A powerful terminal-based coding assistant that integrates OpenAI Codex directly into your local development workflow for automated refactoring, debugging, and feature implementation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install codex-sub-agents
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install codex-sub-agents using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenAI Codex CLI?
The OpenAI Codex CLI is a comprehensive tool designed to bridge the gap between high-level AI reasoning and local file system execution. By leveraging Openclaw Skills, developers can delegate complex programming tasks such as fixing CI/build failures, conducting deep code reviews, and implementing features directly from the terminal. It provides a robust interface that supports both interactive TUI modes and non-interactive scripting, making it an essential addition to any modern developer's toolkit.
This skill enables a seamless integration between your local environment and the GPT-5-Codex model. Whether you are exploring a large codebase or need to match a design spec from an image, the Codex CLI offers the flexibility and power required for professional software development. By incorporating Openclaw Skills into your daily routine, you can significantly reduce the time spent on boilerplate tasks and focus on high-impact architectural decisions.
OpenAI Codex CLI Use Cases
- Automated code refactoring and technical debt reduction.
- Rapid CI/CD failure analysis and automated bug fixing.
- Comprehensive AI-driven code reviews before merging pull requests.
- Implementing new features from design specifications or image inputs.
- Local codebase exploration and documentation generation.
How OpenAI Codex CLI Works
- Initialize the environment by installing the CLI and authenticating with your OpenAI account.
- Launch the skill in either interactive mode for exploration or execution mode for specific tasks.
- The tool analyzes the local file system, leveraging its workspace access to read and modify files.
- Developers use slash commands or natural language prompts to trigger specific coding operations.
- For complex workflows, the CLI can be integrated into larger agentic systems as a specialized subagent.
OpenAI Codex CLI Setup
To get started with this professional set of Openclaw Skills, ensure you have a ChatGPT Plus or Enterprise subscription. Install the package globally and authenticate using the following commands:
npm i -g @openai/codex
codex login
Verify your authentication status using codex login status to ensure the skill is ready for use.
OpenAI Codex CLI Data Schema & Taxonomy
The skill manages sessions and configurations locally to provide a persistent development experience. Data is organized as follows:
| Component | Description |
|---|---|
~/.codex/auth.json |
Stores authentication tokens and profiles. |
~/.codex/prompts/ |
Directory for custom slash command markdown files. |
~/.codex/config.toml |
Main configuration file for features like web search. |
| Session IDs | Unique identifiers used to resume specific coding conversations. |
All Openclaw Skills within this CLI respect workspace boundaries based on the configured approval modes.
OpenAI Codex CLI Advanced Features
- Model switching between gpt-5-codex and standard gpt-5 models.
- Multi-directory support via the
--add-dirflag for monorepo management. - MCP (Model Context Protocol) integration to connect external tools like GitHub or custom documentation.
- Full-auto execution mode for autonomous workspace modifications and failure recovery.
- Image input support for design-to-code transformations.
SKILL.md
Loading
Related Openclaw Skills
safe-web: Secure Web Search and Fetching
A security-focused web fetching and search tool that shields AI models from malicious prompt injections found in live web content.
LSP Code Navigation
A multi-language LSP client that manages persistent background daemons for precise code navigation and semantic analysis.
YouTube Analytics Toolkit
A comprehensive data analysis toolkit for the YouTube Data API v3 that enables automated channel benchmarking, video performance tracking, and search results analysis.
DataForSEO Keyword Research
An automated SEO research toolkit for Openclaw Skills that leverages the DataForSEO API for keyword discovery, competitor intelligence, and SERP analysis.
Migma
A terminal-based AI email engine for designing, sending, and managing marketing campaigns and contact segments.
MoltCops
A local-first security scanner designed to detect malicious patterns and vulnerabilities in AI agent skills before installation.
Featured*
