This is a structured workflow for taking a finalized plan and executing it through repeated Claude-Codex collaboration. You hand it a plan file, and Claude orchestrates while Codex does all the actual coding. Claude reviews each batch of changes, writes up issues by severity in a shared review file, then sends Codex back to fix them until the code passes. It enforces hard limits from your CLAUDE.md (800 line files, 50 line functions, 3-level nesting) and reuses Codex sessions so context carries forward. The strict division of labor is interesting: Claude never touches code, only reads and reviews. It's essentially a CI pipeline run by an AI pair, complete with build checks and multi-round iteration. Works best when you already have a detailed plan and want mechanical execution with quality gates.
npx skills add https://github.com/longranger2/claude-gpt-workflow --skill plan-execute