agents

Use while implementing code changes, after a meaningful slice, to coordinate subagent review/fix/verify loops that preserve the core user or PR intent. Fix regressions, explicit requirement mismatches, validation gaps, and behavior-preserving cleanup; report unrelated improvements or out-of-intent behavior changes instead. Do not use for standalone reviews, brainstorming, or non-code iteration.

Use when transcript, commit, Sentry, GitHub, CI, review, or Garfield history suggests recurring failure patterns that might become hard deterministic checks. Analyze the evidence, reject judgment-based ideas, and output only mechanically enforceable lint, schema, CI, workflow, or deterministic test rules. Do not use for general code review, broad tool selection, or implementation unless explicitly asked.