Codex logo

Codex

Organization
taracodlabs
codex

Delegate coding tasks to OpenAI Codex CLI

Overview

Publishertaracodlabs
Repositoryaiden
Skill namecodex
Stars
852
Forks
150
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by taracodlabs on GitHub. Read the source before you install it.

Installation

Install the Codex AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/taracodlabs/aiden/tree/main/skills/codex
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/taracodlabs/aiden.git /tmp/aiden
mkdir -p .claude/skills
cp -r /tmp/aiden/skills/codex .claude/skills/codex
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codex in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Codex on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Codex is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OpenAI Codex CLI Agent Bridge

Delegate code generation, editing, and explanation tasks to the OpenAI Codex CLI. Codex CLI runs GPT-4o in an agentic coding loop with sandboxed code execution.

When to Use

  • User wants to generate code using OpenAI's GPT-4o model
  • Task requires code execution in a sandboxed environment
  • User wants an alternative to Claude Code using the OpenAI API
  • User wants to benchmark or compare code generation between providers
  • Task requires OpenAI-specific features or models

How to Use

1. Install Codex CLI

powershell
# Requires Node.js 18+
npm install -g @openai/codex

# Verify
codex --version

# Set API key
$env:OPENAI_API_KEY = "sk-..."

2. Run a coding task interactively

powershell
Set-Location "C:\Users\<you>\myproject"
codex "Add input validation to all form fields in the React components"

3. Non-interactive mode

powershell
# Auto-approve all edits (use with caution)
codex --approval-mode auto-edit "Add JSDoc comments to all exported functions in src/"

# Full auto mode (applies changes without confirmation)
codex --approval-mode full-auto "Fix all ESLint errors in the project"

4. Use a specific model

powershell
# Use GPT-4o (default)
codex --model gpt-4o "Optimize the database query in src/db.js"

# Use GPT-4o-mini for faster, cheaper tasks
codex --model gpt-4o-mini "Add error handling to the fetch calls"

5. Ask a coding question without editing files

powershell
# Question mode — returns explanation only
codex --question "What does the middleware chain in src/app.ts do?"

6. Generate code from scratch

powershell
# Create a new file/module
codex "Create a TypeScript utility module with functions for:
- Formatting currency (Indian Rupee)
- Parsing date strings to Date objects
- Debouncing function calls
Save to src/utils/format.ts"

7. Explain existing code

powershell
codex "Explain what the agentLoop.ts file does, focusing on the tool execution flow"

Examples

"Generate a REST API client for the GitHub API in TypeScript" → Use step 6: codex "Create a TypeScript GitHub API client with methods for: list repos, create issue, get PR. Save to src/github-client.ts".

"Fix all TypeScript compilation errors in the project" → Use step 3 with --approval-mode auto-edit after reviewing what changes will be made.

"Explain how the authentication middleware works" → Use step 5 or 7 in question mode — returns an explanation without modifying files.

Cautions

  • --approval-mode full-auto applies all changes without confirmation — always run on a clean git branch
  • Codex CLI bills against your OpenAI API key — monitor usage at platform.openai.com/usage
  • OPENAI_API_KEY must be set in the environment before running any commands
  • Codex executes code in a sandbox but may read any files in the current directory — scope to the right project folder
  • For very large codebases, provide a focused scope (specific file or module) rather than asking it to scan the entire project

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Codex AI skill do?

Delegate coding tasks to OpenAI Codex CLI

Why use Codex on TypingMind?

Because you install it once and use it with any model. Codex is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Codex in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/taracodlabs/aiden/tree/main/skills/codex. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Codex?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Codex?

As many as you like. As long as a model supports skills, you can use Codex with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Codex AI skill free?

Yes. It is published on GitHub by taracodlabs under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇