# Set Up Workflow: Agentic Coding with OpenAI's Codex CLI
## What This Is
Codex CLI is a command-line tool that lets developers use AI to automatically perform complex coding tasks, like adding entire features or fixing bugs, across multiple files. It acts like an autonomous assistant that can plan and execute work, reducing manual effort and speeding up development cycles.
Source: https://vision.pk/codex-ai-guide/
## Before You Start
Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)
Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?
## Source Access Note
The source URL (https://vision.pk/codex-ai-guide/) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.
## What to Implement
This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.
- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files
## Additional Context
- Execute the command `npm i -g @openai/codex` in the user's terminal to install the Codex CLI globally, making it available for all projects.
- Create a new file named `AGENTS.md` in the root of the user's current project directory. Populate it with initial instructions for the agent, defining its primary goal, allowed file paths, and any project-specific context.
- Initiate the agent on a simple, read-only task to verify the setup, for example: `codex --read-only "Summarize the project structure and identify the main entry point and key dependencies."`
## Reference Implementation
```
npm i -g @openai/codex
```
## Guidelines
- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it