Codex CLI

Install

curl -fsSL https://chatgpt.com/codex/install.sh | sh

This is third-party code. Review the repository files before installing.

What it does

Codex CLI is a coding agent that runs on your computer via the codex command. It works with a ChatGPT plan or an API key. Beyond the terminal there are extensions for VS Code, Cursor and Windsurf and a desktop app via codex app. The repository also ships skills used in the project's own development, such as babysit-pr for watching CI and PR reviews.

Who it is for. Developers with a ChatGPT plan or OpenAI API key who want a terminal agent.

Example request

Add input validation to the signup endpoint and write tests

Limitations

Requires ChatGPT sign-in or an OpenAI API key, which needs extra setup. Installers download binaries from releases.openai.com with GitHub Releases as a fallback.

How to disable. Remove the codex binary, or the package with npm uninstall -g @openai/codex or via brew.

Security check

• The agent runs commands and edits files
• The installer downloads a binary
• Code is sent to OpenAI models

README in short

Codex CLI is OpenAI's local coding agent. The README gives install commands for macOS, Linux and Windows, plus npm and Homebrew, and links to prebuilt binaries. Signing in with a ChatGPT plan is recommended, and API keys are also supported. The project is licensed under Apache-2.0.

SKILL.md

---
name: babysit-pr
description: Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.
---

# PR Babysitter

## Objective
Babysit a PR persistently until one of these terminal outcomes occurs:

- The PR is merged or closed.
- A situation requires user help (for example CI infrastructure issues, repeated flaky failures after retry budget is exhausted, permission problems, or ambiguity that cannot be resolved safely).
- Optional handoff milestone: the PR is currently green + mergeable + review-clean. Treat this as a progress state, not a watcher stop, so late-arriving review comments are still surfaced promptly while the PR remains open.

Do not stop merely because a single snapshot returns `idle` while checks are still pending.

## Inputs
Accept any of the following:

- No PR argument: infer the PR from the current branch (`--pr auto`)
- PR number
- PR URL

## Core Workflow

1. When the user asks to "monitor"/"watch"/"babysit" a PR, start with the watcher's continuous mode (`--watch`) unless you are intentionally doing a one-shot diagnostic snapshot.
2. Run the watcher script to snapshot PR/review/CI state (or consume each streamed snapshot from `--watch`).
3. Inspect the `actions` list in the JSON response.
4. If `diagnose_ci_failure` is present, inspect failed run logs and classify the failure.
5. If the failure is likely caused by the current branch, patch code locally, commit, and push. Do not patch random flaky tests, CI infrastructure, dependency outages, runner issues, or other failures that are unrelated to the branch.

Related