Codex Delegate plugin

---
name: codex-delegate
description: Delegates implementation-heavy or repetitive coding work (batch edits, boilerplate, multi-file refactors with clear patterns, test scaffolding) from Claude to OpenAI Codex CLI. Use when token cost outweighs judgment cost. Trigger phrases include "delegate to codex", "let codex do this", "batch refactor across files", "scaffold tests for". Avoid for architecture, security review, or root-cause debugging.
license: MIT
compatibility: Designed for Claude Code. Marketplace plugins use ${CLAUDE_PLUGIN_ROOT}/scripts/run_codex.sh; direct agentskills.io-compatible installations bundle scripts under <skill-root>/scripts/. Resolve paths for the installed host rather than assuming a user skills directory.
---

# Codex Delegate Skill

Claude is the supervisor. Codex CLI runs the mechanical work. Claude plans, constrains scope, reviews the diff, and verifies outcomes.

## Why use this instead of raw `codex exec`

Use this as a minimal adapter when the supervising workflow needs its legacy
sidecar/sentinel contract and on-disk brief convention. Native `codex exec
--json` already provides machine-readable events, and the official
[`openai/codex-plugin-cc`](https://github.com/openai/codex-plugin-cc) supplies
Claude Code delegation, job tracking, and resume. Prefer those facilities when
they satisfy the workflow; do not build another broker in this wrapper.

| What the wrapper handles | What raw `codex exec` costs you |
|---|---|
| **stdin closure** (`</dev/null`) | A direct caller must close stdin or use the CLI's intended prompt-input mode. A historical session hit a 25-minute zero-byte hang on 2026-05-14. This is not an exclusive wrapper capability. |
| **Legacy `.result.json` / sentinel contract** | A caller using native `--json` events must adapt them if a downstream consumer expects these sidecars. `risks` and `tests_run` remain empty placeholders until supervisor acceptance. |
| **Brief convention** (`references/task-template.md`) | Both direct Codex and the official plugin can receive the same scoped brief. The wrapper validates a brief path; it does not prevent drift or enforce allowed paths. Historical F11/F12 incidents motivate independent scope review. |

No matched live comparison has established superior coding quality or total
model-token savings for this wrapper versus the official plugin. The ratios
below compare delegation with an estimated Claude-inline control, not with
native Codex or the official plugin.

### Token-saving ratios (directional dogfood data — measured treatment, ESTIMATED control)

From a 6-round mixed-workload session (`awesome-agentic-ai-zh` 2026-05-14, see `agent-collab-skills/docs/measured-benefits.md`). Honest methodology note (per that doc's own words): the delegated arm was measured (bytes/3 proxy), the Claude-inline control arm was "estimated, not measured, because we didn't run the control condition" — treat every ratio below as directional, not a precise multiplier. The 17-22× row was additionally produced on the since-retired gemini lane (R4 of that session) and has not been re-measured on Codex.

| Workload | Saving vs Claude-inline | When it applies to you |
|---|---|---|
| **Mechanical sweep × 2 parallel** (e.g., term replacement, § strip, doc renumber) | **~7× token reduction** + caught 4 drift files | Repo with > 20 files needing the same edit |
| **Mirror sync** (zh-TW → zh-Hans + en, 8 files) | **17-22× token reduction** | Multi-locale docs / curricula |
| **Multi-file rename / typed-API migration** | ~3× (extrapolated from Phase D title-sweep) | > 10 files following one pattern |
| **Single-file < 50 line fix** | **~1× (don't bother)** | Use Claude direct Edit |
| **Architecture / debugging / security review** | **1× (skill cannot help)** | Claude direct |

The wrapper helps for **token-heavy mechanical work**. It does not help for judgment-heavy work — be honest about which one your task is.