$ loading_
Delegate coding tasks to Codex CLI, review diffs, and commit changes yourself.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "delegate-skills" yet — see the docs or source repo.
Use Codex CLI as a background implementation assistant: add a /health endpoint to my Node.js API following the existing style; first give an execution plan, then make the changes, and output a diff summary, potential risks, and a suggested commit message. I will decide whether to commit.
An implementation plan, code change summary, key diff notes, risk warnings, and a ready-to-use suggested commit message.
Drive Codex CLI to fix lint and type errors in this Python project, but do not commit directly; after the fixes, list the reasons for changes by file, show key diffs, and mark which edits need my manual review.
A file-by-file fix summary, key diffs, a manual review checklist, and recommendations before landing the commit.
Delegate these three small tasks to Codex CLI: 1) add installation steps to the README, 2) add unit tests for the config loader, and 3) remove unused utility functions. Report completion status, corresponding diffs, and whether they should be merged into one commit.
Completion results for each task, change summaries, diff explanations, and clear guidance on splitting or combining commits.
Delegate long-running task decisions to an OpenAI reviewer for structured next steps.
Delegate coding tasks to background AI coding agents for implementation and changes.
Validate and sync skills, agents, commands, and configs across coding CLIs.
Call Codex inside Claude Code for reviews, second opinions, and delegated coding.
Create a composable CLI from docs, specs, SDKs, apps, or scripts.
Connect Claude Code and OpenAI Codex CLI for plan-execute-review coding workflows.