This file is byte-identical to the first copy the registry indexed, one of 391 indexed copies. Same content hash, so the same checks give both the same grade.
CLAUDE.md from rijans/agent-skills is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
The line at the top of this page pins the label git:20261011.e8519fa, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
B 13 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
fail: Size between 200 bytes and 200 KB (11 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Starting a new one? Use a template for CLAUDE.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
GitHub
rijans/agent-skills · 2 stars · license MIT · pushed 2026-10-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3g47po6gdvrjwe5i
GET https://markdownregistry.com/api/v1/resolve?ref=rijans/agent-skills/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/336cc4fbf19beaada7ccf9986414fa91851a8d7a07dfb3ccbe800a69eed0ab49
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
rijans/agent-skills · skills/duckdb-wasm/SKILL.md · Query Parquet files, run in-browser analytical SQL, and persist databases to OPFS with @duckdb/duckdb-wasm, Web…
rijans/agent-skills · skills/humanize-text/SKILL.md · Write and rewrite natural, human-authored prose across articles, technical guides, and documentation while preserving…
rijans/agent-skills · skills/openai-realtime-webrtc/SKILL.md · Build low-latency voice AI agents with OpenAI Realtime API over WebRTC, ephemeral session tokens, RTCPeerConnection…
rijans/agent-skills · skills/use-telegram-serverless/SKILL.md · Build, ship, and scale simple or full-stack Telegram bots and Mini Apps on Telegram Serverless with V8 JS, SQLite…
