agent-pi: Instructions file for Claude Code

CLAUDE.md

agent-pi CLAUDE.md is an instructions file for Claude Code from ruizrica/agent-pi. It costs 793 tokens per session, scanned C, original, MIT.

A rulebook for agent-pi, including strict policies for Git operations. It explains when pushing changes is allowed, how repository visibility matters, and how its two remotes differ.

In plain words
What is it for?
Use it when modifying agent-pi, checking Git remotes, preparing commits, or deciding whether a change may be pushed.
Why use it?
It prevents accidental pushes, especially to public repositories, and keeps private and public project content separated. It also makes the required approval and verification steps clear.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is ruizrica/agent-pi's own configuration. It tells Claude Code how to work on agent-pi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-pi configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ruizrica/agent-pi/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ruizrica/agent-pi

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-pi CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ruizrica/agent-pi/claude-md/github.svg)](https://agentmods.dev/instructions/ruizrica/agent-pi/claude-md)
Your own site
<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.

agentmods 80×15 button for agent-pi CLAUDE.md

Your own site · 80×15
<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>
Per session 793 This file is loaded in full into every session.
When invoked 793 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash cb0bbcf402ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.)
CLAUDE.md · 77 lines

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 push unless 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:
    1. State that you are about to push
    2. Name the remote and branch
    3. Confirm the repo visibility (public vs private)
    4. 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-devruizrica/pi-dev — PRIVATE repo. Full content. This is the working repo.
  • originruizrica/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 origin without explicit user approval.
  • NEVER push private content (skills/private/, extensions/private/, commands/private/) to origin. 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 status before 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/

Read the full file on GitHub · 77 lines

Changes

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.

  1. 9d ago First seen · 77 lines · 793 tokens per session scan C cb0bbcf402ea

Subscribe to this mod's changes

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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens