OpenAI Codex CLI
Starter OpenAI’s terminal coding agent (2026).What's new: see Agent CLI game changers, checked against 0.166.0.
Install
bash
# npm (cross-platform) — use the scoped package
npm install -g @openai/codex
# macOS / Linux installer
curl -fsSL https://chatgpt.com/codex/install.sh | sh
# Windows PowerShell
powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex"WARNING
npm install -g codex (unscoped) is a different package. Always use @openai/codex.
bash
codex --versionFirst run
bash
cd ~/code/my-project
codexSign in with ChatGPT (subscription) or use API key auth depending on your setup.
Everyday usage
bash
# interactive
codex
# start with a prompt
codex "add unit tests for src/utils/date.ts"
# quieter / script-friendly modes exist — check `codex --help` on your versionProject guidance
Codex respects project instruction files commonly used by agents (e.g. AGENTS.md / repo docs). Keep them concise: how to build, test, and what not to touch.
WSL tip
Keep the repo under ~/…, not /mnt/c/…. Codex runs many filesystem and shell operations.
Approvals & sandbox (power user)
Codex can ask before running tools. Common approval styles (see codex --help / docs for exact flags on your version):
| Mode | Behavior |
|---|---|
untrusted | Only trusted read-ish commands without asking; escalate otherwise |
on-request | Model decides when to ask |
never | No approval prompts (CI / sandboxed automation only) |
Example config sketch (~/.codex/config.toml — fields evolve; verify against current docs):
toml
approval_policy = "on-request"
sandbox_mode = "workspace-write"
[sandbox_workspace_write]
network_access = trueSafety
- Review diffs before commit
- Prefer a dedicated branch or worktree
- Don’t paste secrets into prompts
Skills
Shared agent skills: apsolut/apsolut-skills
Official
- https://github.com/openai/codex
- ChatGPT / OpenAI Codex CLI docs