Claude Codex Duo: Evidence-Based Review, Debate, and Planning

说明与用途

Claude Codex Duo 工作流使用 OpenAI Codex 提供结构化、基于证据的代码评审、技术辩论和规划流程，包含验证步骤和最终合并建议。

问题

Developers need structured, evidence‑based code review, technical debate, and planning workflows that avoid blind agreement between models and enforce verification of findings.

结果

The workflow enables structured, evidence‑based code reviews, debates, and planning with clear audit trails, verification steps, and final merge recommendations.

工作流

• 1. Install plugins via Claude marketplace
• 2. Run /codex-pr-review on PR or local changes
• 3. Lead and Codex agents produce concurrent reviews
• 4. Join gate seals artifacts and creates reconciliation ledger
• 5. Verify P0–P3 findings with evidence (reproduction, trace, tests)
• 6. Generate final report with merge recommendation
• 7. For debate, run /codex-debate with chosen mode
• 8. Record claims, evidence grades, and final ruling
• 9. For planning, run /codex-deep-plan with request
• 10. Produce evidence‑backed plan or answer

证据

The project’s defining rule is that agreement between models does not establish whether a claim is correct.

来源

Each claim receives an ID, owner, evidence grade, and status.

来源

The workflow includes citation checks that resolve source references at the pinned commit and compare quoted text.

来源