Borrowing it
Nothing to install: this file belongs to anhnguyen0905/codex-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.
curl -O https://raw.githubusercontent.com/anhnguyen0905/codex-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/anhnguyen0905/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/anhnguyen0905/codex-mcp/agents-md)<a href="https://agentmods.dev/instructions/anhnguyen0905/codex-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anhnguyen0905/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 5.1 | $0.00770 | $0.00770 |
| Opus 5 | $0.00385 | $0.00385 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — codex-mcp / codex-flow
Source of the codex-mcp npm package and the codex-flow Claude Code plugin. The plugin's
behavior is defined in markdown instruction files, not runtime code.
Build & test
npm test— vitest (tests/*.test.ts, AAA style). Must stay green before any commit.npm run build—tsctodist/.node scripts/check-command-sync.mjs— command-mirror gate (see below).node scripts/check-release-consistency.mjs— version-agreement gate (only on version bumps).- In the Codex sandbox, if vitest fails with EPERM writing
node_modules/.vite-temp, usenpx vitest run <file> --configLoader runner; host-run results remain the source of truth.
Hard conventions (CI-gated — violating these red-fails tests)
-
Command mirror:
commands/codex-flow.mdhas a byte-identical mirror at.claude/commands/codex-flow.md. Every edit to one must becp-copied to the other. Gates:scripts/check-command-sync.mjs+tests/flowDocs.test.ts. -
Skill files:
skills/<name>/SKILL.md. Frontmatter is exactly two unquoted fields:name:and a one-linedescription:. Body follows the existing skills —# <Title> (embed into Codex prompts), then## Standards blockwith a fenced ``` block whose contents are what gets embedded into a Codex prompt (label line + terse- Key: valuebullets). Matchskills/exec-deliverable/SKILL.md. -
Skill reachability: every
codex-flow:<token>referenced incommands/codex-flow.mdmust resolve to an existingskills/<token>/SKILL.md(tests/flowDocs.test.ts). Add the token and the SKILL.md together. Skill tokens named in the command must sit inside a**Load skills first...**:line to be recognized. -
Release consistency: on a version bump, the version must agree across
package.json,package-lock.json(2 spots),server.json(2 spots),.claude-plugin/plugin.json, the.mcp.jsonnpx pin, and a## [<version>]heading inCHANGELOG.md. -
Run-state writes:
.codex-flow/STATE.mdand taskStatuslines in.codex-flow/TASKS.mdare edited only throughnode scripts/flow-state.mjs(set/check/task); never hand-edit them in the flow. The helper validates keys, phases, task stages, and status transitions.
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.
- 2d ago Changed · +4 lines · +82 tokens per session 90e247bb9802
- 6d ago First seen · 43 lines · 688 tokens per session scan A a62cb367979f
codex-mcp AGENTS.md is an instructions file published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed 3d ago), licensed MIT. It adds 770 tokens to every session, about $0.0038 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
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.
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.
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).
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).
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.
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.