gru CLAUDE.md

gru CLAUDE.md is an instructions file for coding agents from fotoetienne/gru. It costs 4,110 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Gru, a Rust program that coordinates Claude Code sessions to work on GitHub issues and create pull requests.

In plain words
What is it for?
Use them when developing or reviewing Gru, especially when running its checks or installing it locally.
Why use it?
They give an agent the project context and the standard commands for building, testing, formatting, linting, and checking the code.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/fotoetienne/gru/claude-md
Clone the repo
git clone --depth 1 https://github.com/fotoetienne/gru

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 gru CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fotoetienne/gru/claude-md.svg)](https://agentmods.dev/instructions/fotoetienne/gru/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fotoetienne/gru/claude-md"><img src="https://agentmods.dev/badge/instructions/fotoetienne/gru/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,110 This file is loaded in full into every session.
When invoked 4,110 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.04110 $0.04110
Opus 5 $0.02055 $0.02055
Sonnet 5 $0.00822 $0.00822
Haiku 4.5 $0.00411 $0.00411

Measured 5d ago against content hash d7c162cbc3b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gru CLAUDE.md scanned grade A 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `child_process.rs` - Child process management utilities
CLAUDE.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Gru is a local-first LLM agent orchestrator that autonomously works on GitHub issues using Claude Code. It manages "Minions" (agent sessions) that claim issues, implement fixes, create PRs, and respond to reviews.

Current Phase: V1 - Basic delegation to Claude Code CLI Language: Rust Architecture: Single binary, GitHub as state store, git worktrees for isolation

Build & Development Commands

# Build
just build

# Build with release optimizations
just build-release

# Run tests
just test

# Run tests with output
just test-verbose

# Run linter (with warnings as errors)
just lint

# Automatically fix clippy lints where possible
just fix-clippy

# Format code
just fmt

# Check formatting without modifying
just fmt-check

# Run all checks (format + lint + test + build)
just check

# Install locally
just install

# Clean build artifacts
just clean

# Show project information
just info

Pre-commit Hooks

The project uses git hooks from .githooks/ that automatically run:

  • Code formatting check (just fmt-check)
  • Linting (just lint)
  • Tests (just test)
  • Branch protection (blocks commits to main)
  • TODO/FIXME warnings (non-blocking)

To enable hooks:

git config core.hooksPath .githooks

When pre-commit hooks fail:

  1. Fix the issues using the suggested commands (e.g., just fmt or just fix-clippy)
  2. Review the diff with git diff to see what changed
  3. Stage the fixed files selectively with git add <files>
  4. Never use git add . or git add -A - always stage files explicitly
  5. Example workflow:
    git commit -m "Fix bug"
    # Pre-commit hook fails with formatting errors
    just fmt
    git diff              # Review what changed
    git add src/main.rs   # Stage only the files you want to commit
    git commit -m "Fix bug"
    

To bypass in emergencies:

git commit --no-verify

Read the full file on GitHub · 344 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. 5d ago First seen · 344 lines · 4,110 tokens per session scan A d7c162cbc3b8

Subscribe to this mod's changes

gru CLAUDE.md is an instructions file published in the GitHub repository fotoetienne/gru (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 4,110 tokens to every session, about $0.0205 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.