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/mirinodev/maestro/claude-mdgit clone --depth 1 https://github.com/mirinodev/maestroWrote 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/mirinodev/maestro/claude-md)<a href="https://agentmods.dev/instructions/mirinodev/maestro/claude-md"><img src="https://agentmods.dev/badge/instructions/mirinodev/maestro/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 | $0.03926 | $0.03926 |
| Opus 5 | $0.01963 | $0.01963 |
| Sonnet 5 | $0.00785 | $0.00785 |
| Haiku 4.5 | $0.00393 | $0.00393 |
Grade A, and why
maestro CLAUDE.md scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 475 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
Maestro is a CLI tool for managing Git worktrees with a conductor/orchestra theme. It helps developers work on multiple branches in parallel by creating "orchestra members" (worktrees) with integration for Claude Code, tmux, GitHub, and more.
Development Commands
IMPORTANT: This project uses pnpm exclusively. All commands must use pnpm instead of npm.
Build & Test
pnpm build- Build the TypeScript project using tsuppnpm dev- Watch mode development using tsxpnpm test- Run tests with vitestpnpm test:e2e- Run end-to-end testspnpm test:coverage- Run tests with coverage report (80% minimum threshold)pnpm typecheck- Type checking without emitting files
Code Quality
pnpm lint- ESLint checking on TypeScript filespnpm lint:ci- CI-specific linting with max 26 warnings thresholdpnpm format- Format code with Prettierpnpm prettier:check- Check code formatting
Single Test Execution
pnpm test -- path/to/test.test.ts- Run a specific test filepnpm test -- --reporter=verbose- Run tests with detailed output
Publishing
pnpm changeset- Create a changeset for releasespnpm version- Version bump using changesetspnpm release- Build and publish to npmpnpm prepublishOnly- Pre-publish hook (auto-build and generate completions)
Core Architecture
Main Components
- CLI Entry Point:
src/cli.ts- Main CLI interface using Commander.js - Commands:
src/commands/- Individual command implementations - Core Logic:
src/core/- Core Git and configuration management - Types:
src/types/index.ts- TypeScript type definitions - Utils:
src/utils/- Utility functions and helpers
Key Classes
GitWorktreeManager(src/core/git.ts) - Git worktree operations using simple-git- Configuration management in
src/core/config.ts - Individual command handlers in
src/commands/
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.
- 4d ago First seen · 475 lines · 3,926 tokens per session scan A 1d665fae08d2
maestro CLAUDE.md is an instructions file published in the GitHub repository mirinodev/maestro (9 stars, last pushed 11mo ago), licensed MIT. It adds 3,926 tokens to every session, about $0.0196 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
git-worktree-runner ai.instructions.md
Instructions for coderabbitai/git-worktree-runner, covering ai adapter instructions, when to use a file vs registry, adding a standard ai tool (registry), adding a custom ai tool (file override) and toolname adapter.
mulmoterminal CLAUDE.md
Claude Code instructions for receptron/mulmoterminal, covering claude.md — mulmoterminal, stack & package manager, run after changes, import a component at module scope, never inside a test and no emojis.
vscode-ext-tmux-worktree AGENTS.md
AGENTS.md instructions for kargnas/vscode-ext-tmux-worktree, covering ai agent guidelines, instruction, tested vs code, 1. codebase understanding and project structure.
nexpath CLAUDE.md
Claude Code instructions for hi0001234d/nexpath, covering debugging, nexpath status, nexpath config get, nexpath config set and role: founder | indiehacker | pm.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
ai-research-arm CLAUDE.md
Claude Code instructions for guzus/ai-research-arm, covering claude.md, project overview, core pipeline architecture, key components and scripts (scripts/).