You already know how to collaborate with a coding agent. The useful first question is not “How do I prompt Codex?” It is: where does a second agent improve the system?
Use Codex as an independent reviewer of changes produced by you, Kiro, or Claude. A fresh reviewer is less likely to inherit the implementation thread’s assumptions.
Need immediate, local iteration? → CLI or IDE Need visual diffs + worktrees? → Codex app Need hosted GitHub delegation? → Codex web/cloud Need repeatable shell automation? → codex exec Need an independent check? → /review
The CLI, IDE extension, and app share Codex configuration. The app adds parallel threads and built-in worktree support; the CLI adds a terminal-native interactive flow and non-interactive codex exec. Codex web runs hosted work against connected GitHub repositories.
Keep the expanded Codex surface reference nearby when choosing where a task should run.
codex./review.This creates separation of duties: one agent implements; Codex reviews the diff without editing the worktree. Later, you can reverse the roles.
A review is useful only when a finding connects evidence to impact. Codex may sound certain about a weak concern, or cautious about a real defect. Evaluate the chain:
| Finding | Response |
|---|---|
| Concrete trigger and user-visible impact | Reproduce it, then fix or add a regression test. |
| Valid risk but no reachable trigger | Ask Codex to trace the call path and provide evidence. |
| Style preference already covered by tooling | Reject it and rely on the formatter or linter. |
| Unrelated redesign suggestion | Record separately; keep it out of the current change. |
Ask: “Show the smallest input that triggers this issue and the test that would fail before the fix.” This converts review prose into falsifiable evidence.
/review starts a dedicated local reviewer and leaves the worktree untouched./review.Codex CLI features documents local review, interactive sessions, codex exec, MCP, cloud tasks, and approval modes.