Borrowing it
Nothing to install: this file belongs to handarbeit/fabrik. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/handarbeit/fabrik/main/.claude/skills/audit-documentation/SKILL.mdgit clone --depth 1 https://github.com/handarbeit/fabrikWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/handarbeit/fabrik/audit-documentation)<a href="https://agentmods.dev/skills/handarbeit/fabrik/audit-documentation"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/audit-documentation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/handarbeit/fabrik/audit-documentation"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/audit-documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01919 |
| Opus 5.5 | $0.00011 | $0.00768 |
| Sonnet 5.5 | $0.00005 | $0.00384 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
audit-documentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Documentation
Compare recently shipped features against USER_GUIDE.md, README.md, and docs/index.md. File GitHub issues for documentation gaps and close existing documentation issues whose gaps are now covered.
Usage
/audit-documentation # Scan issues closed in the last 30 days
/audit-documentation --since v0.0.20 # Scan issues referenced in commits since a tag
Known limitation: Rate limits may apply for repos with hundreds of closed issues. The tag-based mode may miss issues if their PRs used Fixes or bare URLs instead of Closes #NNN.
Steps
Step 1 — Parse arguments and pre-flight
Detect whether --since <tag> was provided:
# Tag-based mode
TAG="v0.0.20" # extracted from --since argument
# Validate tag exists locally
git rev-parse --verify "refs/tags/$TAG" 2>/dev/null
if [ $? -ne 0 ]; then
# Try fetching tags and retry
git fetch --tags origin
git rev-parse --verify "refs/tags/$TAG" 2>/dev/null || {
echo "Error: tag '$TAG' not found locally or on origin. Aborting."
exit 1
}
fi
For the default 30-day mode, compute the cutoff date using Python (portable across macOS and Linux):
CUTOFF_DATE=$(python3 -c "from datetime import datetime,timedelta; print((datetime.now()-timedelta(days=30)).strftime('%Y-%m-%d'))")
echo "Scanning issues closed since: $CUTOFF_DATE"
Step 2 — Discover source issues
Tag-based mode (two-pass):
Pass 1 — extract issue numbers from commit messages since the tag:
git log "$TAG..HEAD" --format="%s%n%b" | grep -oE '#[0-9]+' | grep -oE '[0-9]+' | sort -u
Pass 2 — get the tag's commit date, then find merged PRs since that date and extract Closes #NNN references:
TAG_DATE=$(git log -1 --format="%ci" "refs/tags/$TAG" | cut -d' ' -f1)
gh pr list -R handarbeit/fabrik --state merged \
--search "merged:>=$TAG_DATE" \
--json number,body \
--limit 500 \
--jq '.[] | .body' \
| grep -oiE '(closes|fixes|resolves) #[0-9]+' \
| grep -oE '[0-9]+' \
| sort -u
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 234 lines · 27 tokens per session scan A 056ba7d2087e
audit-documentation is a skill published in the GitHub repository handarbeit/fabrik (25 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,919 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
coding-quality-loop
Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.
pr-comments
Triage unresolved review threads on an open PR: per thread either agree (fix, verify, push, reply, resolve) or disagree (justify with a version-matched citation). Use when asked about PR comments or told to reply and resolve.
orchestrate
Run the review lenses over a change: pick the ones the change touches, read or dispatch each, gate go/no-go on cited evidence. Use when asked for our lenses, or to plan or verify a non-trivial change.
pr
Write or draft a minimal GitHub PR title and body: a linked tracker close line plus 3 to 6 one-line bullets, nothing else. Use when running gh pr create / gh pr edit or when asked for a PR description.
forge-code-review
Forge code-review method — order, severity levels, Codex handoff. Use before any commit or when asked to review code — code review, check my code, PR review, before I commit.
gh-pr
Create, review, or manage GitHub pull requests. Use when asked to open, check, or merge a PR.