Codex Delegate
Claude Code skill for using Codex CLI as an execution specialist for implementation-heavy coding work, multi-file refactors, and wrapper-based execution flows.
Install
claude plugin install codex-delegate@ai-research-skillsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Codex Delegate
codex-delegate is a Claude-oriented skill for using Codex CLI as an execution specialist for implementation-heavy coding work while keeping planning, review, and acceptance in Claude.
📚 Part of the agentic AI learning roadmap — a 7-stage curated path for building agentic AI, multilingual (zh-TW · zh-CN · English). This skill is referenced in §13 (Multi-LLM Delegation).
Positioning
This skill is for tasks that are expensive in tokens but cheap in judgment:
- multi-file implementation
- mechanical refactors
- boilerplate generation
- test scaffolding
- large batch edits
It is not meant for architecture, root-cause debugging, security review, or ambiguous product decisions.
What Changed In This Version
- clearer routing boundary between Claude, Codex, and Gemini
- explicit supervisor acceptance gate
- machine-readable wrapper output via
<log>.result.json - regression tests for bash and PowerShell wrappers
Core Pattern
- Claude writes a task file describing scope and constraints.
- Claude launches Codex synchronously through the wrapper.
- The wrapper emits sentinel files plus
result.json. - Claude reviews the diff and runs verification before accepting the result.
Wrapper success is not final acceptance. Claude still owns the judgment.
Relation to openai/codex-plugin-cc
OpenAI ships an official Codex integration for Claude Code,
openai/codex-plugin-cc. It is a
capable, broker-based plugin — and a different design point from this skill.
The two are complementary; the table below is meant to help you pick, not to
rank them.
For a normal Claude Code integration, prefer the official plugin when its
runtime fits your environment. Retain this wrapper as a minimal compatibility
adapter when an existing workflow requires .ai briefs, the legacy
result.json/sentinel contract, a synchronous one-shot process, or the
PowerShell/Bash distribution. Do not add a second broker here. Neither this
wrapper nor its brief template has demonstrated better coding quality or
lower total model cost than the official plugin on matched live tasks.
| Aspect | codex-delegate (this repo) |
openai/codex-plugin-cc |
|---|---|---|
| Form | A single Claude Code skill | A multi-command plugin suite |
| Execution model | Thin synchronous wrapper: run → write result.json → exit |
Persistent broker process with background jobs |
| Job tracking | None by design — one run, one result | /codex:status, /codex:result, /codex:cancel |
| Invocation | Claude invokes the skill; the wrapper script runs Codex | Slash commands (/codex:review, /codex:rescue, …) plus a proactive subagent |
| Review gate | Claude's own acceptance gate (skills/codex-delegate/references/review-checklist.md) |
Optional Stop-hook review gate |
| Platform | bash + PowerShell wrappers, Windows-tested, no Node runtime |
Node.js 18.18+ runtime |
| Delegate routing | Claude supervisor / Codex mechanical execution guidance | Codex-focused |
| Maintainer · License | Wenyu Chiou · MIT | OpenAI · Apache-2.0 |
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.