What is relayos-mcp AGENTS.md?

An AGENTS.md instruction file for relayos-mcp, a Python server that lets coding agents coordinate local terminal agents and commands. It documents the project's architecture, setup, and verification steps.

Use it when maintaining relayos-mcp, installing its development dependencies, or running syntax, type, and other documented checks.

It gives an agent project-specific guidance so it can understand the code layout and check changes using the intended commands.

How jjjjjjjjnnjnn/relayos-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to jjjjjjjjnnjnn/relayos-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/jjjjjjjjnnjnn/relayos-mcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jjjjjjjjnnjnn/relayos-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/jjjjjjjjnnjnn/relayos-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/jjjjjjjjnnjnn/relayos-mcp/agents-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jjjjjjjjnnjnn/relayos-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jjjjjjjjnnjnn/relayos-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 511 This file is loaded in full into every session.

When invoked 511 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00511	$0.00511
Opus 5.5	$0.00204	$0.00204
Sonnet 5.5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 17d ago against content hash c1da832fda5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

relayos-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 17d 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

relayos-mcp — AI Maintainer & Agent Guide (AGENTS.md)

Project Identity: Model Context Protocol (MCP) server designed for Claude Code & Cursor to orchestrate local terminal AI agents (Mimo, OpenCode, shell) for cost-effective, parallel task execution. Language: Python 3.10+ / FastMCP Build System: setuptools / pyproject.toml

🎯 Architecture & Execution Model

Claude Code (Client)  <=== STDIO (JSON-RPC) ===>  relayos_mcp.server (Server)
                                                         │
                                    ┌────────────────────┴────────────────────┐
                                    ▼                                         ▼
                            Agents Subsystem                           CLI Subsystem
                       (mimo / opencode / claude)                     (run_command)

relayos_mcp/server.py: The MCP Server definition. Registers all exposed MCP tools using @mcp.tool().
relayos_mcp/agents/: Wrappers around sub-agent CLI / API runners.
claude_prompt.md: Behavioral contract and prompt guidelines injected into the host LLM to guide tool routing.

⚡ Standard Verification & Test Commands

Any AI working on this repository must verify changes with:

# 1. Install editable package with dev dependencies
pip install -e .

# 2. Syntax and type check
python -m py_compile relayos_mcp/server.py

# 3. Test MCP server initialization via stdio
python -m relayos_mcp.server --help

🛑 Strict Rules for AI Collaborators

Stdio Channel Integrity:
- The MCP protocol strictly relies on stdin/stdout for JSON-RPC message exchange.
- NEVER use raw print() statements inside server handlers that output to stdout! All debug logging must be directed to sys.stderr or a dedicated logfile.
Fail-Safe Sub-agents:
- If a sub-agent (like mimo or opencode) fails, is not installed, or times out, the tool MUST return a clean error description in the JSON payload, rather than crashing the MCP server process.
Timeout Controls:
- Sub-agent shell executions must enforce a hard timeout (default 60s) to prevent hanging Claude Code's session.

Read the full file on GitHub · 52 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.

17d ago First seen · 52 lines · 511 tokens per session scan A c1da832fda5b

Subscribe to this mod's changes

relayos-mcp AGENTS.md is an instructions file published in the GitHub repository jjjjjjjjnnjnn/relayos-mcp (1 stars, last pushed 17d ago), licensed MIT. It adds 511 tokens to every session, about $0.0020 per session on Opus 5.5. 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 2026-10-21.

Building agents Multi-Agent ai-orchestrator developer-tools mcp model-context-protocol

relayos-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
relayos-mcp AGENTS.mdjjjjjjjjnnjnn/relayos-mcp	Instructions file	1	17d ago	MIT	A	511	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

relayos-mcp: Instructions file for Codex