This automates the back-and-forth of getting a design doc ready by having Codex review your plan file, then Claude applies the feedback and kicks off another round until consensus is reached. You run `/plan-review plans/my-feature.md` and it handles the loop: Codex raises at least 10 concrete issues per round (architecture, feasibility, edge cases, tech choices), Claude evaluates which suggestions are valid and revises the plan in place, then decides whether to continue based on status flags like NEEDS_REVISION or APPROVED. It tracks review history across rounds in a separate file and reuses session context so Codex remembers what was already discussed. Useful when you want your plan stress-tested before implementation without manually shuttling feedback between tools.
npx -y skills add longranger2/claude-gpt-workflow --skill plan-review --agent claude-codeInstalls into .claude/skills of the current project.
When the user runs /plan-review {plan-file-path}, start the "adversarial plan iteration" workflow:
NEEDS_REVISION, I automatically ask Codex to review again.MOSTLY_GOOD or APPROVED./plan-review plans/my-feature-plan.md
After each Codex invocation, extract session_id=xxx from the script output and save it as the session ID for the current task. In later Codex calls for the same task, pass --session <id> to reuse context so Codex remembers prior review history and can stay consistent across multiple rounds.
Derive the review file path from the plan file name:
plans/auth-refactor.md → reviews/auth-refactor-review.mdreviews/{plan-file-name-without-.md}-review.mdIf the review file already exists, this is not the first round, so Codex must track the resolution status of issues from the previous round.
Use the /codex skill and give Codex the following instruction:
Read the contents of {plan-file-path} and review it critically as an independent third-party reviewer.
Requirements:
- Raise at least 10 concrete and actionable improvement points
- Each issue must include: issue description + exact location/reference in the plan + improvement suggestion
- Use severity levels: Critical > High > Medium > Low > Suggestion
- If {review-file-path} already exists, read it first and track the resolution status of previous issues in the new round
Analysis dimensions, choosing the relevant ones based on the plan type:
- Architectural soundness: overdesign vs underdesign, module boundaries, single responsibility
- Technology choices: rationale, alternatives, compatibility with the existing project stack
- Completeness: missing scenarios, overlooked edge cases, dependency and impact scope
- Feasibility: implementation complexity, performance risks, migration and compatibility concerns
- Engineering quality: whether it follows the Code Quality Hard Limits in `CLAUDE.md`
- User experience: interaction flow, error/loading states, i18n when relevant
- Security: authentication, authorization, data validation when relevant
Append the current review round to {review-file-path}, creating the file if it does not exist.
Separate rounds with `---` and append new rounds at the end of the file. Use this format:
---
## Round {N} — {YYYY-MM-DD}
### Overall Assessment
{2-3 sentence overall assessment}
**Rating**: {X}/10
### Previous Round Tracking (R2+ only)
| # | Issue | Status | Notes |
|---|-------|--------|-------|
### Issues
#### Issue 1 ({severity}): {title}
**Location**: {location in the plan}
{issue description}
**Suggestion**: {improvement suggestion}
... (at least 10 issues)
### Positive Aspects
- ...
### Summary
{Top 3 key issues}
**Consensus Status**: NEEDS_REVISION / MOSTLY_GOOD / APPROVED
Key principle: be a critical reviewer, not a yes-man. Every issue must be specific enough that someone knows how to revise the plan.
When the review file is created for the first time, add this header at the top:
# Plan Review: {plan title}
**Plan File**: {plan-file-path}
**Reviewer**: Codex
After Codex finishes, I read the latest review round in the review file:
Use the Consensus Status provided by Codex:
| Status | My Action |
|---|---|
NEEDS_REVISION | Revise the plan, then automatically ask Codex to review again and return to Step 2 |
MOSTLY_GOOD | Revise the plan, then tell the user the plan is mostly mature and ask whether another review round is needed |
APPROVED | Tell the user the plan has passed review and is ready for implementation |
After the iteration is complete, report the following to the user:
reviews/{topic}-review.md{topic} is the plan file name without .md---plans/auth-refactor.md -> reviews/auth-refactor-review.mdcursor/plugins
github/awesome-copilot
alirezarezvani/claude-skills
microsoft/win-dev-skills