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>
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

View File

@@ -2,7 +2,10 @@
name: git-history
description: >
Inspect git history: query logs with pickaxe, line-range, or custom formats; find bug origins via bisect; locate problematic commits for cherry-picking or reverting. Use when investigating history, tracing when a change happened, or finding the commit that broke something. Return structured results for downstream agents. Do not use for authoring or formatting commit messages, or executing rebase/squash/fixup operations — use git-commits for that.
Use when investigating git history — pickaxe (`-S`/`-G`) or `-L` line-range log
queries, tracing when a change landed, bisecting what broke something, or
locating a commit to revert or backport. Not authoring or rebasing commits ->
`git-commits`. Not a Gitea server's history -> `gitea-branches`.
metadata:
category: git
@@ -16,81 +19,47 @@ allowed-tools: Bash
## Gotchas
- **Pickaxe searches (`-S` vs `-G`)**: `-S"string"` finds commits where string count changed; `-G"regex"` finds any line matching regex in diffs. They're not equivalent: a line replaced (one removal + one addition) matches `-G` but not `-S` if count is unchanged.
- **`--follow` only works for single files**: it traces renames but fails with multiple paths or directory globs. Use `git log -- <single-file>` or query without `--follow`.
- **Bisect with skips**: if bisect cannot pinpoint a commit because the culprit is adjacent to skipped commits, it reports "cannot find exact culprit" and lists candidates. This is not a failure — it's as precise as the skip range allows.
- **Interactive rebase is non-recoverable on mistake**: there's no undo once `rebase -i` starts. Suggest `git reflog` to recover if the user realizes mid-way they selected the wrong commits.
- **`-L` (line-range history) requires exact line numbers or regex patterns**: off-by-one errors omit the target range. Test the range with `git log -L` before offering it to users.
- `-S"string"` matches only where the string's *count* changed, so a line edited in place matches `-G"regex"` and not `-S`. Reach for `-G` whenever the string may have moved rather than appeared.
- `--follow` traces renames for exactly one path. Given several paths or a glob it fails instead of degrading, so run it once per file.
- Under `git bisect run`, exit `128` or above **aborts the session** rather than marking the commit bad, so a crashing test script ends the search silently.
- Bisect answering "cannot find exact culprit" beside skipped commits is a complete result: it is as precise as the skip range allows.
## Query Logs and Locate Commits
## Step 1 — Pick the entry procedure
Default to `git log --oneline` for quick inspection. For deeper queries:
| What is known | Procedure |
|---|---|
| Content, a file, or a line range to search for | Query the log — Step 2 |
| Nothing to search for — only that the behaviour changed between two points | Bisect — read `references/bisect.md` |
| The commit itself, already identified | Step 3 |
- **Find when a string appeared or disappeared**: Use `git log -S"string"` (count-sensitive, finds adds/removes). If you need any mention of the string in diffs, use `git log -G"regex"` instead. Add `--pickaxe-regex` to treat the `-S` string as a POSIX ERE, and `--pickaxe-all` to show every changed file in a matching changeset, not just the matching ones. Binary files are searched by `-S`; `-G` ignores them unless `--text` is also supplied.
- **Trace changes to a specific line or function**: Use `git log -L <start>,<end>:<file>` or `git log -L :<function>:<file>` (requires function name heuristic). This shows the evolution of that range across all commits.
- **Filter by change type**: Use `git log --diff-filter=<type>` (A=added, M=modified, D=deleted, R=renamed) to narrow to specific file operations.
- **Mainline-only history through merges**: Use `--first-parent` to follow only the integration branch and skip merged-in side-branch commits; combine with `--merges`/`--no-merges` or `--ancestry-path`/`--min-parents`/`--max-parents` for other ancestry-graph filtering — see `references/git-log-format.md` for the full set.
- **Custom format for structured output**: Construct format string with `%h` (hash), `%s` (subject), `%an` (author), `%ar` (relative date), `%b` (body). Example: `git log --format="%h | %s | %an (%ar)"`.
- **File-specific history with renames**: Use `git log --follow -- <file>` (single file only). Without `--follow`, log stops at the rename boundary.
## Step 2 — Query the log
## Bisect to Find Blame Commit
Default to `git log --oneline`, then narrow by whatever is known:
Use bisect when hunting for the commit that introduced a bug or behaviour change. Binary search reduces iterations from O(N) to O(log N).
- **Content**: `git log -S"string"`, or `-G"regex"` to match any diff line. `--pickaxe-regex` makes the `-S` argument a POSIX ERE; `--pickaxe-all` shows every file in a matching changeset.
- **A line or function**: `git log -L <start>,<end>:<file>` or `git log -L :<function>:<file>`. Confirm the range resolves before reporting on it — an off-by-one silently omits the target.
- **A file across renames**: `git log --follow -- <file>`. Without `--follow` the history stops at the rename boundary.
- **Mainline only**: `--first-parent` follows the integration branch and skips commits merged in from side branches.
- **Structured output**: `git log --format="%h | %s | %an (%ar)"`.
**Basic manual flow:**
```bash
git bisect start
git bisect bad [HEAD] # mark current (or specified) as broken
git bisect good <commit> # mark known-good baseline
# Git checks out midpoint; test it manually
git bisect good # if test passes
git bisect bad # if test fails
# Repeat until git reports "X is the first bad commit"
git bisect reset # return to original HEAD
If you need the placeholder catalogue, format presets, `--diff-filter` letters, full `-L` syntax, ancestry filters, pickaxe binary-file behaviour, or `git diff` output-control flags such as `--stat`, `--word-diff` and the whitespace options, read `references/git-log-format.md`.
## Step 3 — Act on a located commit
Offer the operation and its consequence; run it only once the user has chosen.
- Backporting the commit to another branch is a cherry-pick, and cherry-pick is `git-commits`' — it owns the destination-branch check, the `rtk git` wrapper and the `--abort` path. Hand it the SHA; do not run `git cherry-pick` from here.
- `git revert <commit>` adds a new commit undoing it — for un-applying merged work without rewriting history.
- `git blame <file>` attributes each line to the commit that last touched it, when the question is which commit introduced one specific line.
For diff output control on the located commit, read `references/git-log-format.md`.
## Step 4 — Return the result
Report each located commit in this shape, so a calling agent can act on it without reparsing raw log output:
```text
<sha> — <subject>
<author> (<relative date>)
Recommendation: <action or "none">
```
**Automated with `git bisect run`:** if a test command exists, use `git bisect run <cmd>`. Git interprets the exit code: `0`=good, `1-124`=bad, `125`=skip (build broken), `126-127`=POSIX shell errors treated as bad, `128+`=**aborts the bisect session entirely** (not treated as bad — a crashed test script can silently end the search).
**With skip:** if a commit is untestable (broken build), use `git bisect skip` to exclude it without manually deciding good/bad. If the first-bad is adjacent to skips, bisect reports it cannot pinpoint but lists candidates.
**Undoing a wrong good/bad call:** `git bisect log` prints the session's decision history; save it (`git bisect log > bisect.log`), edit out the mistaken entry, then `git bisect reset && git bisect replay bisect.log` to resume from the corrected log instead of restarting the whole search.
**Narrowing and speeding up the search:** `git bisect start HEAD v1.2 -- src/` limits bisection to a path, cutting the number of trials. `--no-checkout` updates the `BISECT_HEAD` ref instead of checking out a working tree (useful for tests that don't need one; automatic in bare repos). `--first-parent` follows only first parents at merges, finding the integration commit that introduced a regression while ignoring broken side branches.
**Inspecting remaining candidates visually:** `git bisect visualize` (alias `view`) opens the suspects in gitk; add `--stat` or `-p` to show diffstat or full patches instead. Falls back to `git log` when no graphical display is detected.
**For non-regression hunts:** use `git bisect start --term-new <new> --term-old <old>` to search for a property change instead of a bug (e.g., performance regression). Then use the custom terms instead of `good`/`bad`.
For rebase execution (interactive rebase, squash/fixup/reword, conflict handling) see git-commits — it owns history-rewriting operations. This skill only locates commits and reports on history; it does not execute rebases.
## Find and Manipulate Problematic Commits
Once a commit is identified (via log query or bisect), offer cherry-pick or revert. This section is general git knowledge, not sourced from `history-inspection.md` — `git-branches`'s SKILL.md explicitly delegates cherry-pick/revert here (see its Merging section), which is why this skill carries them rather than treating them as out of scope:
- **Cherry-pick**: `git cherry-pick <commit>` copies a commit's changes onto current HEAD. Use when backporting fixes to other branches.
- **Revert**: `git revert <commit>` creates a new commit that undoes the changes. Use when un-applying a merged commit without rewriting history.
- **Blame for context**: `git blame <file>` shows which commit last changed each line. Use to trace a specific line back to its introducing commit.
## Inspect Diffs
Diff-output tuning is in scope too: `--stat` for a diffstat summary, `--word-diff` for word-level (not line-level) changes, and whitespace flags (`-w`, `--ignore-blank-lines`) to suppress noise from reformatting. See `references/git-log-format.md` for the full flag set.
## Return Results Structured
For agent consumption, return:
- **Commit SHA** (full or abbreviated as appropriate)
- **Subject line** (from `%s`)
- **Author and date** (from `%an` and `%ar`)
- **Action taken or recommended** (e.g., "Found via bisect", "Offer cherry-pick to main", "Rebase conflicts detected")
Example for agent:
```
Found first bad commit: abc1234
Subject: fix null pointer in parser
Author: Alice (2 weeks ago)
Recommendation: Backport to release branch via cherry-pick
```
## Reference
For the full log format placeholder catalogue, named format presets, `--diff-filter` letters, `-L` range syntax, ancestry filters, and `git diff` output-control flags, read `references/git-log-format.md`.