/ Verzeichnis / Playground / claude-gpt-workflow
← Alle Server ↗ GitHub
● Community longranger2 ⚡ Sofort

claude-gpt-workflow

von 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.

▶ Demo ansehen 📦 Installieren 💡 Anwendungsfälle

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

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

Installation

Repository des Autors · Offizielle Dokumentation zu Claude Skills

Anwendungsfälle

Praxisnahe Nutzung: claude-gpt-workflow

Stress-test a plan by having another model attack it

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

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

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

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

Fallstricke
  • Endless review loops — Cap at 3 rounds — diminishing returns after
Kombinieren mit: filesystem · git

Delegate a batch refactor to Codex with Claude reviewing

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

Wann einsetzen: A rename / signature change across 50+ files.

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

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

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

Implement a feature with iterative quality refinement

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

Wann einsetzen: A feature complex enough that a single generation won't get it right.

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

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

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

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.✓ Kopiert
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.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
Codex API tokens — potentially 2–5x a single-model workflow since both models run
Tokens pro Aufruf
High — plan + review + execute
Kosten in €
Two API subscriptions (Claude + OpenAI)
Tipp
Reserve this for risky work; don't use it for small one-file edits

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: OPENAI_API_KEY in env for Codex CLI
Datenabfluss: Code leaves your machine to both providers — check corporate policy

Fehlerbehebung

Häufige Fehler und Lösungen

ask_codex.sh: command not found

Codex CLI not on PATH or not installed

Prüfen: 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

Alternativen

claude-gpt-workflow vs. andere

AlternativeWann stattdessenKompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen