What is codex-bridge CLAUDE.md?

Repository instructions for eLyiN/codex-bridge, a small server that lets Claude Code send requests to OpenAI Codex through the official command-line tool. It covers setup, development, and deployment.

Use it when developing or deploying codex-bridge, including installation, running it from source, authentication, verification, and batch or pipeline use.

It gives contributors the project context and required commands, reducing mistakes when installing, changing, or checking the bridge.

codex-bridge CLAUDE.md — Instructions file by eLyiN

Install

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.

agentmods

npx agentmods add instructions/elyin/codex-bridge/claude-md

Clone the repo

git clone --depth 1 https://github.com/eLyiN/codex-bridge

Per session 2,621 This file is loaded in full into every session.

When invoked 2,621 The same file — it is already loaded in full.

Security scan C 1 finding. Scan, not verified.

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	$0.02621	$0.02621
Opus 5	$0.01311	$0.01311
Sonnet 5	$0.00524	$0.00524
Haiku 4.5	$0.00262	$0.00262

Measured 2d ago against content hash 81ab7fd3a1f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

codex-bridge CLAUDE.md scanned grade C 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist/ build/ *.egg-info

CLAUDE.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Codex Bridge is a lightweight MCP (Model Context Protocol) server that enables Claude Code to interact with OpenAI's Codex AI through the official CLI. The project follows extreme simplicity principles from Carmack and Torvalds - doing ONE thing well: bridging Claude to Codex CLI.

Key Characteristics:

Non-interactive execution with structured output formats (text, JSON, code)
Stateless architecture with no session management
Direct subprocess integration for optimal performance
Batch processing support for CI/CD workflows
Pipeline-friendly stdin support

Development Commands

Prerequisites

Codex CLI: Install from OpenAI (official CLI)
Authentication: Setup OpenAI API credentials
Verify: codex --version

Installation & Setup

Development Mode:

# Clone and install in development mode
git clone https://github.com/shelakh/codex-bridge.git
cd codex-bridge
pip install -e .

# Run directly from source
python -m src

Production Installation:

# Install from PyPI
pip install codex-bridge

# Or use uvx (recommended)
uvx codex-bridge

Claude Code Integration:

# Production installation (recommended)
claude mcp add codex-bridge -s user -- uvx codex-bridge

# Development mode (from local source)
claude mcp add codex-bridge -s user -- python -m src

Testing & Verification

# Test CLI availability
codex --version

# Test basic functionality
python -c "from src.mcp_server import execute_codex_prompt; print('MCP server loaded successfully')"

# Test package installation
python -c "import src; print(f'Codex Bridge v{src.__version__}')"

Build & Distribution

# Clean build
rm -rf dist/ build/ *.egg-info

# Build package
uvx --from build pyproject-build

# Verify build
pip install dist/*.whl
python -c "import src; print('Package works!')"

Read the full file on GitHub · 279 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.

2d ago First seen · 279 lines · 2,621 tokens per session scan C 81ab7fd3a1f6

Subscribe to this mod's changes

codex-bridge CLAUDE.md is an instructions file published in the GitHub repository eLyiN/codex-bridge (114 stars, last pushed 1mo ago), licensed MIT. It adds 2,621 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 6,785 tokens

codex-bridge CLAUDE.md