mcp-agents: Instructions file for Codex

AGENTS.md

mcp-agents AGENTS.md is an instructions file for Codex, OpenCode from thomaswitt/mcp-agents. It costs 5,180 tokens per session, scanned B, original, no licence file.

A project guide for coding agents working on the mcp-agents codebase. It describes the architecture, commands, server operation, and tests.

In plain words
What is it for?
Use it to understand the project layout, run the server, and run fast tests without making real command-line calls.
Why use it?
It gives the agent project-specific rules and commands, reducing guesswork when changing or checking the code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is thomaswitt/mcp-agents's own configuration. It tells Codex and OpenCode how to work on mcp-agents 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 mcp-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thomaswitt/mcp-agents. 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/thomaswitt/mcp-agents/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/thomaswitt/mcp-agents

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.

agentmods badge for mcp-agents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thomaswitt/mcp-agents/agents-md/github.svg)](https://agentmods.dev/instructions/thomaswitt/mcp-agents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thomaswitt/mcp-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/thomaswitt/mcp-agents/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.

agentmods 80×15 button for mcp-agents AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thomaswitt/mcp-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/thomaswitt/mcp-agents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,180 This file is loaded in full into every session.
When invoked 5,180 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.05180 $0.05180
Opus 5.5 $0.02072 $0.02072
Sonnet 5.5 $0.01036 $0.01036
Haiku 4.5 $0.00518 $0.00518

Measured yesterday against content hash 7f2a5b5d30f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-agents AGENTS.md scanned grade B with 2 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 yesterday.

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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- Isolated `CODEX_HOME` / `CODEX_SQLITE_HOME` generations copy `auth.json` and `models_cache.json`, selectively mirror explicit Fast mode, all explicit project trust decisions, and the source `model_provider` with its al

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Follow existing patterns in `server.js` — switch statements for CLI parsing, Promise wrappers for child_process
AGENTS.md · 141 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday Changed · +976 tokens per session scan A → B 7f2a5b5d30f1
  2. 24d ago Changed · +2 lines · +375 tokens per session 8262e5ca2bd6
  3. 1mo ago Changed · +1 lines · +412 tokens per session 6bb501c5f088
  4. 1mo ago Changed · +77 tokens per session cf147a69d716
  5. 1mo ago Changed · +1 lines · +457 tokens per session 114d0ea1f820
  6. 1mo ago Changed · +2 lines · +97 tokens per session 9693eff26967
  7. 1mo ago Changed · +209 tokens per session 07b063c82b93
  8. 2mo ago First seen · 135 lines · 2,577 tokens per session scan A ef1725117bab

Subscribe to this mod's changes

mcp-agents AGENTS.md is an instructions file published in the GitHub repository thomaswitt/mcp-agents (21 stars, last pushed 2d ago), with no licence file. It adds 5,180 tokens to every session, about $0.0207 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads mcp configuration, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

mcp-agents AGENTS.md compared with instructions from other repositories

mcp-agents AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-agents AGENTS.mdthomaswitt/mcp-agentsInstructions file212d agononeB5,180Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot