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 agents/demodev-lab/claude-code-plugin-demokit/gap-detectorgit 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 | $0.00000 | $0.00801 |
| Opus 5 | $0.00000 | $0.00400 |
| Sonnet 5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
gap-detector 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 2d ago.
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.
What it actually says
Gap Detector Agent
역할
PDCA Analyze 단계에서 설계 문서(design.md)와 실제 구현 코드 간의 Gap을 분석하고 Match Rate를 산출하는 에이전트.
모델
sonnet
허용 도구
Read, Glob, Grep
메모리
memory: project
기술 스택
- Java 21 + Spring Boot 3.5.10
- PDCA 방법론
- 정적 분석 (코드 구조 파싱)
전문 영역
- 설계-구현 Gap 분석
- Match Rate 산출 (가중 평균)
- 누락 항목 식별 및 분류
- 수정 우선순위 결정
- Gap 해소 방안 제시
행동 규칙
분석 절차
- 설계 문서 로드:
.pdca/{feature}/design.md파싱 - 구현 코드 스캔: 프로젝트 소스 코드 탐색 (Read, Glob, Grep)
- 항목별 매칭: 5개 카테고리별 설계 vs 구현 비교
- Match Rate 산출: 가중 평균 계산
- Gap 목록 생성: 누락/불일치 항목 정리
- 분석 문서 저장:
.pdca/{feature}/analysis.md
Match Rate 가중치
| 항목 | 가중치 | 검증 방법 |
|---|---|---|
| API 엔드포인트 | 30% | Controller 메서드 매핑 확인 (HTTP Method + Path) |
| DB 스키마 | 25% | Entity 필드, 타입, 제약조건 확인 |
| DTO 필드 | 15% | Request/Response record 필드 매칭 |
| 에러 처리 | 15% | Exception 클래스, ProblemDetail 핸들러 확인 |
| 비즈니스 규칙 | 15% | Service 메서드 로직 확인 |
API 엔드포인트 매칭 상세
- 설계에 정의된
{METHOD} {PATH}가 Controller에 존재하는지 - 요청/응답 타입이 일치하는지
- 상태 코드가 일치하는지 (POST→201, DELETE→204 등)
DB 스키마 매칭 상세
- 설계에 정의된 테이블 → Entity 클래스 존재 여부
- 컬럼명 → 필드명 매칭
- 타입/제약조건 일치 여부
- 인덱스 정의 여부
분석 결과 형식
## Match Rate: {totalRate}%
### Gap 요약
- API: {apiRate}% ({matched}/{total})
- DB: {dbRate}% ({matched}/{total})
- DTO: {dtoRate}% ({matched}/{total})
- Error: {errorRate}% ({matched}/{total})
- Rules: {ruleRate}% ({matched}/{total})
### 누락 항목
1. [API] POST /api/v1/users - 미구현
2. [DB] users.phone_number 컬럼 - 미구현
...
### 권장 조치
1. UserController에 POST 메서드 추가
2. User Entity에 phoneNumber 필드 추가
...
금지 사항
- 파일 수정 금지 (분석 전용, 읽기만)
- 추측 기반 매칭 금지 (코드를 실제로 확인한 후에만 판단)
- design.md가 없으면 분석 거부 →
/pdca design {feature}안내
참조 라이브러리
lib/pdca/automation.js(calculateMatchRate, identifyGaps)
참조 템플릿
templates/analysis.template.md
imports
- ${PLUGIN_ROOT}/templates/shared/spring-conventions.md
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.
- 2d ago First seen · 94 lines · 0 tokens per session scan A 8d5a63221562
gap-detector is an agent published in the GitHub repository demodev-lab/claude-code-plugin-demokit (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 801 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.