update-docs — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited update-docs (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Scan the repository and update both README.md and CLAUDE.md to accurately reflect the current state of the codebase. Only document what actually exists — never add speculative content.
Collect the following by reading actual source files (never rely on existing docs):
server.registerTool( or server.tool( across src/ to get every tool name. Count them. Group by file/category.src/**/*.ts (excluding *.test.ts) and build the file tree. Note tool count per file (e.g. # 3 tools).src/**/*.test.ts and list them all.src/tools/index.ts for exported functions (e.g. jsonResponse, textResponse).export type across src/ to find type aliases (e.g. QueryParams).api.request()), how auth works, and the tool registration method (server.registerTool vs server.tool).src/config.ts for env var names and defaults.Read README.md and CLAUDE.md. For each, identify:
Apply edits to fix every discrepancy found. Preserve the existing structure and tone of each file — only change what is actually wrong or missing.
Re-read both files end-to-end after editing. Confirm they are consistent with each other and with the source code. Fix any remaining issues.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.