# Using OpenAI Codex CLI with GPT-5-Codex Source: https://www.youtube.com/watch?v=iqNzfK4_meQ Recap page: https://rapidrecap.app/video/iqNzfK4_meQ Generated: 2025-10-14T18:32:25.889+00:00 --- ## Quick Overview The demonstration successfully showcases using the OpenAI Codex CLI, logged in with a GPT-4 subscription, to generate a multi-player game plan and deploy the application to Vercel, proving the tool's capability for complex coding tasks like full game implementation. **Key Points:** - The presenters utilize the OpenAI Codex CLI, requiring a GPT-4 subscription, to create a plan for implementing a multiplayer feature in a game called 'Bonk'. - The CLI offers several modes including 'plan', 'status', 'approvals', 'install', and 'transcript', allowing for structured task management. - The first step involves asking Codex to 'Write a plan to implement multiplayer for the game in this repo,' which it executes by referencing existing notes and planning step-by-step. - The discussion highlights different Codex model levels (raw, medium, high, low, etc.) for balancing speed and reasoning depth, defaulting to 'auto' or 'full access' for this task. - The successful deployment to Vercel is demonstrated, allowing the two participants to play the multiplayer game in real-time, confirming the generated code worked. - The utility of the Codex CLI is emphasized for handling complex, multi-faceted coding tasks across various languages and frameworks. ![Screenshot at 00:09: The Codex CLI interface displays a prompt asking the user to select a model level, illustrating the structured, command-driven interaction developers use with the tool.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-00-09.png) **Context:** The video features two developers, one identified as Eason who led the CLI effort, discussing recent updates to the GPT-5 Codex CLI tool. They are collaborating in a modern office setting, using a laptop to interact with the command-line interface (CLI) to manage a software development task—specifically, adding multiplayer functionality to a simple, colorful 2D game displayed on the screen. ## Detailed Analysis The video demonstrates the capabilities of the OpenAI Codex CLI, which requires a GPT-4 subscription to access the more powerful models. The user initiates a complex task: creating a plan to implement a multiplayer feature for a game shown on screen. The CLI provides several commands like 'plan', 'status', 'approvals', and 'install' for workflow management. The presenter asks the CLI to generate a plan for implementing multiplayer, which it does by synthesizing existing notes into a step-by-step roadmap. The presenter also explains the different model levels available (e.g., raw, medium, high) which allow users to balance speed against reasoning quality, defaulting to 'auto' or 'full access' for complex tasks. After generating and reviewing the plan, they execute deployment steps using commands like 'codex --deploy', which successfully deploys the application to Vercel. The final outcome shows the two developers playing the newly implemented multiplayer feature of the game in real-time, confirming the CLI's effectiveness in handling complex coding instructions and deployment pipelines. ### Codex CLI Introduction & Setup - Presenters discuss recent updates to GPT-5 Codex CLI - Requires GPT-4 subscription for advanced capabilities - Demo setup involves a simple 2D game with multiplayer feature. ### CLI Commands and Workflow - Key commands include 'plan' for generating roadmaps, 'status' for checking session configuration, 'approvals' to select deployment rigor, and 'install' for execution - Model selection allows balancing speed vs. reasoning (e.g., raw, medium, high). ### Multiplayer Implementation Plan - CLI generates a step-by-step plan to implement multiplayer using DeepRL, referencing existing notes and planning necessary code changes, including handling tokens and state synchronization. ### Deployment and Verification - The team deploys the feature using the 'codex --deploy' command, which targets Vercel for deployment - Successful real-time multiplayer gameplay confirms the plan and code execution were effective. ![Screenshot at 00:05: The laptop screen showing the simple, block-based 2D game environment that the developers are attempting to add multiplayer functionality to.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-00-05.png) ![Screenshot at 00:12: A clapperboard is held up, confirming the scene is part of a formal production shoot for the video about Codex CLI.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-00-12.png) ![Screenshot at 00:41: The command line interface shows the developer typing a command, initiating the process of asking Codex to generate a plan.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-00-41.png) ![Screenshot at 01:14: The terminal output displays the detailed, multi-step implementation plan generated by Codex for adding the multiplayer feature.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-01-14.png) ![Screenshot at 02:09: The presenter gestures while discussing the 'approvals' feature of the CLI, which controls deployment security and rigor.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-02-09.png) ![Screenshot at 02:42: The multiplayer interface of the game appears on screen, showing two connected players \(indicated by two colored characters\).](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-02-42.png) ![Screenshot at 03:38: The presenter discusses using the 'codex --search' command to pull up the latest documentation versions.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-03-38.png) ![Screenshot at 04:31: The game displays the 'Multiplayer' setup screen, indicating a successful connection between the two laptops.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-04-31.png) ![Screenshot at 04:47: The game ends with a 'Bonk! Game Over' screen, concluding the successful multiplayer session.](https://ss.rapidrecap.app/screens/iqNzfK4_meQ/00-04-47.png)