/ Directory / Playground / claude-gpt-workflow
← All servers ↗ GitHub
● Community longranger2 ⚡ Instant

claude-gpt-workflow

by longranger2 · longranger2/claude-gpt-workflow

Delegates code execution to Codex CLI while Claude orchestrates — adversarial plan review and iterative refinement between two AI models.

Three skills that split roles: Claude orchestrates strategy, Codex executes. codex delegates coding tasks to Codex CLI. /plan-review has Codex adversarially critique Claude's plan before implementation. /plan-execute runs the approved plan with back-and-forth review loops until quality passes. Three feedback loops — plan refinement, review/fix, batch execution.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Live Demo

What it looks like in practice

claude-gpt-workflow-skill.replay ▶ ready
0/0

Install

Author repository · Claude Skills documentation

Use Cases

Real-world ways to use claude-gpt-workflow

Stress-test a plan by having another model attack it

👤 Engineers doing high-stakes refactors ⏱ ~45 min intermediate

When to use: Before touching code on a migration or risky refactor, you want a second model to poke holes.

Flow
  1. Draft a plan with Claude
    Write a plan.md for migrating our auth module from JWT to session cookies.✓ Copied
    → Step-by-step plan written to plan.md
  2. Trigger adversarial review
    /plan-review plan.md✓ Copied
    → Codex returns critique with risks Claude missed
  3. Iterate until both agree
    Incorporate Codex's critique, re-submit, repeat until clean.✓ Copied
    → Plan reaches stable state

Outcome: A plan that has survived real adversarial review, not just self-grading.

Pitfalls
  • Endless review loops — Cap at 3 rounds — diminishing returns after
Combine with: filesystem · git

Delegate a batch refactor to Codex with Claude reviewing

👤 Teams doing mechanical multi-file changes ⏱ ~60 min intermediate

When to use: A rename / signature change across 50+ files.

Flow
  1. Plan and approve
    Plan + review a rename of <old> to <new> across the codebase.✓ Copied
    → Approved plan.md
  2. Execute
    /plan-execute plan.md — Codex does the edits, Claude reviews each batch.✓ Copied
    → Files change in batches, each passes Claude's review

Outcome: A clean multi-file change with two sets of eyes on every batch.

Pitfalls
  • Codex does something Claude would have rejected — The /plan-execute loop catches it — but only if quality criteria in the plan are explicit
Combine with: git

Implement a feature with iterative quality refinement

👤 Devs who've seen one-shot AI code fall over on edge cases ⏱ ~90 min advanced

When to use: A feature complex enough that a single generation won't get it right.

Flow
  1. Write plan with acceptance criteria
    Plan a feature with explicit acceptance tests, then /plan-execute.✓ Copied
    → Plan with testable criteria
  2. Watch the loop
    Let the review/fix loop run — summarize each iteration.✓ Copied
    → Iterations converge to passing criteria

Outcome: A feature that passes explicit acceptance, not just a commit that compiles.

Combinations

Pair with other MCPs for X10 leverage

claude-gpt-workflow-skill + git

Commit after each loop iteration so you can revert if the loop diverges

Before each /plan-execute iteration, create a git tag.✓ Copied
claude-gpt-workflow-skill + filesystem

Plan and critiques live in the repo

Write plan.md and review-notes.md to docs/ and keep them in git.✓ Copied

Tools

What this MCP exposes

ToolInputsWhen to callCost
ask_codex.sh request string Delegate a coding task Codex API tokens
/plan-review plan file path Before execution Codex API tokens
/plan-execute approved plan path After /plan-review passes Codex tokens per iteration

Cost & Limits

What this costs to run

API quota
Codex API tokens — potentially 2–5x a single-model workflow since both models run
Tokens per call
High — plan + review + execute
Monetary
Two API subscriptions (Claude + OpenAI)
Tip
Reserve this for risky work; don't use it for small one-file edits

Security

Permissions, secrets, blast radius

Credential storage: OPENAI_API_KEY in env for Codex CLI
Data egress: Code leaves your machine to both providers — check corporate policy

Troubleshooting

Common errors and fixes

ask_codex.sh: command not found

Codex CLI not on PATH or not installed

Verify: which codex
Plan-execute loops forever

Acceptance criteria too vague — tighten the plan or cap iterations

Models disagree and plan never stabilizes

Force a tiebreaker round with a shorter scope

Alternatives

claude-gpt-workflow vs others

AlternativeWhen to use it insteadTradeoff
Single-model Claude CodeThe task isn't risky enough to justify two-model overheadFewer adversarial signals
agent-skill-tddDiscipline comes from tests, not from another model's critiqueNo cross-model review

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills

Continue exploring

Related tools and workflows

Choose another guide for your workflow, or explore a collection.

Shared context · plan

RevenueCat AI Toolkit

Plan in-app purchase integrations and RevenueCat project workflows with official cross-platform skills and optional authenticated MCP access.

Skill

Browse all topic collections → · See 29 new official additions →