claude-code-bridge

Bridges Codex and Claude Code CLI for local analysis, code changes, and reviews.

1|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/oozoofrog/codex-skills --skill claude-code-bridge-oozoofrog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-code-bridge
Source: https://github.com/oozoofrog/codex-skills/tree/main/claude-code-bridge
Command: npx skills add https://github.com/oozoofrog/codex-skills --skill claude-code-bridge-oozoofrog

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Bridge Codex with the local Claude Code CLI for real analysis, implementation, and review handoffs. Use when Codex should call Claude directly from the shell to analyze a codebase, draft or apply targeted code changes, produce a second-opinion review, or compare Codex and Claude outputs in trusted local repositories.

Core Features & Use Cases

  • Enable Codex to invoke the Claude Code CLI for analysis, implementation, and review tasks without losing validation responsibility.
  • Support opt-in usage and session-based workflows to manage when Claude is used.
  • Provide references/templates for prompts and task briefs to guide interactions.

Quick Start

Opt in to Claude CLI usage and run a Codex task with claude-code-bridge to start analysis, implementation, or review.

Frequently Asked Questions about claude-code-bridge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I bridge Codex with Claude CLI for local code analysis?

You can invoke Claude CLI directly from Codex for local code analysis by applying an opt-in gating flow and session management to ensure safe, reproducible interactions.

Can I use Claude Code CLI to review code changes made by Codex?

Yes, Codex can call Claude CLI to produce second-opinion reviews or compare outputs. The bridge provides templates for task briefs to guide targeted code changes and review interactions.

When should I use a local CLI bridge for code review instead of manual checks?

Use a local CLI bridge when Codex needs to delegate analysis, implementation, or review tasks to Claude without losing validation responsibility in a trusted local repository environment.

What's the best way to manage Claude CLI sessions when integrating with Codex?

The best way is using the bridge's session management and opt-in usage gating, which controls exactly when Codex calls Claude for analysis or review to maintain reproducible interactions.

Does Claude CLI integration work in trusted local repositories?

Yes, the bridge applies specifically to codebases where Codex should call Claude CLI for analysis, implementation, or review in a trusted local environment, ensuring safe handoffs.