codex

Execute OpenAI Codex CLI coding tasks in local repositories.

147|11|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/CrawlScript/MMClaw --skill codex-crawlscript
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/CrawlScript/MMClaw/tree/main/mmclaw/skills/codex
Command: npx skills add https://github.com/CrawlScript/MMClaw --skill codex-crawlscript

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates coding tasks by leveraging OpenAI Codex, allowing users to write, edit, refactor, and explain code directly within their local repositories.

Core Features & Use Cases

  • AI-Assisted Coding: Generate new code, fix bugs, refactor existing code, and get explanations for code snippets.
  • Local Repository Integration: Operates directly on your project files, supporting specified working directories.
  • Foreground/Background Execution: Handles both quick tasks and long-running operations efficiently.
  • Use Case: Ask Codex to "write a Python function to calculate the factorial of a number" or "refactor the user authentication module to use JWT".

Quick Start

Use the codex skill to execute the command 'codex exec --full-auto "write a python function to reverse a string"' in the current directory.

Frequently Asked Questions about codex

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

FAQPage Schema
How do I use AI to refactor code in my local repository?

AI-assisted code refactoring executes directly within your local repository by running OpenAI Codex CLI commands. You can prompt it to modify existing files, such as asking it to refactor an authentication module to use JWT, and it will apply the changes locally.

What is the best way to generate new code functions using an AI assistant?

Generating new code functions is handled by executing AI-powered coding tasks via the OpenAI Codex CLI. You provide a natural language prompt like "write a Python function to calculate factorial" and the tool generates the requested code in your specified working directory.

Does AI code generation work with background processing for long-running tasks?

Background processing is supported for long-running coding tasks. The tool offers both foreground and background execution modes, allowing you to handle quick edits and extended operations efficiently without blocking your local environment.

Do I need to install a specific binary to run AI coding tasks locally?

You need the 'codex' binary installed and configured on your system to run AI coding tasks. This local binary requirement allows the tool to operate directly on your project files within specified working directories.

How does AI code generation handle explanations for existing code snippets?

AI code generation handles explanations by processing existing code snippets through OpenAI Codex. It analyzes the provided code within your local repository and returns a natural language explanation of its functionality.

Can I use full-auto mode for non-interactive code editing?

Non-interactive code editing is supported using the full-auto execution mode. You can run commands like 'codex exec --full-auto' with a specific prompt to apply code changes automatically without manual intervention.