What is claude-codex AGENTS.md?

Repository instructions for coding agents working on a project that connects the Codex desktop app to Claude Code through a shared server protocol. It describes project conventions, commands, and automatic checks.

Finding directory-specific guidance, installing dependencies, running development and build commands, type-checking, linting, testing, and checking the environment.

It gives an agent the local rules and test commands needed to edit the right parts of the project safely.

How fuergaosi233/claude-codex configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to fuergaosi233/claude-codex. 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/fuergaosi233/claude-codex/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fuergaosi233/claude-codex

Made for: Claude Code, 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/fuergaosi233/claude-codex/agents-md/github.svg)](https://agentmods.dev/instructions/fuergaosi233/claude-codex/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fuergaosi233/claude-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/fuergaosi233/claude-codex/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/fuergaosi233/claude-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/fuergaosi233/claude-codex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 861 This file is loaded in full into every session.

When invoked 861 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	$0.00861	$0.00861
Opus 5.5	$0.00344	$0.00344
Sonnet 5.5	$0.00172	$0.00172
Haiku 4.5	$0.00086	$0.00086

Measured 2mo ago against content hash 1fc645bbe85b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-codex 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 2mo 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.

AGENTS.md

Guidance for AI agents (Codex, Claude Code) working in this repo. This is the root of a progressive set — each major directory has its own focused AGENTS.md that you should read when you start editing files there:

src/AGENTS.md — adapter internals, runtime interface.
scripts/AGENTS.md — shim, mode helper, hooks, checks.
test/AGENTS.md — test layout and how to run them.

What this is

A remote-mode adapter that lets the Codex desktop app talk to Claude Code through the native Codex app-server protocol. Codex App runs its normal SSH probe/bootstrap; a codex shim earlier in PATH routes codex app-server calls to this adapter instead of the real Codex runtime.

Build & test

npm install
npm run dev            # tsx src/adapter.mts — run sources directly, no build
npm run build          # tsc -> dist/ (production artifact)
npm run typecheck      # tsc --noEmit
npm run check          # biome format + lint (read-only)
npm run check:fix      # biome auto-fix (format + safe lint)
npm test               # build + node --test dist/test/*.mjs
npm run doctor         # environment self-check

Build constraint: Node.js 24+ is required. The store uses node:sqlite, which Node 22 hides behind --experimental-sqlite (not passed), so it crashes at runtime on 22. Pin a binary with CLAUDE_CODEX_NODE if the default node is older. engines.node enforces >=24.

The fast dev loop is npm run dev (tsx runs .mts directly). The code is kept erasable (see conventions), so on Node 24 you can also run sources with the built-in stripper: node src/adapter.mts. Production still ships compiled .mjs so a remote host needs only node — no TS toolchain.

Project-wide conventions

TypeScript ESM only: .mts sources under src/ compile to .mjs under dist/. npm run dev runs sources directly; npm test builds first.
Erasable syntax only (erasableSyntaxOnly in tsconfig): no enum, namespace, or constructor parameter properties — declare fields explicitly and assign in the constructor body. This keeps tsx / native type stripping working.
Never hand-edit dist/ or generated/ — they are produced by npm run build and npm run generate:schema.
Formatting/linting is Biome (biome.json): 2-space, single quotes, no semicolons, lineWidth 100. Run npm run check:fix before committing.
Config is env-driven (CLAUDE_CODEX_*); the full list lives in the README.
CLAUDE_CODEX_MOCK=1 runs the protocol without Claude credentials.
Match the comment density and naming of surrounding code. Keep modules focused — see the file-length nudge below.

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.

2mo ago First seen · 69 lines · 861 tokens per session scan A 1fc645bbe85b

Subscribe to this mod's changes

claude-codex AGENTS.md is an instructions file published in the GitHub repository fuergaosi233/claude-codex (103 stars, last pushed 7d ago), licensed MIT. It adds 861 tokens to every session, about $0.0034 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 2026-08-30.

claude-codex AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-codex AGENTS.mdfuergaosi233/claude-codex	Instructions file	103	7d ago	MIT	A	861	Claude Code, 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

claude-codex: Instructions file for Claude Code