OpenAI Codex is a specialized artificial intelligence system designed to translate natural language into code.

We just published a course on the freeCodeCamp.org YouTube channel that will teach you how to use Codex to accelerate real-world coding workflows and developer productivity. Andrew Brown from ExamPro developed this course.

Here are the sections in this course:

  • Introduction

  • Codex Essentials

  • The AI Certification Roadmap

  • Study Recommendations & Passing Requirements

  • Validity and Re-certification

  • Accessing the Code Repository Codeex Fundamentals

  • What is Codeex? Agentic Coding vs. Coding Harness

  • Common Use Cases and Skills

  • Understanding the Agentic Loop

  • OpenAI GPT Model Families

  • Deep Dive: Model Intelligence vs. Context Windows

  • Installation Requirements (Node.js & WSL 2)

  • Authentication: Subscription vs. API Keys

  • Checking Login Status and Account Info

  • Lab: Installing Codeex and "Hello World"

  • Using API Keys for Production and Automation

  • Setting Environment Variables for Keys

  • Subscriptions vs. API Token Billing

  • Managing the Context Window (400k Token Limits)

  • Truncation and Hallucination Issues

  • Commands: /clear and /compact

  • Lab: Managing Context History

  • Codeex Sessions, Threads, and Messages

  • Session Commands: /new, /resume, /fork, and /rename

  • Under the Hood: SQLite and JSONL Session Storage

  • Tracking Usage with Custom Scripts

  • Customizing the Status Line

  • Project Guidance via agents.md

  • Truncation Limits and Tracing

  • Lab: Creating Project Guidelines

  • Deep Dive: Plan Mode and Clarifying Questions

  • Project Lab: Building a Wolfenstein 3D Clone

  • Sandbox Security: Bubble Wrap and Seatbelt

  • Approval Policies (Untrusted, Request, Never)

  • OS-Specific Settings and Network Access

  • Permission Overrides: Auto Mode vs. Full Access

  • Creating and Troubleshooting Rules

  • Global vs. Project Configuration (config.toml) API, SDKs, and Extensions

  • Non-Interactive (Headless) Mode for CI/CD

  • OpenAI Interaction Layers: REST API vs. SDKs

  • Implementing the OpenAI Agents SDK

  • Working with the Codeex SDK

  • Using the Codeex Desktop Application

  • Installing the VS Code Extension

  • The Codeex App Server Protocol

  • Automated Workflows with GitHub Actions

  • Anatomy of Agent Skills

  • Discovery, Activation, and Execution

  • Skill Locations and Marketplace

  • Lab: Image Generation Skills

  • Project Lab: Building a Task Manager Skill

  • Optimizing Cost with Model and Effort Selection

  • Fast Mode for Inference

  • Connecting MCP Tools (Roblox Example)

  • Orchestrating Sub-Agents and Worker Teams

Watch the full course on the freeCodeCamp.org YouTube channel (5-hour watch).

/you