiers
that are usable.
## `add` forms
```bash
git worktree add <path> <branch> # <branch> exists locally: check it out — non-destructive
git worktree add -b <branch> <path> # create a new branch; fails if it exists
git worktree add <path> # branch named after $(basename <path>): checked out
# if it exists, else created from HEAD
git worktree add -B <branch> <path> # create the branch, or reset an existing one to HEAD,
# discarding the commits it carried
git worktree add --track -b <branch> <path> <remote>/<branch>
# new local branch tracking the remote — always works
git worktree add <path> <branch> # <branch> absent locally and in exactly one remote:
# Git expands this to the --track -b form above
git worktree add -d <path> # detached HEAD, no branch
```
The same `git worktree add <path> <branch>` spelling appears twice above and does two
different things: it checks out a local branch when one exists, and only otherwise falls
through to the remote-tracking shortcut. Read the local branch list before relying on either.
**Do not write `git worktree add <path> <remote>/<branch>`.** A remote-tracking ref resolves as a
commit-ish, so the tracking shortcut never fires and the worktree lands on a **detached HEAD with
no local branch and no upstream** — commits there go unreachable once HEAD moves or the worktree is
removed, and `git push` fails without an explicit refspec. That spelling is correct only as the
final argument of the `--track -b` form.
## Full `add` flag table
| Flag | Meaning |
@@ -11,7 +53,7 @@ source_keys:
| `-b <branch>` | Create and check out a new branch; fails if it exists |
| `-B <branch>` | Like `-b` but resets the branch if it already exists |
| `-d` / `--detach` | Detach HEAD; useful for throwaway experiments |
| `--orphan` | Create empty unborn branch |
| `--orphan` | Create empty unborn branch — **Git 2.42+**; earlier versions exit 129 with `error: unknown option 'orphan'`. Fallback below |
| `--no-checkout` | Suppress initial checkout (for sparse-checkout setup) |
| `--guess-remote` | Look for a matching remote-tracking branch by path basename |
| `--lock [--reason <str>]` | Lock immediately on creation (atomic; avoids race vs. add-then-lock) |
@@ -25,7 +67,22 @@ Using `-` as `<commit-ish>` is shorthand for `@{-1}` (the branch checked out bef
```bash
git worktree add --orphan -b <branch> <path>
```
Creates an empty branch with no commits.
Creates an empty branch with no commits. **`--orphan` needs Git 2.42 or later** — it was added
upstream in 2.42, and on 2.39.5 this fails with `error: unknown option 'orphan'` and exit 129.
Check `git --version` before reaching for it.
Fallback on older Git, verified on 2.39.5 — detach first, then orphan the linked worktree in place,
which leaves the main worktree on its own branch throughout:
```bash
git worktree add -d <path> # linked worktree, detached HEAD
cd <path>
git switch --orphan <branch> # unborn branch: empty index, empty working tree
```
`git worktree list` then shows the new worktree at `0000000 [<branch>]` until its first commit.
Do not substitute `git switch --orphan` in the *main* worktree: it clears that checkout, which is
the disruption worktrees exist to avoid.
## Sparse-checkout worktree
@@ -48,9 +105,41 @@ git worktree unlock <path> # when reconnected
## Remote-branch disambiguation
```bash
git worktree add <path> <remote>/<branch>
git worktree add --track -b <branch> <path> <remote>/<branch> # explicit: no guessing at all
git worktree add <path> <branch> # shortcut: needs one clear remote
```
For ambiguous names across remotes, `checkout.defaultRemote` config disambiguates explicitly, or `--guess-remote` auto-matches by path basename (default controlled by `worktree.guessRemote` config). If a branch name matches multiple remotes during `worktree add` and neither is set, Git refuses rather than guessing.
**The bare-name shortcut needs exactly one remote.** It fires only when `<branch>` is not found
locally, none of `-b`/`-B`/`--detach` were given, and a tracking branch of that name exists in
exactly one remote. When several remotes carry the name, `checkout.defaultRemote` picks one for
disambiguation purposes; with no such setting the shortcut has no single remote to resolve against
and does not apply. When the remote is ambiguous or unknown, use the explicit `--track -b` form.
`--guess-remote` covers the *other* spelling — `git worktree add <path>` with no `<commit-ish>` at
all. It bases the new branch on the remote-tracking branch matching `$(basename <path>)` when
exactly one remote has it, and marks that branch as upstream. Its default comes from the
`worktree.guessRemote` config.
## Repair after a manual move
```bash
git worktree repair # the MAIN worktree moved: run it there to reconnect every linked
# worktree back to the main worktree
git worktree repair # a LINKED worktree moved: run it inside that recently-moved worktree
git worktree repair <path>... # reconnect a specific linked worktree — runnable from any worktree,
# naming each moved tree's new path
```
Which form applies depends on what moved:
| What moved | Remedy |
|---|---|
| The main worktree (or bare repo) | `git worktree repair` in the main worktree |
| One linked worktree | `git worktree repair` inside that worktree |
| Several linked worktrees | `git worktree repair <path>...` from any worktree, listing each new path |
| Both main and linked worktrees | `git worktree repair <path>...` in the main worktree, naming each linked worktree's new path — this restores the connections in both directions |
Only the no-argument form is tied to the current directory. The `<path>...` form is not — it
reestablishes the connection to every path you name, run from any worktree.
## Configuration
@@ -61,3 +150,29 @@ For ambiguous names across remotes, `checkout.defaultRemote` config disambiguate
| `gc.worktreePruneExpire` | How long before stale worktree metadata is pruned by `git gc` |
| `extensions.worktreeConfig` | Enable per-worktree config scope (`config.worktree` file) — see Gotchas in SKILL.md |
| `checkout.defaultRemote` | Disambiguates which remote to use when a branch name matches multiple remotes during `worktree add` |
## Workflow patterns
**Emergency fix without disrupting current work** — nothing is stashed, and the main worktree is
untouched throughout:
```bash
git worktree add -b emergency-fix ../temp main
cd ../temp
# fix, then commit
git commit -a -m "fix: critical production bug"
cd -
git worktree remove ../temp
```
**Review a PR branch alongside your own work** — both branches stay checked out, so there is no
context switch:
```bash
git worktree add ../review-pr-123 origin/feature-xyz # detached HEAD — read-only review
git worktree add --track -b feature-xyz ../review-pr-123 origin/feature-xyz # if you will commit
# open ../review-pr-123 in a second editor window or terminal
```
Pick the second form the moment you intend to push anything back: the first leaves no branch to
push and no upstream to push to.