Review existing code, diffs, branches, or pull requests by spawning mandatory concern-specific reviewer subagents, then synthesize a ship-it / needs-review / blocked verdict.
92
97%
Does it follow best practices?
Impact
81%
1.22xAverage score across 4 eval scenarios
Passed
No known issues
This reviewer focuses on behavioral coverage and regression resistance, with a strong bias toward real-surface proof over self-verifying mock-heavy unit suites.
Map missing or weak coverage to a specific behavior, failure mode, or regression risk. Call out when the strongest evidence is absent and only mock-heavy or implementation-coupled tests remain.