Agent
Code review specialist for branch comparisons and PR preparation. Use PROACTIVELY when: (1) Reviewing branch changes before merge, (2) Comparing current branch vs main/develop, (3) Preparing code for PR submission, (4) Analyzing diffs for security/performance issues.
Agent
Shallow scan for obvious bugs in PR changes. Agent #2 in parallel review.
Agent
Review PR changes for CLAUDE.md compliance. Agent #1 in parallel review.
Agent
Check if PR changes comply with guidance in code comments. Agent #5 in parallel review.
Agent
Verifies a single PR review comment against actual code. Returns VALID BUG or FALSE POSITIVE with evidence. Spawned by the pipeline to triage comments in parallel.
Agent
Score issue confidence to filter false positives. Uses 0-100 scale with explicit rubric.
Agent
Implements a single code fix from review feedback. Spawned by the pipeline command to fix one specific issue. Use when delegating individual fix tasks.
Agent
Review git blame and history for context on modified code. Agent #3 in parallel review.
Agent
Check previous PR comments that may apply to current changes. Agent #4 in parallel review.
Agent
Check if a PR is eligible for code review. Returns eligibility status and reason.
Agent
Analyze and triage PR feedback from AI reviewers (Copilot, Gemini). Use when: (1) PR has bot comments to review, (2) Need to separate valid issues from false positives, (3) Prioritizing code review feedback.
Agent
Generate a summary of PR changes for code review context.
Agent
Technical debt analyzer for pre-merge reviews. Use PROACTIVELY when: (1) Checking if changes introduce maintainability issues, (2) Evaluating code quality before merge, (3) Identifying refactoring opportunities in new code.
Agent
Adversarial reviewer for technical documentation. Reports only what would cause a bad architecture, design, or implementation decision. Use on PRDs, ADRs, technical specs, design docs, RFCs, and system documentation before the work is implemented or relied upon. Spawned by the adversarial-doc-review skill — always in…
Agent
Explores declared API contracts for a feature — OpenAPI, GraphQL, tRPC, protobuf, JSON Schema. Separate from endpoint code (backend-explorer covers that). Critical for multi-repo features. Opt-in primitive — invoke directly from any skill.
Agent
Explores backend/API layer for a feature. Finds models, views, serializers, endpoints, services, and database patterns. Spawned by explore-plan for parallel exploration.
Agent
Explores the configuration surface for a feature. Finds env vars, settings modules, feature flags, secrets handling, and per-environment overrides. Opt-in primitive — invoke directly from any skill.
Agent
Orchestrates execution of an approved PLAN-.md (or equivalent step list) by dispatching each step to plan-step-executor in order, accumulating carry-over notes between steps, and halting on blockers. Use AFTER a plan is approved and you want a single delegate to drive the whole feature instead of spawning…
Agent
Explores frontend/UI layer for a feature. Finds components, views, hooks, API clients, routing, and state management. Spawned by explore-plan for parallel exploration.
Agent
Explores git history and open PRs for a feature. Finds recent changes, conflicts, and historical patterns. Spawned by explore-plan for parallel exploration.