collaborating-with-claude

Launch Claude Code via a bridge script for code design and review tasks.

425|37|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/cnfjlhj/ai-collab-playbook --skill collaborating-with-claude-cnfjlhj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: collaborating-with-claude
Source: https://github.com/cnfjlhj/ai-collab-playbook/tree/main/skills/full/collaborating-with-claude
Command: npx skills add https://github.com/cnfjlhj/ai-collab-playbook --skill collaborating-with-claude-cnfjlhj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Use Claude Code CLI as a collaborator while keeping Codex as the primary implementer.

Core Features & Use Cases

This skill provides a lightweight bridge script (scripts/claude_bridge.py) that returns structured JSON and supports multi-turn sessions via SESSION_ID.

Quick Start

Start a Claude Code collaboration session by running the bridge script in scripts/claude_bridge.py and prompt it to review a coding task, receiving a structured JSON response.

Frequently Asked Questions about collaborating-with-claude

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

FAQPage Schema
How do I use Claude Code as a review collaborator while keeping Codex as the primary implementer?

You can collaborate with Claude Code for code reviews by running a local bridge script that returns structured JSON, ensuring Codex remains the primary implementer while Claude provides design and debugging feedback.

Can I maintain multi-turn review sessions with Claude Code across different prompts?

Yes, multi-turn sessions are supported using a SESSION_ID parameter, allowing you to maintain context and continuity across multiple interactions with Claude Code for ongoing code review and design tasks.

Does the Claude Code collaboration bridge modify my source files directly?

No, the bridge script does not modify source files directly. It outputs unified diffs when requested and encourages you to verify any proposed changes locally before applying them to your codebase.

What do I need to set up before starting a Claude Code collaboration session?

You need the local bridge script located at scripts/claude_bridge.py to launch the session. This script handles the communication and returns structured JSON responses for your coding tasks.

What coding tasks are best suited for collaborating with Claude Code?

The collaboration is applicable for code debugging, evaluating design tradeoffs, and reviewing diffs, where Claude Code acts as a partner providing structured feedback while you retain implementation control.

What format does the Claude Code bridge script return for review responses?

The bridge script returns structured JSON responses, providing organized feedback that can include unified diffs for proposed changes, making it easier to parse and apply review suggestions.