Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/commands/queelius/claude-anvil/repo-audit)<a href="https://agentmods.dev/commands/queelius/claude-anvil/repo-audit"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-audit/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/commands/queelius/claude-anvil/repo-audit"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.00708 |
| Opus 5.5 | $0.00010 | $0.00283 |
| Sonnet 5.5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
repo-audit 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-audit
Run repoindex ops audit with the given filters and summarize the results. Read-only: this command surfaces gaps, it does not fix them.
Arguments
Forward any arguments directly to the CLI. Common filters:
| Flag | Purpose |
|---|---|
--language python |
Only Python repos |
--tag work/active |
Only repos with a matching tag |
--recent 7d |
Only repos with commits in the last 7 days |
--dirty |
Only repos with uncommitted changes |
--category essentials |
Scope to essentials, development, discoverability, or documentation |
--severity critical |
Show only critical issues |
Workflow
Step 1: Run the audit
Always pass --json so the output is parseable.
repoindex ops audit --json <forwarded args>
Each JSON line represents one repo with its score per category and a list of failed checks.
Step 2: Aggregate
Walk the JSONL output and count:
- Total repos audited.
- Critical failures: sum of critical-severity failed checks, grouped by check name.
- Recommended failures: same, grouped by check name.
- Repos with zero issues (perfect score).
- Worst offenders: repos with the most critical failures.
Step 3: Summarize
Produce a compact report:
Audit summary (N repos, filters: ...)
Critical gaps
no_license 7 repos: foo, bar, baz, ...
no_readme 3 repos: ...
Recommended gaps
no_citation 12 repos: ...
no_ci 9 repos: ...
Perfect (no gaps): 4 repos
Worst offenders:
repo-a 4 critical, 6 recommended
repo-b 3 critical, 5 recommended
Cap each repo list to the first 5 names plus a count for the rest.
Step 4: Offer follow-ups
End with suggestions, do not execute them automatically:
- To fix deterministic gaps across a subset:
repoindex ops generate <kind>filtered with--language/--tag/--recent/--dirty(positional query strings were removed and now error). - To drill into one repo: use the
repo-polishagent. - To re-run with tighter scope:
/repo-audit --severity critical --category essentials.
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.
- yesterday First seen · 84 lines · 25 tokens per session scan A 822e0367ccc9
repo-audit is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 708 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 2026-10-19.
Other commands, from other repositories
ia-review
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees.
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
prune-sync-log
Prune stale entries from the whetstone sync decision log.
ia-changelog
Create engaging changelogs for recent merges to main branch.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
open-pr
Create a pull request for the current branch following the the team's standard PR template.