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

65
plugins/gitea/skills/gitea-files/references/examples.md
View File

@@ -1,65 +0,0 @@
---
source_keys:
- gitea-mcp-repo
- gitea-mcp-slim-go
---
# Canonical call sequences
## Push a file to a new branch, then open a PR
```
1. get_repository_tree or get_file_contents on the base branch — only needed if the
new file is actually replacing an existing one; skip for a brand-new path.
2. create_or_update_file
owner, repo
path: "docs/example.md"
content: "<base64-encoded content>"
message: "docs: add example"
branch_name: "main"
new_branch_name: "feat/add-example" ← branches off before the commit lands
(sha omitted — this is a new file)
3. Hand off to gitea-prs to open a PR from "feat/add-example" into "main".
```
`new_branch_name` on `create_or_update_file` replaces a separate branch-creation call — the branch is created and the commit lands on it in one step.
## Update a file when you don't already have its SHA
SHA is mandatory for updates. If it wasn't captured earlier in the conversation:
```
1. get_file_contents
owner, repo
ref: "main"
path: "docs/example.md"
→ read the top-level `sha` field (not content.sha)
2. create_or_update_file
owner, repo
path: "docs/example.md"
content: "<new base64-encoded content>"
message: "docs: update example"
branch_name: "main"
sha: "<sha from step 1>"
```
Do not guess or omit the SHA — the write either fails (409 on create-path fallback) or is rejected outright.
## Delete a file
Same SHA-first pattern, no fallback path:
```
1. get_file_contents owner, repo, ref: "main", path: "docs/old-example.md"
→ read the top-level `sha` field
2. delete_file
owner, repo
path: "docs/old-example.md"
message: "docs: remove old example"
branch_name: "main"
sha: "<sha from step 1>"
```

50
plugins/gitea/skills/gitea-files/references/reading.md Normal file
View File

@@ -0,0 +1,50 @@
---
source_keys:
- gitea-mcp-repo
- gitea-mcp-slim-go
---
# Reading files, directories and trees
All three read calls select what to read with `ref` — a branch name, tag, or commit SHA. On
`get_repository_tree` the same value goes in `tree_sha` despite the name.
## Single file
`get_file_contents(owner, repo, ref, path)`.
The response carries the file's `sha` at the **top level**, not nested under `content`. That field
is the write-ready SHA, so capture it whenever a write may follow.
Content comes back base64-encoded — decode it — **unless `withLines: true` was passed**, in which
case `content` is already plain text: a JSON array of `{"line": N, "content": "..."}` objects.
The response reports `"encoding": "base64"` either way, so that field is wrong under `withLines`
and decoding on its word yields garbage. Pass `withLines: true` only when you need numbered lines
to quote specific lines back to the user; omit it for a normal content fetch.
## One directory level
`get_dir_contents(owner, repo, ref, path)` returns the immediate entries only — name, path, type,
size. No recursion, no content, no `sha`.
## Whole repository tree
`get_repository_tree(owner, repo, tree_sha, recursive)`. Set `recursive: true` to walk
subdirectories in one call.
The response sets `truncated: true` when one page does not hold every entry. Page through with
`page`/`per_page` (defaults `1` and `30`) until a page returns fewer entries than `per_page`.
## Neither listing is a SHA source for a write
`get_dir_contents` entries carry no `sha` at all. `get_repository_tree` entries do carry a blob or
tree hash, but reaching it costs an extra round trip and returns no content. `get_file_contents` is
the canonical path for a write's SHA: one call returns the decoded content and the write-ready
`sha` together.
## A 404 that is really a 403
These reads gate on `write:repository`, not on read access alone, and some Gitea endpoints answer
an under-scoped token with 404 instead of 403 so they do not leak whether the resource exists. A
404 on a path you are confident about is a scope problem until proven otherwise — check the token's
configured scopes before concluding the file or directory does not exist.

16
plugins/gitea/skills/gitea-files/references/sources.md
View File

@@ -2,15 +2,16 @@
## gitea-mcp-repo
**Description:** Official gitea-mcp repository (v1.3.0); operation/*.go source files documenting all 55 MCP tools, their parameters, and CLI flags.
**Description:** Official gitea-mcp repository (v1.3.0); operation/*.go source files documenting all 55 MCP tools, their parameters, and CLI flags. Tool parameters and SHA/concurrency behavior were cross-checked live against the deployed MCP tool schemas via `ToolSearch`, per this repo's process for resolving schema-vs-docs drift, rather than copied from the derived research doc.
**Source:** https://gitea.com/gitea/gitea-mcp
- **Research doc:** plugins/gitea/docs/research/docs/gitea/sources.md
**Contributing files:**
- SKILL.md (Gotchas, Reading, Writing — tool parameters and SHA/concurrency behavior, cross-checked live against the deployed MCP tool schemas via ToolSearch)
- references/examples.md (canonical call sequences)
- SKILL.md (Gotchas — cross-flow parameter and encoding traps; Dispatch)
- references/reading.md (read-tool parameters, `ref`/`tree_sha` selection, tree pagination)
- references/writing.md (write-tool parameters, SHA/concurrency behavior, canonical call sequences, failed-write triage)
## gitea-mcp-slim-go
@@ -21,8 +22,9 @@
- **Research doc:** plugins/gitea/docs/research/docs/gitea/sources.md
**Contributing files:**
- SKILL.md (Gotchas — top-level `sha` field location, `get_dir_contents`/`get_repository_tree` not being usable SHA sources for a file write)
- references/examples.md (SHA-first update/delete sequences)
- SKILL.md (Gotchas — base64 response encoding)
- references/reading.md (top-level `sha` field location, `get_dir_contents`/`get_repository_tree` not being usable SHA sources for a file write)
- references/writing.md (SHA-first update/delete sequences)
## context7-websites-gitea
@@ -33,7 +35,7 @@
- **Research doc:** plugins/gitea/docs/research/docs/gitea/sources.md
**Contributing files:**
- SKILL.md (Gotchas — "Direct commits to a branch are a first-class action, not a workaround")
- SKILL.md (Handoff — committing straight to a branch is the normal path, not an escape hatch)
## context7-gitea-tea-cli
@@ -43,4 +45,4 @@
- **Research doc:** plugins/gitea/docs/research/docs/gitea/sources.md
**Contributing files:** (none)
- **Contributing files:** (none)

79
plugins/gitea/skills/gitea-files/references/writing.md Normal file
View File

@@ -0,0 +1,79 @@
---
source_keys:
- gitea-mcp-repo
- gitea-mcp-slim-go
---
# Creating, updating and deleting files
`sha` is the optimistic-concurrency token for every write, and it comes from
`get_file_contents`'s **top-level** `sha` field — never from `content.sha`, a directory listing, or
a tree entry. Do not guess or reuse a stale value: a mismatched SHA is rejected exactly like a
missing one.
`content` is base64-encoded, and the branch the commit lands on is `branch_name`, not `ref`.
## Create a new file
Call `create_or_update_file(owner, repo, path, content, message, branch_name)` with `sha` omitted
entirely. An omitted `sha` always means *create*, so the call returns HTTP 409 if the path already
exists.
To branch off as part of the same write, pass `new_branch_name`: the branch is created and the
commit lands on it in one call, replacing a separate branch-creation step.
## Update an existing file
1. `get_file_contents(owner, repo, ref: <branch>, path)` → read the top-level `sha`.
2. `create_or_update_file(owner, repo, path, content, message, branch_name, sha: <that value>)`.
## Delete a file
Same SHA-first pattern, with no create-style fallback. `sha` is schema-**required** on
`delete_file`, unlike `create_or_update_file` where omitting it means *create* — so an omitted `sha`
is rejected client-side by input validation and the call never reaches Gitea. The HTTP 422 that is
actually reachable here is the stale-`sha` case.
1. `get_file_contents(owner, repo, ref: <branch>, path)` → read the top-level `sha`.
2. `delete_file(owner, repo, path, message, branch_name, sha: <that value>)`.
## Worked sequence — new file on a new branch, then a PR
```text
1. create_or_update_file
owner, repo
path: "docs/example.md"
content: "<base64-encoded content>"
message: "docs: add example"
branch_name: "main"
new_branch_name: "feat/add-example" ← branches off before the commit lands
(sha omitted — this is a new file)
2. Hand off to gitea-prs to open a PR from "feat/add-example" into "main".
```
Step 1 needs no preceding read: a brand-new path has no SHA. Fetch the current file first only
when the write replaces an existing one.
## Triaging a failed write
| Symptom | Cause | Action |
|---|---|---|
| HTTP 409 | `sha` omitted on a path that already exists | Fetch the current SHA, retry as an update |
| HTTP 422 | Stale `sha` — the file changed between the read and the write | Re-fetch the SHA immediately before the write |
| 403 or 422 with no SHA explanation | Branch protection requires signed commits | Stop and report |
| HTTP 413 | Reverse-proxy body limit in front of Gitea | Report; retrying cannot fix it |
| Client-side input-validation error naming `sha` | `sha` omitted on `delete_file`, where it is schema-required | Fetch the current SHA and retry — nothing was sent to Gitea |
| HTTP 404 | Wrong path, or a token without `write:repository` | Verify the path, then the token's scopes |
**Signed commits.** These writes create commits server-side from a bare API token with no 2FA or
PGP context. If the target branch's protection rule requires signed commits, Gitea rejects the
write as a generic 403 or 422 that never names signing, and reads against that same branch keep
succeeding right up until the write. When a write fails without a clean 409 or 404 explanation,
check the branch's protection rule before assuming the SHA is wrong and retrying.
**Payload size.** base64 inflates `content` roughly 33% over the raw file size, and a 413 is
usually a reverse-proxy body-size limit in front of the Gitea instance rather than a Gitea-side
rejection. No amount of retrying, or changing the SHA, path, or branch, will fix it — the proxy's
config has to be raised, which is outside this skill's control. Surface that distinction instead
of retrying the same call.