Plan Execute
Claude orchestrates Codex CLI to implement a plan, reviews the diff, loops until it passes.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 6fefe5b
Solid orchestration template (batching, Codex delegation prompt, severity-scored review file), but it's inert without the companion `codex` skill and a locally installed, authenticated Codex CLI — this repo alone won't run.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 5/5
What Plan Execute does
Reads a finalized plan file, delegates implementation to Codex CLI in batches, then Claude does a read-only code review and writes a severity-scored review file, sending fixes back to Codex until the build is clean. Triggers on '/plan-execute <plan-file-path>', 'plan execute', 'implement plan', or 'execute plan' when a plan file is supplied.
How to install Plan Execute
git clone https://github.com/longranger2/claude-gpt-workflow
cd claude-gpt-workflow
mkdir -p ~/.claude/skills
cp -r plan-execute ~/.claude/skills/plan-execute
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Plan Execute
-
/plan-executeClaude orchestrates Codex CLI to implement a plan, reviews the diff, loops until it passes.
It also activates on plain-language prompts like these:
-
Implement this finalized plan file and review the results. -
Execute the plan in docs/plan.md and fix issues after review. -
Send this plan off to be built, then review the resulting diff.
Frequently asked questions
- Is the Plan Execute skill free?
- Yes. The skill itself is free from longranger2/claude-gpt-workflow. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Plan Execute work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Solid orchestration template (batching, Codex delegation prompt, severity-scored review file), but it's inert without the companion `codex` skill and a locally installed, authenticated Codex CLI — this repo alone won't run.
- What is the Plan Execute SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
- How do I install Plan Execute?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Plan Execute with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.