It manages iterative development, architectural design, and code reviews through a persistent tmux session.
Install
mkdir -p .claude/skills/codex && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18" && unzip -o skill.zip -d .claude/skills/codex && rm skill.zipInstalls to .claude/skills/codex
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
This skill should be used when the user asks to "use codex", "ask codex", "run codex", "call codex", "codex cli", or explicitly asks to delegate work to a frontier reasoning model (e.g., "have GPT-5 review this", "get the OpenAI reasoning model to design X", "ask the high-reasoning model"). Also triggers on "continue codex" / "resume the codex session" for iterative development. Do NOT trigger when the user is merely discussing GPT-5 / OpenAI reasoning as a topic, or asking Claude itself to do complex implementation / architecture / review work without naming codex or a frontier reasoning model.Key capabilities
- →Spawn long-lived tmux coding sessions
- →Manage iterative backend architecture refinement
- →Perform complex codebase reasoning tasks
- →Resume previous reasoning sessions
How it works
Spawns a persistent tmux session to allow the AI to maintain state and perform iterative work on complex logic.
Inputs & outputs
When to use codex
- →Complex backend architecture design
- →Iterative implementation of difficult features
- →High-reasoning code reviews
- →Refactoring legacy code bases
About codex
Integrates an advanced reasoning model via a long-lived tmux session. It manages iterative development sessions, complex architecture design, and high-level code reviews.
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
When not to use it
- →Simple code snippets
- →One-off tasks requiring no iteration
- →Explicitly requested 'fire and forget' tasks
Prerequisites
Limitations
- →Requires active session management
- →Overkill for simple syntax fixes
How it compares
Enables multi-turn, stateful development sessions rather than single-prompt code generation.
Compared to similar skills
codex side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| codex (this skill) | 32 | 2mo | Review | Advanced |
| senior-fullstack | 35 | 7mo | Review | Intermediate |
| codex-claude-cursor-loop | 3 | 9mo | Review | Advanced |
| consult-codex | 2 | 2mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
senior-fullstack
davila7
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.
codex-claude-cursor-loop
bear2u
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality
consult-codex
centminmod
Compare OpenAI Codex GPT-5.2 and code-searcher responses for comprehensive dual-AI code analysis. Use when you need multiple AI perspectives on code questions.
dev
browseros-ai
Full feature development workflow. Explores codebase, designs, writes PRD, implements, reviews, fixes, and creates PR. Use with "/dev <feature description>".
software-architecture
davila7
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
architect-review
sickn33
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.