Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/demodev-lab/claude-code-plugin-demokit/optimizenpx skills add demodev-lab/claude-code-plugin-demokit --skill optimizegit clone --depth 1 https://github.com/demodev-lab/claude-code-plugin-demokitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00059 | $0.01306 |
| Opus 5 | $0.00030 | $0.00653 |
| Sonnet 5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
optimize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/optimize - 성능 최적화 분석
help
인자가 help이면 아래 도움말만 출력하고 실행을 중단한다:
/optimize — 성능 최적화 분석 및 개선
사용법:
/optimize [target] [--fix]
파라미터:
target 최적화 대상 (선택, 기본 전체)
도메인명, 파일경로, all
--fix 분석 후 자동 수정 (선택, 기본 분석만)
예시:
/optimize — 전체 분석
/optimize User — User 도메인 최적화
/optimize User --fix — User 도메인 분석 + 자동 수정
관련 명령:
/review — 코드 리뷰
/qa — 동적 품질 검증
/erd — ERD 다이어그램
심각도 기준
🔴 Critical — 즉시 수정 (N+1 쿼리, 누락 인덱스로 인한 풀스캔) 🟡 Warning — 수정 권장 (트랜잭션 범위 과다, readOnly 누락) 🟢 Info — 선택적 개선 (Projection 최적화, 페이징 개선)
실행 절차
담당 에이전트: domain-expert (코드 레벨) + dba-expert (DB 레벨, 병렬)
1단계: 프로젝트 스캔
- Entity, Repository, Service 파일 전체 수집
- application.yml JPA 설정 확인
체크포인트: [1/6 완료: 프로젝트 스캔]
병렬 분석 (Task A + Task B 동시 실행)
Task A (domain-expert):
2단계: N+1 문제 분석
다음 패턴을 탐지:
- Entity:
@OneToMany/@ManyToMany없이FetchType.LAZY미지정 - Repository:
findAll()후 연관 Entity 접근 패턴 - Service: 루프 내
findBy*호출 - QueryDSL:
fetchJoin()미사용
출력:
[N+1] User.orders — @OneToMany without FetchType.LAZY
해결: fetch = FetchType.LAZY + @BatchSize(size = 100)
또는: @EntityGraph(attributePaths = {"orders"})
체크포인트: [2/6 완료: N+1 분석]
4단계: 트랜잭션 분석
@Transactional범위 확인 (불필요하게 넓은 범위)- 읽기 전용 메서드에
@Transactional(readOnly = true)미적용 - Controller에
@Transactional사용 여부
출력:
[Transaction] UserService.getUser() — readOnly = true 누락
해결: @Transactional(readOnly = true) 추가
체크포인트: [4/6 완료: 트랜잭션 분석]
Task B (dba-expert):
3단계: 인덱스 분석
@Query/QueryDSL에서 WHERE 조건 컬럼 추출findBy*쿼리 메서드의 조건 컬럼 분석- 복합 인덱스 필요 여부 판단
출력:
[인덱스] Order.userId + Order.status — 복합 인덱스 권장
@Table(indexes = @Index(name = "idx_order_user_status", columnList = "user_id, status"))
체크포인트: [3/6 완료: 인덱스 분석]
5단계: 쿼리 최적화
SELECT *대신 필요한 컬럼만 Projection- 불필요한 Entity 전체 로드
- 페이징 없는 대량 조회
체크포인트: [5/6 완료: 쿼리 최적화]
6단계: 결과 보고서
두 Task 결과를 통합하여 보고서 생성:
## 성능 최적화 보고서
| 카테고리 | 심각도 | 건수 |
|----------|--------|------|
| N+1 문제 | 🔴 Critical | N건 |
| 인덱스 누락 | 🔴 Critical | N건 |
| 트랜잭션 범위 | 🟡 Warning | N건 |
| 쿼리 최적화 | 🟢 Info | N건 |
### 상세 내역
(각 항목별 문제-해결 방안)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 148 lines · 59 tokens per session scan A 563cabe0a558
optimize is a skill published in the GitHub repository demodev-lab/claude-code-plugin-demokit (2 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 1,306 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…