Plan Execute

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.

skills.sh installs: 249
GitHub stars: 81
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add longranger2/claude-gpt-workflow --skill plan-execute --agent claude-code

Installs into .claude/skills of the current project.

Files

Plan Execute Skill

Purpose

When the user runs /plan-execute {plan-file-path}, start the "orchestrated plan execution" workflow:

I (Claude Code) ask Codex to implement the code according to the plan.
After Codex finishes, I review the generated code.
I write the review into the reviews/ directory, then ask Codex to inspect and fix the issues.
Repeat until the code quality bar is met.

Core principle: I do not write or edit code myself. I only do two things: review code and orchestrate Codex. All code changes, including implementation and fixes, are performed by Codex.

Usage

/plan-execute plans/my-feature-plan.md

Session Reuse

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 implementation and fix history instead of rereading the entire codebase every time.