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.
npx skills add jmlero/claude-toolkit --skill audit-docsgit clone --depth 1 https://github.com/jmlero/claude-toolkitWrote 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/jmlero/claude-toolkit/audit-docs)<a href="https://agentmods.dev/skills/jmlero/claude-toolkit/audit-docs"><img src="https://agentmods.dev/badge/skills/jmlero/claude-toolkit/audit-docs/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/jmlero/claude-toolkit/audit-docs"><img src="https://agentmods.dev/badge/skills/jmlero/claude-toolkit/audit-docs.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 | $0.00033 | $0.00717 |
| Opus 5.5 | $0.00013 | $0.00287 |
| Sonnet 5.5 | $0.00007 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
audit-docs 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform a comprehensive audit of all documentation and markdown files in this project.
Scope
Find and read every .md file in the project. Pay special attention to:
docs/directory (all files and subdirectories)- Root-level docs (
README.md,CLAUDE.md,CONTRIBUTING.md,CHANGELOG.md, etc.) - Any index or table-of-contents files
- Agent/skill definitions if present (
.claude/)
Audit Checks
For each file, evaluate and report as: OK, WARN, or ACTION.
1. Staleness
- Does the content match the current codebase? (Check referenced env vars, endpoints, config values against actual code)
- Are referenced files/directories still present?
- Are issue-specific docs for completed/shipped work still in active docs instead of an archive?
- Do code examples match current patterns?
2. Redundancy
- Is the same information documented in multiple files?
- Are there docs that are strict subsets of other docs?
- Do architecture/project docs contain implementation details that belong elsewhere?
3. Broken References
- Do all internal links and cross-references point to existing files?
- Do all
@./pathincludes in CLAUDE.md resolve to existing files? - Does any index/TOC file list only files that exist?
- Does any index/TOC include all files that actually exist?
4. Bloat & Scope Creep
- Are stable docs free of issue-specific implementation details?
- Are any files over 300 lines? If so, can they be split or trimmed?
- Are there empty or near-empty files (<10 lines of content)?
- Are there empty directories?
5. Accuracy of Context-Loaded Docs
Files loaded via @ in CLAUDE.md get injected into every AI session. They must be worth the token cost.
- Is every
@-included file actively useful for day-to-day development? - Could any
@-included content be moved to on-demand docs? - Is the total token footprint of
@-included files reasonable? (flag if combined content exceeds ~500 lines)
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.
- 2mo ago First seen · 78 lines · 33 tokens per session scan A 23a7af59520b
audit-docs is a skill published in the GitHub repository jmlero/claude-toolkit (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 717 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 2026-08-31.
audit-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-docsjmlero/claude-toolkit | Skill | 2 | 6mo ago | Apache-2.0 | A | 33 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |