What is maestro-mcp AGENTS.md?

Developer instructions for Maestro MCP, a Python server that coordinates tasks across computers through the Model Context Protocol, or MCP.

Use them when installing dependencies, editing Maestro modules, checking Python syntax, running tests, or starting the server in command-line or web mode.

They document setup, code conventions, architecture, syntax checks, tests, and ways to run the server.

maestro-mcp AGENTS.md — Instructions file for Codex and OpenCode by rmstxrx: Developer instructions for Maestro MCP, a Python server that…

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/rmstxrx/maestro-mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/rmstxrx/maestro-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rmstxrx/maestro-mcp/agents-md.svg)](https://agentmods.dev/instructions/rmstxrx/maestro-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/rmstxrx/maestro-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rmstxrx/maestro-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 738 This file is loaded in full into every session.

When invoked 738 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00738	$0.00738
Opus 5	$0.00369	$0.00369
Sonnet 5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 4d ago against content hash 64e6ff6f1b5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maestro-mcp AGENTS.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.

AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maestro MCP — Agent Developer Guide

Guide for AI coding agents (Codex, Claude Code, Gemini) working on this codebase.

Build & Test

# Setup
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Syntax check (fast, no runtime deps)
python -m py_compile maestro/hosts.py maestro/tools/fleet.py

# Run tests
pytest tests/ -v

# Run server (stdio mode for MCP)
python server.py --transport stdio

# Run server (HTTP mode, requires MAESTRO_ISSUER_URL)
python server.py --transport streamable-http --port 8222

Code Style

Imports: from __future__ import annotations at top of every module. stdlib → third-party → local, separated by blank lines.
Type annotations: Modern union syntax (str | None, list[str]), not Optional[str] or List[str].
Formatting: 4-space indent. No trailing whitespace. Single blank line between functions, two before top-level classes.
Naming: _private_function for internal helpers, UPPER_CASE for module constants, lower_case for local variables.

Architecture

server.py              ← FastMCP entry point, OAuth setup, wiring
maestro/
  config.py            ← MaestroConfig (frozen dataclass, from_env)
  hosts.py             ← Fleet topology: HostConfig, HOSTS registry, command helpers
  transport.py         ← SSH ControlMaster lifecycle, _ssh_run, _scp_run, retries
  local.py             ← Zero-overhead local execution (is_local: true hosts)
  relay.py             ← HTTP file transfer relay (push/pull/task results)
  client.py            ← Client context detection (remote/local/lan profiles)
  oauth_state.py       ← Atomic JSON persistence for OAuth state
  tools/
    fleet.py           ← All MCP tools (fleet + orchestra) registered here
    orchestra.py        ← Agent dispatch helpers, task registry, auto-promote

Key Patterns

Auto-Promote (block_timeout)

Execution tools try to finish within block_timeout seconds. If they don't, the task is shielded into TASK_REGISTRY and a task_id is returned. The caller uses poll() or the HTTP endpoint to retrieve results.

Read the full file on GitHub · 69 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.

4d ago First seen · 69 lines · 738 tokens per session scan A 64e6ff6f1b5d

Subscribe to this mod's changes

maestro-mcp AGENTS.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 738 tokens to every session, about $0.0037 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.

Building agents

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 · 5,182 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

maestro-mcp AGENTS.md