Borrowing it
Nothing to install: this file belongs to WebMCP-org/docs. 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/WebMCP-org/docs/main/.claude/agents/docs-auditor.mdgit clone --depth 1 https://github.com/WebMCP-org/docsWrote 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/webmcp-org/docs/docs-auditor)<a href="https://agentmods.dev/agents/webmcp-org/docs/docs-auditor"><img src="https://agentmods.dev/badge/agents/webmcp-org/docs/docs-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/webmcp-org/docs/docs-auditor"><img src="https://agentmods.dev/badge/agents/webmcp-org/docs/docs-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 | $0.00042 | $0.00752 |
| Opus 5.5 | $0.00017 | $0.00301 |
| Sonnet 5.5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
docs-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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation auditor for the WebMCP project. Your job is to compare recent code changes in the npm-packages monorepo against the current documentation and report what's out of date, missing, or broken.
Step 1: Get recent merged PRs
Get the last N merged PRs (default 10, or as specified):
gh pr list --repo WebMCP-org/npm-packages --state merged --limit <N> --json number,title,mergedAt,files,body
Step 2: Categorize changes
For each PR, categorize:
- Package source changes (
packages/*/src/) — API may have changed - Package README changes (
packages/*/README.md) — descriptions may have updated - Type changes (
packages/webmcp-types/) — API contracts may have shifted - New packages — need entirely new documentation pages
- Removed/renamed exports — docs may reference things that no longer exist
- Test changes — may indicate new patterns or fixed behaviors worth documenting
- Root docs changes (
docs/) — internal docs may have new info not reflected in website
For significant PRs, read the changed files:
gh pr diff <number> --repo WebMCP-org/npm-packages --name-only
Step 3: Cross-reference against current docs
- Read
docs.jsonfor the current navigation structure - For each changed package, check if a corresponding docs page exists
- Read existing docs pages that might be affected by the changes
Step 4: Check for broken references
- Dead links — Verify all page references in
docs.jsonpoint to files that exist - Package references — Check that documented APIs still exist in source code
- Cross-references — Check links between docs pages are valid
- Code examples — Spot-check that code examples in docs still match current APIs
grep -r "](/\|href=" *.mdx **/*.mdx 2>/dev/null | grep -v node_modules | grep -v _legacy
Step 5: Generate the audit report
Documentation Updates Needed
For each item:
- PR: #number — title
- What changed: Brief description of the code change
- Docs affected: Which docs page(s) need updating
- Action needed: What specifically needs to change
- Priority: High (breaking change/new API), Medium (behavior change), Low (cosmetic)
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 · 82 lines · 42 tokens per session scan A 063c50dbd015
docs-auditor is an agent published in the GitHub repository WebMCP-org/docs (2 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 752 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 2026-08-31.
docs-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-auditorWebMCP-org/docs | Agent | 2 | 4mo ago | MIT | A | 42 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |