Agent Claude Code
Scan other repos for skills and agents worth sharing, grade them, and recommend what to import. Use when the task mentions "anything to update", "check repos", "scan for skills", "what's new", "maintain", or any request to find shareable skills/agents in other codebases.
Agent
Verify that implementation satisfies the plan's acceptance criteria and matches wireframe/design specifications. Use after completing a task (/next step 6) or before creating a PR (/pr step 3). Spawn with mode "task" for single-task review or "pr" for full-branch review.
Agent
Audit agent definitions for quality, consistency, and best practices. Use when the task mentions agent audit, agent review, agent quality, agent consistency, or checking agent definitions.
Agent
Verify that a bug fix actually resolves the defect described in BUG.md and doesn't introduce obvious regressions. Spawned by /fix-bug before PR creation as the blocking gate for bug-fix branches — the bug analogue of acceptance-reviewer for feature branches.
Agent
Audit CLAUDE.md and project documentation against the actual codebase to find drift. Use when the task mentions docs audit, convention drift, stale docs, CLAUDE.md check, or documentation accuracy.
Agent
Hunt efficiency problems in code changes — N+1 queries, missed concurrency, hot-path bloat, wasteful recomputation, missing eager-loading, and await-in-loop patterns. Spawned conditionally by /review-branch — only when the branch diff touches DB access, async code, or tight loops — in parallel with acceptance-reviewer…
Agent
Review feature plans for codebase convention violations before approval. Use when a plan has been produced by /plan-feature and needs convention checking, or when the task mentions plan review, convention check, or plan audit.
Agent
Diagnose failing CI runs OR evaluate completed implementations against plan acceptance criteria. Use when the task mentions CI, pipeline, failing checks, build failure, test failure, post-implementation review, acceptance check, or verify implementation.
Agent
Review PRs for code quality, architectural concerns, and pattern consistency. Use when the task mentions review PR, code review, check PR, or look at a pull request.
Agent
Hunt silent failures, inadequate error handling, and inappropriate fallbacks in code changes. Spawned conditionally by /review-branch — only when the branch diff contains error-handling changes — in parallel with acceptance-reviewer and simplicity-reviewer.
Agent
Verify that the implementation is the simplest shape that meets the plan — reuses existing code, follows DECISIONS.md, and avoids scope creep or dead scaffolding. Spawned by /review-branch in parallel with acceptance-reviewer against the full branch diff.
Agent
Verify that TASKS.md fully covers PLAN.md — every acceptance criterion, wireframe screen, and scope item maps to at least one task. Use after /task-writer generates or updates TASKS.md. Reports coverage gaps, unmapped criteria, and scope creep.
Agent
Verify that WIREFRAMES.md is complete, internally consistent, uses valid design tokens, references real components, and covers all screens from PLAN.md's frontend scope. Use after wireframe generation. Reports structural gaps, invalid tokens, missing screens, and component mismatches.