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 skills add https://github.com/longranger2/claude-gpt-workflow --skill plan-review