Markdown lint
License MIT
Prompt-injection scan
No credentials
AI safety scan: clean — A code-documentation methodology skill that emphasizes reading actual code over names, ranking facts by proximity to code, and refusing to invent rationales. It includes explicit safety guardrails (no secrets in examples, no papering over bugs, no deletion of others' docs without consent, no compliance/legal claims) and shows no hidden instructions or attempts to override agent behavior.
Approved by a human reviewer before publishing.
Every version goes through the same pipeline; the badge always describes the version you download. Automated checks reduce risk, they don’t replace reading the file before you run it.