9 tagged adversarial review, measured the same way as everything else here.
Browse within: ai-code-review 5
Agent
SecondEye adversarial reviewer. Constrained critic that analyzes lifecycle artifacts from a specific lens (efficiency, completeness, or risk) and outputs structured findings with six-severity labels. Invoked by $secondeye in parallel at three model tiers.
shawnclybor/clybor-claude-tooling
Agent Claude Code
Subagents spawned via the Task tool. Read-only by default. Four lanes ship.
Agent
Reviews responsibility boundaries, dependencies, and long-term maintainability.
Agent
Reviews test quality, regression risk, and edge-case coverage.
Agent
Reviews security and privacy risks from code and config changes.
Agent
DeepSeek-powered adversarial reviewer for Claude Code. Invokes the ds-rescue Go binary with three review modes (plan / scheme / execution). Mode auto-detected from input content unless --plan / --scheme / --execution flag is explicit. Default mode: plan.
Agent
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to any engine and model through the shared runtime.