domains / families / software-engineering / performance-testing-review-multi-agent-review
Coordinate specialized code, security, architecture, and performance reviewers and consolidate their results. Use when a codebase needs parallel review across multiple disciplines. Review a defined code diff from relevant correctness, authorization and performance perspectives; delegate only when authorized and reproduce findings centrally.
The two copies describe the same task (coordinating a multi-perspective code review) but disagree on the core procedure. The first copy is a high-level orchestration framework that mandates dynamic agent routing, parallel/sequential execution, weighted conflict resolution, and quality-score validation. The second copy is a bounded, safety-focused procedure that explicitly forbids spawning agents without authorization, rejects weighted voting and confidence scores, and requires central reproduction of findings. Because the first copy's 'intelligent synthesis' and 'weighted scoring' directly conflict with the second copy's 'resolve disagreement through code or tests' and 'do not invent confidence scores,' crowning one would hide a real, safer alternative. The combined instruction must reconcile these by making delegation optional and prioritizing evidence-based resolution over algorithmic scoring.