code-fixing

Best for: multi-LLM parallel code review with structural context analysis.

Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.

Applying fixes in a loop until an independent verifier signs off on final diff.

Complex multi-phase orchestrated workflows requiring coordination across role-specialized agents.

Iterative code review when language-specific inspectors and optional specialist agents (security, perf, migration) are needed and findings must be actionable.

Perform effort-calibrated code review with bug hunting, reuse/simplification, and efficiency improvements.

Launch multiple in parallel (one per focus area), then pass all results to review-fix — depth over breadth in each area.

When re-review cycles need automation to prevent manual fix+re-check loops, with atomic history per finding

Use review-findings when you need its specific guidance

finding correctness bugs and design improvements before code review