What is skill-codex CLAUDE.md?

Project instructions for skill-codex, a bridge that lets Claude Code ask OpenAI Codex to review code, perform tasks, or provide advice. It also describes the bridge’s commands, automatic review hook, setup, and coding conventions.

Use it when developing, reviewing, testing, or extending the skill-codex project across Windows, macOS, and Linux.

It gives contributors one agreed description of how the project works and how its code should be written and tested.

How Arystos/skill-codex configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Arystos/skill-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/Arystos/skill-codex/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Arystos/skill-codex

Made for: Claude Code.

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/arystos/skill-codex/claude-md/github.svg)](https://agentmods.dev/instructions/arystos/skill-codex/claude-md)

Your own site

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

Per session 729 This file is loaded in full into every session.

When invoked 729 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.00729	$0.00729
Opus 5.5	$0.00292	$0.00292
Sonnet 5.5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 1mo ago against content hash b6405ac5d989, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-codex CLAUDE.md scanned grade A with 1 finding 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 1mo 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.

Runs shell commandslowCapability

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

- Mock `child_process.spawn` for runner tests

CLAUDE.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-codex

Cross-platform Claude Code skill integrating OpenAI Codex CLI for code review, task delegation, and consultation.

Architecture

MCP Server (src/): One-direction bridge -- Claude Code calls Codex via codex exec CLI
Slash Commands (commands/): /codex-review, /codex-do, /codex-consult
Auto-review Hook (hooks/): PostToolUse hook with smart diff filtering
Setup CLI (setup/): npx skill-codex setup one-command installer

Key Design Decisions

Subscription-first: Works with codex login (ChatGPT Plus/Codex subscription). No OPENAI_API_KEY required.
Codex as peer, not authority: Claude critically evaluates all Codex output. Findings are suggestions, not directives.
Cross-platform: Windows (git-bash), macOS, Linux. Uses shell: false with resolved binary path + windowsHide: true on Windows.
Single MCP tool (codex_exec): Mode param controls behavior (exec vs full-auto).

Code Conventions

TypeScript strict mode, ES2022 target, Node16 modules
Immutable data patterns -- never mutate, return new objects
Small focused files: 50-150 lines typical, 400 max
Typed errors with retryable boolean on BridgeError base class
All magic numbers in src/config/constants.ts
Cross-platform paths via src/config/paths.ts and src/util/platform.ts

Testing

Framework: vitest
Target: 80%+ overall, 90%+ on runner and guards
Mock child_process.spawn for runner tests
Mock which for binary check tests
Use temp dirs for lock file tests

Build & Run

npm install
npm run build
npm test

MCP Server

The server exposes one tool: codex_exec with params:

prompt (string, required)
mode ("exec" | "full-auto", default "exec")
cwd (string, optional)
timeoutMs (number, optional)
requireGit (boolean, optional)

Environment Variables

Variable	Default	Description
`SKILL_CODEX_TIMEOUT_MS`	`600000` (10 min)	Subprocess timeout
`SKILL_CODEX_MAX_RETRIES`	`3`	Retry count for transient errors
`SKILL_CODEX_DEBUG`	--	Enable debug logging to stderr
`SKILL_CODEX_DEPTH`	`0`	Recursion depth (set automatically)
`SKILL_CODEX_WINDOWS_SANDBOX`	`unelevated`	Windows `windows.sandbox` mode; works around elevated-sandbox spawn failures (codex#24098)

Read the full file on GitHub · 70 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.

1mo ago First seen · 70 lines · 729 tokens per session scan A b6405ac5d989

Subscribe to this mod's changes

skill-codex CLAUDE.md is an instructions file published in the GitHub repository Arystos/skill-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 729 tokens to every session, about $0.0029 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code Code review ai-coding anthropic codex cross-platform

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).

microsoft/vscode · 9,649 tokens

skill-codex: Instructions file for Claude Code