collaborating-with-codex

Delegate coding tasks to Codex CLI and retrieve structured JSON results.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables Claude to delegate coding tasks to an OpenAI Codex CLI session so you can prototype, debug, and review code with a secondary model while your primary session remains the final authority. It solves the friction of running deterministic CLI-based code tools, capturing structured outputs, and continuing multi-turn workflows across separate agent sessions.

Core Features & Use Cases

  • Multi-turn sessions: Preserve and resume context using SESSION_ID for continued interactions.
  • Sandboxed execution: Choose between read-only, workspace-write, and danger-full-access sandboxes to limit side effects.
  • Structured JSON output: Returns success, SESSION_ID, agent_messages, and optional full traces for programmatic consumption.
  • Image and cross-platform support: Attach images to prompts and handle Windows path/escaping automatically.
  • Use Cases: Prototype algorithm implementations, generate unified diffs for changes, debug runtime errors with full trace output, or ask Codex to write unit tests and review fixes.

Quick Start

Ask the skill to run Codex CLI to analyze the authentication flow in /path/to/project and return a JSON summary including a SESSION_ID.

Frequently Asked Questions about collaborating-with-codex

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

FAQPage Schema
How do I delegate coding tasks from Claude to Codex CLI for debugging?

You can delegate coding tasks from Claude to Codex CLI by using this Skill to bridge the two models, enabling you to prototype, debug, and review code while Claude remains the final authority.

Can I preserve session context across multiple Codex CLI turns?

Yes, you can preserve and resume context across multiple Codex CLI turns using SESSION_ID, which allows for continued interactions and multi-turn workflows between separate agent sessions.

What sandbox permissions are available when running Codex CLI?

When running Codex CLI, you can choose between read-only, workspace-write, and danger-full-access sandboxes to limit side effects and control the execution environment safely.

Does the Codex CLI integration return structured output for programmatic use?

Yes, the Codex CLI integration returns structured JSON output containing success status, SESSION_ID, agent_messages, and optional full traces for direct programmatic consumption.

Can I attach images to prompts when running Codex CLI?

Yes, you can attach images to prompts when running Codex CLI, and the Skill automatically handles cross-platform support including Windows path escaping.

What should I do if Codex CLI is not found in my environment path?

If Codex CLI is not found in your environment path, you must install and configure it to be available in PATH, as this Skill requires the Codex CLI executable to function properly.