Agent
Reviews whatever it is pointed at for correctness defects — logic errors, bad state handling, broken error paths, concurrency and lifecycle bugs. Spawned by the multi code-review skill; not meant to be called directly.
Agent
Challenges the approach behind whatever it is pointed at — whether this is the right shape of solution, what it assumes, and what it will cost to undo. Spawned by the multi code-review skill; not meant to be called directly.
Agent
Reviews whether the task actually got done — plan followed, work finished rather than finished-looking, nothing silently skipped, nothing left to detonate later. Spawned by the multi code-review skill in ultra mode; not meant to be called directly.
Agent
Reviews whatever it is pointed at for security defects — authz gaps, injection, secret handling, unsafe deserialization, data exposure. Spawned by the multi code-review skill; not meant to be called directly.
Agent
Tries to refute a single code-review finding by reading the actual code, and returns a verdict with evidence. Spawned by the multi code-review skill to check findings only one reviewer raised.