Use for code/PR/diff review and refactor audits. Triggers: review this, before merge, antipattern, 리뷰, 코드 리뷰, 머지 전에 확인.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Read dev first for project-wide conventions.
Class, fast path, rule authority, proof, and safety: dev. Current/public evidence: dev routing.
dev-testing owns test adequacy and QA execution. dev-debugging owns RCA;
dev-architecture owns coupling and boundary placement.
Review as a skeptical, independent outsider. Executor claims, passing tests, AI summaries, and user-facing "done" prose are untrusted until you confirm them yourself — assume the work may have failed and look for the regression or false-confidence test that proves it. Inspect artifacts before believing them; a green run you did not read is not evidence.
Tool findings go first (Automated Pre-Scan item 3); then manual findings sorted
Critical > High > Medium > Low > Style; then a dedicated blocking_issues block; verdict last.
For dispatched plan-audit (PABCD A-gate) reviews the verdict is additionally
machine-scannable: end the reply with a final line VERDICT: PASS,
VERDICT: GO-WITH-FIXES (blockers=N), or VERDICT: FAIL (mapping:
Approve -> PASS; Approve-with-suggestions -> GO-WITH-FIXES; Request-changes /
Block -> FAIL). The dispatching agent's exit rule is AUDIT-LOOP-01
(cxc-pabcd §A): FAIL always triggers another round.
Every finding carries a concrete trigger, impact, and path:line (FAMILY-CITE-01) — no
finding on a hunch. Do not file pre-existing debt unless the patch worsened it. When a change
introduces a value/type/message crossing a module boundary, trace the consumer side before
declaring it correct, rather than reviewing the emitting hunk alone.
Run a dedicated pass: what previously-working behavior can now break, and do the tests cover that surface? Flag deletion-only "fixes", tautological tests, tests that merely mirror the implementation, and scope-drift abstractions added beyond the request.
| Severity | Definition |
|---|---|
| Critical | Exploitable security flaw, data loss, or production outage |
| High | Correctness or security defect affecting users |
| Medium | Bounded defect or material maintainability risk |
| Low | Minor risk with limited impact |
| Style | Convention-only issue with no behavioral risk |
| Indicator | Verdict | Action |
|---|---|---|
| No high/critical issues | ✅ Approve | Merge |
| Only Medium/Low/Style issues | 🔧 Approve with suggestions | Fix Medium before merge unless the author explicitly marks it non-blocking with a stated reason and tracked follow-up |
| Any unresolved High issue | ⚠️ Request changes | Author must address before merge |
| Any Critical issue | 🚫 Block | Cannot merge until resolved |
Deterministic blocker semantics (REVIEW-BLOCK-01): any unresolved Critical or High blocks the merge. Medium findings should be fixed before merge. When explicitly marked non-blocking by the author with a stated reason, Medium may pass with a tracked follow-up. Style never affects the verdict.
Before writing or reviewing code smells, read common antipatterns.
| Condition | Reference |
|---|---|
| Any review: pre-scan, impact order, mindset, readiness | review-process.md |
| Classify quality signals or file-size findings | quality-thresholds.md |
| Code-smell scan (dev §6) | common-antipatterns.md |
| Every PR: security and performance quick-checks | security-performance-review.md |
| Receive/request feedback or review AI-generated code | review-feedback.md |
| Subagent review, AI evidence, slop cleanup, or boundary-guard deletion | subagent-and-slop-review.md |
| Before verdict; falsify findings, cover changed files, or re-review an interdiff | finding-verification.md |
| Current/public review proof or browser-source verification | external-review-evidence.md |
| Tech debt inventory/paydown | tech-debt.md |
| AI review tool coordination | ai-assisted-review.md |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use for AST search and codemods. Triggers: ast-grep, sg, function/call/class/import, empty catch, missing await, YAML rules.
The English summary is being prepared. Showing the original description.
Use for coding, PR delivery, scaffolding and QA. Triggers: develop, fix, refactor, test, review, docs, browse, stacked PR, 개발, 수정, 검토, 스택 PR.
The English summary is being prepared. Showing the original description.
Use for module boundaries and dependencies. Triggers: circular import, coupling, barrel, re-export, validation placement, 모듈 경계, 순환 참조.
The English summary is being prepared. Showing the original description.
Use for APIs, servers and app databases. Triggers: REST, GraphQL, migration, query optimization, middleware, caching, queues, 백엔드, API 작업, 마이그레이션, 쿼리 최적화.
The English summary is being prepared. Showing the original description.
Use for analytics and data pipelines. Triggers: ETL, ELT, data quality, SQL optimization, schema drift, backfill, 데이터 파이프라인, 데이터 품질, 백필.
The English summary is being prepared. Showing the original description.
Use for debugging and system comprehension. Triggers: debug this, root cause, how does X work, reverse engineer, 왜 안 돼, 디버깅, 원인 분석, 로직 파악, 뜯어봐.
The English summary is being prepared. Showing the original description.