Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable…
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Prepare a restartable, evidence-backed project handoff when work pauses, changes owner, reaches a review point, or needs controlled…
Use when review feedback on a proposed change needs evidence-based triage.
Handles inbound messages from Claude Code Channels (Telegram, Discord, webhooks) with session context awareness.
Inspect a code diff, branch, commit, or PR and report its concrete blast radius with minimal prose.
Choose the right Zoom architecture for a use case.
Stack-aware code review orchestrator that detects tech stacks from changed files, dispatches parallel review lanes to subagents with…
Independent senior-engineering quality auditor — architecture, ownership, domain integrity, abstraction, and maintainability.
Verify claims that work is complete, broken, missing, merged, deployed, or live by checking the relevant repository and platform evidence.
Implement ClickUp Enterprise SSO, OAuth 2.0 multi-workspace access,
Production readiness checklist for ClickUp API v2 integrations covering
Diff-first repository code review with concrete file/line findings, call-chain tracing, protocol and resource checks, Code Rot analysis…
Use when the user asks to "set up CODEOWNERS", "who should review this", "define module boundaries", "this service keeps needing changes…
Conduct high-quality, persona-driven code reviews.
Performs finding-first code reviews on diffs to detect behavioral defects, regressions, amplification risks, and impact surfaces.
Use when receiving code review requests, reviewing pull requests, evaluating implementation quality, or before merging changes.
Deploys five specialized AI agents to perform comprehensive, parallel code reviews and generate integrated quality reports.
Use when you need to evaluate CodeRabbit PR comments and fix or reply
Implement coding tasks with Codex as the only writer, then use OpenCode as a read-only reviewer and iterate on verified findings.
Use when writing or reviewing code or structured configuration.