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/agents/queelius/claude-anvil/community-auditor)<a href="https://agentmods.dev/agents/queelius/claude-anvil/community-auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/community-auditor/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/agents/queelius/claude-anvil/community-auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/community-auditor.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 | $0.00046 | $0.00852 |
| Opus 5.5 | $0.00018 | $0.00341 |
| Sonnet 5.5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
community-auditor 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 today.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit repository hygiene and community practice for JOSS submission. This is a quick, focused check of files and metadata that JOSS reviewers explicitly look for.
Checks
1. License
-
LICENSEorLICENSE.mdexists in repo root - License is OSI-approved (MIT, GPL-2, GPL-3, Apache-2.0, BSD-2-Clause, BSD-3-Clause, etc.)
- License text is complete (not a stub)
- DESCRIPTION/pyproject.toml license field matches the file
2. Contributing Guidelines
-
CONTRIBUTING.mdexists (or contributing section in README) - Explains how to report bugs
- Explains how to submit patches/PRs
- Mentions coding standards or style guide (optional but good)
3. Code of Conduct
-
CODE_OF_CONDUCT.mdexists - Uses a recognized standard (Contributor Covenant recommended)
4. Issue Tracker
Check GitHub repo settings:
gh repo view --json hasIssuesEnabled
- Issue tracker is enabled
- Issue tracker is public (no login required to browse)
5. Development History
# First commit date
git log --reverse --format="%ai" | head -1
# Latest commit date (compute months elapsed between this and the first commit)
git log -1 --format="%ai"
# Commit count
git rev-list --count HEAD
# Contributors
git shortlog -sn --all | head -10
# Tags/releases
git tag -l | wc -l
# Issues and PRs (if GitHub)
gh issue list --state all --limit 1 --json number | head
gh pr list --state all --limit 1 --json number | head
- 6+ months of public development
- Multiple commits (not a single bulk dump)
- At least one tagged release
- Evidence of issues or PRs (even self-authored counts)
6. Installation Instructions
- README has clear installation section
- Dependencies listed or handled automatically
- Both stable (CRAN/PyPI) and development (GitHub) install paths documented
Output Format
# Community Audit Report
## Summary
- **License**: [type] — pass | fail
- **CONTRIBUTING**: present | missing
- **CODE_OF_CONDUCT**: present | missing
- **Issue tracker**: enabled | disabled
- **Dev history**: N months, M commits, K contributors
- **Installation docs**: present | missing
## Findings
### [Finding title]
- **Check**: license | contributing | conduct | tracker | history | install
- **Severity**: critical | major | minor
- **Evidence**: [what was found or not found]
- **Fix**: [actionable — e.g., "Create CONTRIBUTING.md with bug reporting and PR guidelines"]
[Repeat for each finding]
## Strengths
[Anything notably good — active issue tracker, detailed contributing guide, etc.]
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.
- today First seen · 113 lines · 46 tokens per session scan A f9873fb2e238
community-auditor is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 852 once invoked, about $0.0002 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 agents, from other repositories
data_layer
AI ethics, data governance, and schema validation checkpoint. Use for W4 feature validation ethics clearance, compliance audits, and data lineage verification. Oversight level 3 — requires human approval on BLOCKED decisions.
patent-creator
Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.
clinical-research-coordinator
Use for Clinical Research Coordinator work in Clinical Operations including IRB, consent, protocol deviation, SAE, regulatory binder.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
privacy-reviewer
Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct evidence set from security. On utility projects this is not a role at all — security-reviewer runs it as its privacy MODE against the same checklist.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.