{"slug": "cc-doubleteam-claude-plans-codex-executes-claude-reviews", "title": "Cc-doubleteam – Claude plans, Codex executes, Claude reviews", "summary": "Anthropic's Claude Code now integrates OpenAI's Codex CLI in a three-phase workflow where Claude plans and reviews while Codex executes tasks, burning ChatGPT usage limits instead of Claude limits. The system, available via the cc-doubleteam plugin, allows users to run `/doubleteam <task>` for automated development cycles with optional planning-only or skip-review modes.", "body_md": "Three-phase project mode for Claude Code: Claude plans, Codex executes, Claude reviews — execution burns your ChatGPT limits, not your Claude limits.\n\nYou get Fable-quality planning plus Codex execution without burning your Claude usage on the heavy lifting. The models work in sequence, each at their best effort level.\n\n- Claude Code installed\n- Codex CLI:\n`npm install -g @openai/codex`\n\nthen`codex login`\n\n(requires paid ChatGPT Plus subscription) - Codex plugin in Claude Code:\n\n```\n/plugin marketplace add openai/codex-plugin-cc\n/plugin install codex@openai-codex\ngit clone https://github.com/responsiblparty/cc-doubleteam\ncp -r cc-doubleteam/skills/doubleteam ~/.claude/skills/doubleteam\n```\n\nOptionally copy `CLAUDE.md`\n\ncontents into your project's `CLAUDE.md`\n\nto enable proactive suggestions:\n\n```\ncat cc-doubleteam/CLAUDE.md >> /path/to/your/project/CLAUDE.md\n```\n\nRestart Claude Code after install. Type `/doubleteam`\n\nto confirm it's working.\n\n`/doubleteam <task>`\n\n— starts immediately with your task`/doubleteam`\n\n— Claude asks what the task is- Claude will also proactively suggest it when a session is heading into a substantial build\n\n| Phase | Model | Effort | Role |\n|---|---|---|---|\n| 1 — Plan | Claude Fable (fallback: Opus) | high | Produces step-by-step implementation plan; pauses for your approval |\n| 2 — Execute | Codex | xhigh | Implements the plan; burns ChatGPT limits, not Claude limits |\n| 3 — Review | Claude Fable (fallback: Opus) | max | Reviews output against plan; flags issues without rewriting |\n\n`just plan`\n\n→ Phase 1 only`skip review`\n\n→ Phases 1 and 2 only- If Codex is unavailable → falls back to Claude execution (noted in output)\n\nMIT", "url": "https://wpnews.pro/news/cc-doubleteam-claude-plans-codex-executes-claude-reviews", "canonical_source": "https://github.com/responsiblparty/cc-doubleteam", "published_at": "2026-06-11 21:33:42+00:00", "updated_at": "2026-06-11 21:49:46.641485+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "large-language-models", "generative-ai", "ai-products"], "entities": ["Claude", "Codex", "OpenAI", "ChatGPT", "Fable", "Opus", "Claude Code", "Codex CLI"], "alternates": {"html": "https://wpnews.pro/news/cc-doubleteam-claude-plans-codex-executes-claude-reviews", "markdown": "https://wpnews.pro/news/cc-doubleteam-claude-plans-codex-executes-claude-reviews.md", "text": "https://wpnews.pro/news/cc-doubleteam-claude-plans-codex-executes-claude-reviews.txt", "jsonld": "https://wpnews.pro/news/cc-doubleteam-claude-plans-codex-executes-claude-reviews.jsonld"}}