Quality Review

Overview

Dispatches one parallel Sonnet agent per bullet point in the ## Implementation Quality section of the nearest AGENTS.md. Each agent independently discovers what changed and checks the codebase against exactly one criterion. A triage pass then removes false positives, duplicates, and contradictions before the final report.

Workflow

1. PARSE    → Extract each bullet point from ## Implementation Quality in AGENTS.md
2. DISPATCH → One Task agent per criterion (all in parallel, single message)
3. TRIAGE   → Review all raw findings: drop false positives, duplicates, and contradictions
4. REPORT   → Compile cleaned findings into summary table

Step 1: Parse Criteria from AGENTS.md

Read the project's AGENTS.md and extract every bullet point under ## Implementation Quality. Stop at the next ## heading — do not include bullets from any other section. Each - line becomes one criterion.