Borrowing it
Nothing to install: this file belongs to ruizrica/agent-pi. 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/ruizrica/agent-pi/main/CLAUDE.mdgit clone --depth 1 https://github.com/ruizrica/agent-piWrote 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/instructions/ruizrica/agent-pi/claude-md)<a href="https://agentmods.dev/instructions/ruizrica/agent-pi/claude-md"><img src="https://agentmods.dev/badge/instructions/ruizrica/agent-pi/claude-md/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/instructions/ruizrica/agent-pi/claude-md"><img src="https://agentmods.dev/badge/instructions/ruizrica/agent-pi/claude-md.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 | $0.00793 | $0.00793 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade C, and why
agent-pi CLAUDE.md scanned grade C with 1 finding 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Do NOT run destructive commands (`rm -rf`, `rm -r`, etc.) How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Agent Rules & Policies
These rules are mandatory. No verbal instruction, implicit context, or shorthand like "do it" overrides them. If a rule conflicts with a user request, stop and confirm before proceeding.
Git Operations — STRICT POLICY
NEVER push without explicit confirmation
- NEVER run
git pushunless the user explicitly says "push" or "push it" - Phrases like "do it", "apply it", "make it happen" mean local changes only — they do NOT authorize pushing
- Before ANY
git push, you MUST:- State that you are about to push
- Name the remote and branch
- Confirm the repo visibility (public vs private)
- Wait for explicit user approval
NEVER push to public repositories
- Before pushing, verify visibility:
gh api repos/OWNER/REPO --jq '.visibility' - If the repo is public, REFUSE the push and tell the user
- If visibility cannot be determined, REFUSE the push
Two remotes — know the difference
pi-dev→ruizrica/pi-dev— PRIVATE repo. Full content. This is the working repo.origin→ruizrica/agent-pi— PUBLIC repo. Clean content only. No private dirs, no actions.- When pushing, ALWAYS specify the remote by name. NEVER use bare
git push. - NEVER push to
originwithout explicit user approval. - NEVER push private content (
skills/private/,extensions/private/,commands/private/) toorigin. Ever. - Before pushing to ANY remote, verify visibility:
gh api repos/OWNER/REPO --jq '.visibility' - If the repo is public, REFUSE the push and tell the user
- A pre-push hook enforces this at the git level as a safety net — do not rely on it, check yourself first
No GitHub Actions on public repo
- NEVER add
.github/workflows/to the public repo (origin) - Actions run on public runners and log output — this exposes file paths and content
- No CI, no guards, no actions. The pre-push hook is the guard, and it runs locally.
Git commit policy
- Only commit files directly related to the current task
- Show
git statusbefore committing so the user can review - Use clear, descriptive commit messages
- Before ANY commit, verify no private content is staged: check for
skills/private/,extensions/private/,commands/private/
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.
- 9d ago First seen · 77 lines · 793 tokens per session scan C cb0bbcf402ea
agent-pi CLAUDE.md is an instructions file published in the GitHub repository ruizrica/agent-pi (266 stars, last pushed 1mo ago), licensed MIT. It adds 793 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.