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.
npx agentmods add instructions/fotoetienne/gru/claude-mdgit clone --depth 1 https://github.com/fotoetienne/gruWrote 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/fotoetienne/gru/claude-md)<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>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 | $0.04110 | $0.04110 |
| Opus 5 | $0.02055 | $0.02055 |
| Sonnet 5 | $0.00822 | $0.00822 |
| Haiku 4.5 | $0.00411 | $0.00411 |
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 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:
- Fix the issues using the suggested commands (e.g.,
just fmtorjust fix-clippy) - Review the diff with
git diffto see what changed - Stage the fixed files selectively with
git add <files> - Never use
git add .orgit add -A- always stage files explicitly - 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
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.
- 5d ago First seen · 344 lines · 4,110 tokens per session scan A d7c162cbc3b8
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.
Other instructions, from other repositories
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).