Borrowing it
Nothing to install: this file belongs to lynnlangit/precision-medicine-mcp. 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/lynnlangit/precision-medicine-mcp/main/.claude/skills/doc-audit/SKILL.mdgit clone --depth 1 https://github.com/lynnlangit/precision-medicine-mcpWrote 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/lynnlangit/precision-medicine-mcp/doc-audit)<a href="https://agentmods.dev/skills/lynnlangit/precision-medicine-mcp/doc-audit"><img src="https://agentmods.dev/badge/skills/lynnlangit/precision-medicine-mcp/doc-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/skills/lynnlangit/precision-medicine-mcp/doc-audit"><img src="https://agentmods.dev/badge/skills/lynnlangit/precision-medicine-mcp/doc-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 223 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 224 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00187 | $0.02522 |
| Opus 5.5 | $0.00075 | $0.01009 |
| Sonnet 5.5 | $0.00037 | $0.00504 |
| Haiku 4.5 | $0.00019 | $0.00252 |
Grade A, and why
precision-medicine-doc-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 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Precision Medicine MCP — Doc Audit Skill
Purpose
After every platform version update, run this audit to catch stale numbers, missing patient references, and repeated content before they spread further. The audit has six checks (A–F) that map directly to the six canonical principles. Run them in order: A feeds B, and B+C together surface D violations.
Step 0 — Prove the checks still fire
A green audit is only meaningful if the checks are capable of going red. Three times a check in this suite reported a clean repo while being structurally unable to fail — an exemption added to quiet noise in one sub-rule, then applied to the whole check. Run this first:
python .claude/skills/doc-audit/scripts/self_test.py
It builds a small synthetic repo in a temp directory, confirms the audit reports it clean, then introduces one defect at a time and asserts the responsible check catches it. The real repo is never touched.
If any check does not fire, stop. Fix that check before reading the audit output — a check that cannot fail reports green and stops anyone looking.
Step 1 — Run the automated audit script
The bundled script does the mechanical work. Run it from the repo root:
python .claude/skills/doc-audit/scripts/audit.py 2>&1 | tee /tmp/doc-audit-report.txt
The script outputs a structured report with six sections. Read the output — it will tell you exactly which files have violations and what the correct values are.
If the script is not yet installed (first run), see Installation below.
Step 2 — Interpret the six check sections
Check A — Tool counts: code vs registry
The script greps @mcp.tool() in every servers/mcp-*/src/*/server.py and
compares to the count in docs/reference/shared/server-registry.md.
A violation means: someone added or removed a tool in Python code but forgot to update the registry table. The server code is always right; update the registry.
Check B — Hardcoded counts: all MD files
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 248 lines · 187 tokens per session scan A e35481f232b3
precision-medicine-doc-audit is a skill published in the GitHub repository lynnlangit/precision-medicine-mcp (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 187 tokens to every session and 2,522 once invoked, about $0.0007 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.
precision-medicine-doc-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| precision-medicine-doc-auditlynnlangit/precision-medicine-mcp | Skill | 24 | 2mo ago | Apache-2.0 | A | 187 | Claude Code |
| decouplerscverse/decoupler | Skill | 301 | 4d ago | BSD-3-Clause | A | 192 | Claude Code, Codex |
| single-cellinflexa-ai/inflexa | Skill | 36 | yesterday | Apache-2.0 | A | 50 | Claude Code, Codex |
| microbiomeinflexa-ai/inflexa | Skill | 36 | yesterday | Apache-2.0 | A | 36 | Claude Code, Codex |
| statistical-modelinginflexa-ai/inflexa | Skill | 36 | yesterday | Apache-2.0 | A | 26 | Claude Code, Codex |
| dna-methylationinflexa-ai/inflexa | Skill | 36 | yesterday | Apache-2.0 | A | 40 | Claude Code, Codex |
| genomic-variantsinflexa-ai/inflexa | Skill | 36 | yesterday | Apache-2.0 | A | 31 | Claude Code, Codex |