codex-review
Have Codex independently review an existing implementation plan while Claude coordinates a bounded revision loop. For automatic reviewer selection from either host, use claudex-loop with mode=review.
- License 许可
- MIT
- 最近更新
- 2026-10-07
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- codex-review
- description
- Have Codex independently review an existing implementation plan while Claude coordinates a bounded revision loop. For automatic reviewer selection from either host, use claudex-loop with mode=review.
- disable-model-invocation
- true
03 SKILL.md 正文
Codex Review
Compatibility entry point: explicitly use Codex as the plan reviewer. The shared workflow and executable live in the sibling claudex-loop skill; install that skill alongside this one.
In Claude Code, load claudex-loop and start at mode=review, host=claude, reviewer Codex. Preserve PLAN_FILE, LOG_FILE, MAX_ROUNDS / rounds, and explicit model/effort arguments. The invocation authorizes reviewing, not implementation. Do not restart an interview when the supplied plan is already adequate.
In Codex, explain that this explicit command would use the same provider for planning and review. Use the shared claudex-loop mode=review workflow with Claude as the independent reviewer unless the user specifically requested same-provider review. If they did, perform and label that as ordinary Codex review; do not claim cross-provider approval or use the cross-provider approval runner to certify it.
Read the shared runtime reference. Resolve the runner from the installed sibling skill, not the target repository. Use the actual resolved plan path on every round and build handoff. A valid completed result and APPROVED verdict are both required; failed, empty, blocked or malformed results are not approval. The host logs findings and dispositions, and stops at the round cap.
If implementation follows, use the shared build/inspection phase. An independent plan review does not replace independent review of the final code.
04 同仓库更多 Skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment [Superpowers; user-invoked. Use to write or pressure-test a skill, e.g. product-studio changes.]
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code [product-studio: canonical Code-tab execution, entered via build-ticket; user-invoked otherwise]
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. [Python alternative to playwright-skill (canonical for scripted browser checks); user-invoked only.]
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".