maestro-mcp: Instructions file for Claude Code

CLAUDE.md

maestro-mcp CLAUDE.md is an instructions file for Claude Code from rmstxrx/maestro-mcp. It costs 2,717 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for working on Maestro MCP v1, an archived system that coordinates tasks across multiple computers through an AI-agent interface.

In plain words
What is it for?
Use them when examining the old architecture, its task-running process, or its 11 available tools during migration or maintenance work.
Why use it?
They prevent developers from treating the old repository as the active project and preserve details useful for understanding the move to Maestro v2.

Instructions file for Claude Code

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

This is rmstxrx/maestro-mcp's own configuration. It tells Claude Code how to work on maestro-mcp 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 maestro-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rmstxrx/maestro-mcp. 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/rmstxrx/maestro-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rmstxrx/maestro-mcp

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 maestro-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rmstxrx/maestro-mcp/claude-md.svg)](https://agentmods.dev/instructions/rmstxrx/maestro-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rmstxrx/maestro-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rmstxrx/maestro-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,717 This file is loaded in full into every session.
When invoked 2,717 The same file — it is already loaded in full.
Security scan A 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 $0.02717 $0.02717
Opus 5 $0.01358 $0.01358
Sonnet 5 $0.00543 $0.00543
Haiku 4.5 $0.00272 $0.00272

Measured 7d ago against content hash 9bf00604f8a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

maestro-mcp 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| File I/O | `transfer_pull_file` | Pull any larger file out-of-band via a ready-made curl command. |
CLAUDE.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DORMANT — Maestro v1 (maestro-mcp) superseded by Maestro v2

This repo is the archived v1 of the Maestro orchestrator. Active development happens in ~/Development/maestro/ (v2). Do not develop here.

Dormant as of: 2026-04-14.

See STATE.md for the v1→v2 migration pointers. The guide below is preserved for reference — much of the v1 design carried forward into v2 unchanged.


Maestro MCP — Developer Guide (v1, historical)

Maestro is a multi-host machine fleet orchestration layer and AI agent orchestra, exposed via the Model Context Protocol (MCP). It runs inside a Docker container on Cellar and uses Hub-local tmux for all task execution and tracking.

Architecture

All task execution uses Hub-local tmux: every run_task(...) and dispatch_agent(...) creates a tmux window on the Hub. Commands are staged into /tmp/maestro/inbox/, executed inside SSH sessions, and tracked in the persistent ledger.

  • Entry Point (server.py): Configures FastMCP, sets up OAuth, wires modules, and starts the server.
  • maestro/mux.py: Hub-local tmux primitives (stage_script, create_task_window, wait_for_completion, kill_window).
  • maestro/tools/fleet.py: Fleet tools: run_task, read_file, write_file, orchestra_status, stop_task.
  • maestro/tools/orchestra.py: Orchestra tools: dispatch_agent, current_tasks, read_task_output, transfer_pull_file, transfer_push_file, prepare_relay. Also owns the task registry, task ledger, auto-promote, and scope prefix.
  • maestro/relay.py: HTTP transfer handlers, bearer auth, ephemeral tokens, and server-side staging for out-of-band downloads/uploads.
  • maestro/task_result.py: /tasks/{id}/result HTTP handler.
  • maestro/hosts.py: Fleet topology, host registry, allowed-dir enforcement, shell-aware command wrapping.
  • maestro/transport.py: SSH ControlMaster lifecycle and SCP helpers.
  • maestro/local.py: Zero-overhead local execution for the hub host (is_local: true).
  • maestro/client.py: Client classification and per-client block timeout profiles.
  • maestro/config.py: Environment-backed configuration (MaestroConfig).
  • maestro/oauth_state.py: Atomic JSON persistence for OAuth state.

Read the full file on GitHub · 240 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. 7d ago First seen · 240 lines · 2,717 tokens per session scan A 9bf00604f8a2

Subscribe to this mod's changes

maestro-mcp CLAUDE.md is an instructions file published in the GitHub repository rmstxrx/maestro-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,717 tokens to every session, about $0.0136 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens