Defame1297
fc305ba7d9
Five documents told authors that a prose-form dangling routing target blocks. The
gate reports it as a SUGGESTION and exits 0. Verified on fixtures: `-> name` and
`/name` are blocking ERRORs, the prose form is SUGGESTION-tier unless a second
resolving target in the same sentence corroborates it. ADR-0020 and gates.md were
right; contract.md, retrofit.md, description-quality.md, finding-criteria.md and
agent-author's contract.md were wrong — and they are what an author and an auditor
actually read. The whole 39-skill corpus was retrofitted against them.
skill-audit was also self-contradictory: it imports validate.sh's SUGGESTIONs into
the Structure dimension verbatim while its own rubric grades the same target a FAIL,
so one target got reported twice at two tiers. The script owns the grade; the rubric
now says so.
The YAML-fold trap that broke gitea-labels-milestones (#100) was warned about only
in retrofit.md, reachable only from the improve flow when a budget is exceeded. It
is now in both contract.md files, which SKILL.md mandates on the create flow too.
agent-audit loaded both rubrics unconditionally on every run — 3,323 words for a
clean audit against skill-audit's 1,636. dac9cad fixed exactly this in skill-audit
and edited agent-audit in the same commit without applying it. Same treatment: the
criteria move to a new finding-criteria.md and load per dimension. Clean run now
2,083 words, a 37% cut.
Routing: apm-workflow's description shed dependency installation while still owning
the flow, and apm-install's boundary did not exclude it, so "install my apm
dependencies" matched the CLI-binary skill with no route back. Fixed on both sides.
forge regains two of the three phrasings the retrofit deleted.
forge Step 1 called grill-with-docs unconditionally — a skill in plugins/bin, which
kyberforge does not declare as a dependency. It resolves here only because the
walk-up sweeps sibling plugins; a standalone install dead-ends. Step 1 now names
the cross-plugin dependency and gives an inline fallback. Declaring it properly in
apm.yml remains the better fix.
Also: both audit SKILL.md files now grade exit 2 as "did not run, dimension
unverified" rather than as findings; skill-audit's README row described content that
moved, which its own finding-criteria.md grades a FAIL; and body-discipline.md's
`git show <sha>:plugins/...` command is fenced, since an installed plugin cache has
no repo and file-structure.md makes a bare repo path a FAIL.
Refs: #100, #101, #125
ADR: 0020
90 lines
5.8 KiB
Markdown
90 lines
5.8 KiB
Markdown
---
|
|
name: agent-audit
|
|
description: >
|
|
Use when the user wants an agent definition audited — "audit this agent",
|
|
"review my agent file", "is this ready to ship" — or after hand-editing an
|
|
agent outside agent-author. Not applying fixes -> agent-author. Not a skill
|
|
directory -> skill-audit.
|
|
allowed-tools: Bash Read
|
|
metadata:
|
|
category: factory
|
|
source_keys:
|
|
- context7-websites-code-claude
|
|
- claude-code-plugins-docs
|
|
- claude-code-subagents-docs
|
|
- context7-github-en-copilot
|
|
- github-custom-agents-configuration
|
|
---
|
|
|
|
## Gotchas
|
|
|
|
- Do not narrate PASS/FAIL per check while auditing. Gather findings internally and surface them only in the Step 4 report. Narrating each check as you go is the default failure mode here.
|
|
- Agents take the same 250/400-character description gates as skills and **no body word gate at all** — an agent body becomes the system prompt of a fresh context, so the 900-word skill ceiling does not transfer. Judge an over-long agent body through the delegation check, never by word count.
|
|
- At plugin/APM scope the agent is a single vendor-neutral file by design, so provider safety stops meaning Claude-Code-versus-Copilot field leakage there.
|
|
- Vale reporting `0 files` scanned means NOT RUN, not clean. Fall back to full Step 3 judgment for every dimension it would have covered.
|
|
|
|
## Step 1 — Deterministic checks
|
|
|
|
Resolve all three paths against this skill's own directory so they work from a repo checkout and an installed plugin cache alike. Run exactly:
|
|
|
|
```bash
|
|
bash scripts/validate.sh <agent-file>
|
|
bash scripts/validate-provenance.sh <agent-file>
|
|
bash scripts/vale-wrap.sh <agent-file> [<counterpart-file>]
|
|
```
|
|
|
|
`validate.sh` takes either half of a project/user-scope pair or the single plugin/APM-scope file, detects the provider from the extension and the scope by walking up, then checks required fields, kebab-case `name`, `FILL IN:` placeholders, template HTML comments left in frontmatter, the ADR-0020 description budget (250 chars SUGGESTION, 400 FAIL, measured on the folded YAML value) and the fields that scope permits. Its findings become the `### Structure` dimension — its FAILs and its SUGGESTIONs both — except the ones the Step 2 scope contract re-routes.
|
|
|
|
If a validation script fails or cannot run — Bash denied, `python3` or `vale` absent, `references/field-inventory.md` missing — read `references/validation-scripts.md`; what these scripts measure is not reproducible by reading.
|
|
|
|
`validate-provenance.sh` prints nothing on success, so read its exit code before you read its silence. **0** is a genuine pass, including the silent exit 0 at project or user scope, where plugin-scope provenance does not apply. **1** means real findings: its FAILs and INFOs become a separate `### Provenance` dimension, and it emits Why and Fix itself — surface those verbatim. **2** means the check never ran — a bad argument or a missing dependency, reason on stderr, no findings and often no stdout at all. On a 2, report `### Provenance` as unverified and quote the stderr reason; never grade it as a clean pass. `validate.sh` uses the same 2 tier.
|
|
|
|
`vale-wrap.sh` applies the bundled `Kyberforge` style as a prefilter. Pass no `--config`; the wrapper locates its own. At project/user scope pass both files of the pair, not only the one you were handed. Every rule is graded `error`, so every alert is a FAIL. Report each one citing its rule ID, filed under the dimension it belongs to, and do not re-derive it by judgment:
|
|
|
|
| Rule | Dimension |
|
|
|---|---|
|
|
| `Kyberforge.DescriptionOpener`, `Kyberforge.CompositionNote`, `Kyberforge.VagueWording`, `KyberforgeCopilot.ProactivePhrase` | description |
|
|
| `Kyberforge.SentenceOpenerThereIs`, `Kyberforge.PaddingPhrase` | body |
|
|
|
|
## Step 2 — Read the agent and load its scope contract
|
|
|
|
Read the agent file end to end, and at project/user scope its counterpart too. A path containing `.apm/agents/` is plugin/APM scope; anything else is project or user scope. Each contract names the dimensions that apply there and where `validate.sh` findings other than Structure belong:
|
|
|
|
| Scope | Read |
|
|
|---|---|
|
|
| plugin/APM | `references/scope-plugin-apm.md` |
|
|
| project, user | `references/scope-project-user.md` |
|
|
|
|
## Step 3 — Qualitative audit
|
|
|
|
Read `references/finding-criteria.md` first — every dimension's FAIL and SUGGESTION criteria. Load the rubric below only for a dimension the criteria put in play: one carrying a candidate finding, or one where the criterion alone does not settle the call.
|
|
|
|
| Dimension | Rubric |
|
|
|---|---|
|
|
| description | `references/description-quality.md` |
|
|
| body, delegation, comment-discipline | `references/body-and-delegation.md` |
|
|
|
|
Each rubric is the reasoning behind its criteria, not a second copy of them. Cite file and line number for every finding.
|
|
|
|
## Step 4 — Report
|
|
|
|
Open with a coverage line naming every dimension checked. At project/user scope:
|
|
|
|
```text
|
|
Checked: structure · provider-safety · description · body · delegation · comment-discipline · pair-consistency · provenance
|
|
```
|
|
|
|
At plugin/APM scope, drop `pair-consistency` — there is no pair to check.
|
|
|
|
Then output only the dimensions that have findings, grouped under H3 headings, FAILs before SUGGESTIONs within each. Omit clean dimensions — their absence is what confirms they passed.
|
|
|
|
Each finding:
|
|
|
|
```text
|
|
FAIL/SUGGESTION <finding> — file:line
|
|
Why: <why this is a problem>
|
|
Fix: <exact change — quote before/after where applicable>
|
|
```
|
|
|
|
Close with a `## Result` block holding one line: `PASS`, `PASS (N suggestions)`, or `FAIL (N fails · M suggestions)`, each optionally followed by ` · P info`. INFO findings are observational and never change PASS/FAIL; omit `· P info` when there are none. Add a second line, `Run agent-author to address findings.`, whenever there is at least one finding. Do not apply fixes — report and propose only.
|