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/sam-mountainman/codex-mcp/agents-mdgit clone --depth 1 https://github.com/sam-mountainman/codex-mcpWrote 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/sam-mountainman/codex-mcp/agents-md)<a href="https://agentmods.dev/instructions/sam-mountainman/codex-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sam-mountainman/codex-mcp/agents-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 | $0.00397 | $0.00397 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
codex-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 3d 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.
What it actually says
codex-mcp setup contract
If a user asks an AI coding agent to set up this repository, complete the setup for Claude Code instead of stopping at a README summary.
- Read the current default branch and release metadata when the repository is hosted remotely. Do not choose a version from a stale local cache.
- Confirm Node.js 18+ is available.
- Install the official Codex CLI (
@openai/codex) and Claude Code (@anthropic-ai/claude-code) only when missing. - Before changing authentication, use a structured question UI when available. Present these choices in order:
- ChatGPT account login (recommended): run
codex loginand use the user's ChatGPT/Codex allowance. - OpenAI API key: use metered OpenAI Platform billing and pass the key through stdin, never a command argument or normal chat.
- Existing authentication: preserve a working
codex login statussession.
- ChatGPT account login (recommended): run
- Run the platform installer:
- macOS/Linux:
./install.sh - Windows PowerShell:
.\install.ps1
- macOS/Linux:
- Require
npm run verify,claude plugin validate --strict ., andclaude mcp listto succeed forplugin:codex-mcp:codex. - Unless the user opts out, run
npm run live-smoke. This makes two small model calls and verifies both a new session and continuation with a changed reasoning level. - Tell the user to restart Claude Code or run
/reload-plugins, then askCodexの状態を確認して.
Do not hard-code the user's requested model or reasoning level into source. The server default is gpt-5.6-sol with max, while every model tool accepts per-call model and reasoning_effort overrides. Preserve explicit user choices exactly and let the local Codex CLI validate model availability.
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.
- 3d ago First seen · 20 lines · 397 tokens per session scan A e97a751429ac
codex-mcp AGENTS.md is an instructions file published in the GitHub repository sam-mountainman/codex-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 397 tokens to every session, about $0.0020 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.