Codex Claude Collab

Coordinate Codex with Claude Code in real time for collaborative software work. Use when the user wants Codex to plan or review while Claude Sonnet or Opus implements, when creative/frontend/product work should be delegated to Claude, when a Codex-to-Claude handoff loop is requested, or when phrases like "notify Sonnet", "notify Opus", "Claude gets the work done", "Codex reviews", "realtime Claude Code", or "Claude Code delegation" appear.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ashinno/Codex-Claude-Collab --skill codex-claude-collab
Manual install
git clone --depth 1 https://github.com/ashinno/Codex-Claude-Collab.git /tmp/Codex-Claude-Collab
mkdir -p ~/.claude/skills
cp -r /tmp/Codex-Claude-Collab/. ~/.claude/skills/codex-claude-collab

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Codex Claude Collab

## Overview

Use this skill to run a deliberate Codex -> Claude Code -> Codex loop:

1. Codex scopes the work, writes acceptance criteria, and chooses Sonnet or Opus.
2. Claude Code performs the implementation in the shared workspace with streaming output.
3. Claude leaves a concrete completion note or transcript.
4. Codex reviews the diff, verifies behavior, and either requests follow-up work or reports the final result.

Keep Codex responsible for planning, risk control, and review. Delegate execution, exploration, and creative implementation to Claude only when the task benefits from another agent doing substantive work.

When this skill is active and the delegation decision matches, start Claude Code automatically. Do not ask the user for a separate confirmation before delegating unless the next action needs credentials, production access, destructive commands, paid external services, or a decision that cannot be inferred safely. Use Claude Code's bypass permission mode for local delegated work so Claude can read and edit the shared workspace without prompting for each tool call.

## Delegation Decision

Delegate when at least one is true:

- The user explicitly asks to use Claude Code, Sonnet, Opus, or a realtime handoff.
- The task is broad creative work such as frontend design, copy variants, product flows, visual polish, or implementation with many valid approaches.
Read the full skill on GitHub

Details

Skill name
codex-claude-collab
Repo updated
22 May 2026

FAQ

What does the Codex Claude Collab skill do?

Coordinate Codex with Claude Code in real time for collaborative software work. Use when the user wants Codex to plan or review while Claude Sonnet or Opus implements, when creative/frontend/product work should be delegated to Claude, when a Codex-to-Claude handoff loop is requested, or when phrases like "notify Sonnet", "notify Opus", "Claude gets the work done", "Codex reviews", "realtime Claude Code", or "Claude Code delegation" appear.

How do I install the Codex Claude Collab skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ashinno/Codex-Claude-Collab --skill codex-claude-collab. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Codex Claude Collab popular?

It lives in ashinno/Codex-Claude-Collab, which has 49 GitHub stars and 0 forks.

Related skills

Jev

49

PyModel/jev-judge-mcp

Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.

AI, LLMs & Agents

Claude Code MCP Setup

84

grasmash/drupal-claude-skills

Add and configure MCP (Model Context Protocol) servers in Claude Code. Use when adding new MCP servers, configuring remote MCP, setting up OAuth MCP servers, troubleshooting MCP connections, or running /mcp diagnostics. Covers stdio, HTTP, and SSE transport types.

AI, LLMs & Agents

Jev MCP

49

PyModel/jev-judge-mcp

Use before a step that judges material you already have — a claim against evidence, screening fetched text before reading it, classifying or keeping or dropping many items, finding or reranking candidates, one bounded choice, comparing two passages, grading on an ordered rubric, judging a file without reading it into your context, extracting a regex-matched value, reviewing a patch, or checking that work finished. Batch every question about one state into one call. Jev is invoked when an unresolved judgment earns a model decision. Deterministic evidence takes precedence; Jev is not a mandatory

AI, LLMs & Agents

AI News Keji

49

lovekeji-ai/keji-skills

生成 AI/科技新闻日报:从已配置的 Newsletter、RSS、可选外部来源和网站来源抓取、去重、评分并生成 Markdown。触发:用户说"生成日报 / AI日报 / 今日新闻 / 刷新日报 / fetch news / /ai-news-keji",或要求重新配置本 skill("改输出目录 / 重新配置 Newsletter / 重新选外部集成 / 更新个人偏好")。不触发:单纯"看看 BestBlogs 推荐"、"我关注的 AI builder"等请求,应交给对应的独立 skill。

AI, LLMs & Agents

Lark MCP

37

whatevertogo/FeiShuSkill

飞书/Lark 官方 MCP 集成。支持发送消息、创建群组、操作多维表格(Bitable)、导入/搜索文档、知识库查询。触发词:飞书、Feishu、Lark、多维表格、bitable、飞书文档、飞书群。

AI, LLMs & Agents

R00 Travisvn Awesome Claude Skills Datascience

50

WireTarantulaKnife/r09-travisvn-awesome-claude-skills-datascience

🤖 Data Science & AI/ML skill suite derived from travisvn/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.