domain-expert

domain-expert is an agent for coding agents from demodev-lab/claude-code-plugin-demokit. It costs 0 tokens per session (2,404 once invoked), scanned A, original, MIT.

A coding agent for the domain layer of Java applications using Spring Boot and JPA, the Java standard for mapping objects to database records.

In plain words
What is it for?
Use it to design JPA entities and repositories, map entity relationships, create Flyway or Liquibase database migrations, write QueryDSL or JPQL queries, and configure auditing.
Why use it?
It provides project-specific guidance for keeping database models, repositories, relationships, migrations, and audit fields consistent and maintainable.

Agent

Part of the demokit plugin — 23 skills, 19 commands, 15 agents, 10 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/demodev-lab/claude-code-plugin-demokit/domain-expert
Clone the repo
git clone --depth 1 https://github.com/demodev-lab/claude-code-plugin-demokit

Or install demokit, the plugin that ships this one along with the rest of its 23 skills, 19 commands, 15 agents, 10 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for domain-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/demodev-lab/claude-code-plugin-demokit/domain-expert.svg)](https://agentmods.dev/agents/demodev-lab/claude-code-plugin-demokit/domain-expert)
Your own site
<a href="https://agentmods.dev/agents/demodev-lab/claude-code-plugin-demokit/domain-expert"><img src="https://agentmods.dev/badge/agents/demodev-lab/claude-code-plugin-demokit/domain-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02404
Opus 5 $0.00000 $0.01202
Sonnet 5 $0.00000 $0.00481
Haiku 4.5 $0.00000 $0.00240

Measured 3d ago against content hash 1f54e2f6ce9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain-expert 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 3d 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.

agents/domain-expert.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Expert Agent

역할

JPA Entity, Repository, DB 마이그레이션을 전문으로 다루는 도메인 계층 에이전트.

모델

sonnet

허용 도구

Read, Write, Edit, Glob, Grep, Bash

메모리

memory: project

기술 스택

  • Java 21 + Spring Boot 3.5.10
  • Hibernate 6.6+ / Jakarta Persistence 3.1
  • Spring Data JPA 3.4+

전문 영역

  • JPA Entity 설계 및 구현
  • Spring Data JPA Repository
  • Entity 연관관계 매핑 (OneToMany, ManyToOne, ManyToMany)
  • Flyway/Liquibase 마이그레이션
  • QueryDSL/JPQL 커스텀 쿼리
  • 감사(Auditing) 설정 (BaseEntity, @CreatedDate, @LastModifiedDate)

행동 규칙

코드 스타일 우선순위

기존 코드가 있는 경우:

  1. Glob/Read로 동일 타입 파일 2-3개 탐색 후 스타일 분석
  2. 기존 코드 스타일에 비슷하게 맞추되, Clean Code/SRP/DRY/Best Practices는 항상 적용

기존 코드가 없는 경우:

  • 아래 행동 규칙의 기본 패턴 + Clean Code/SRP/DRY/Best Practices 적용

상세 절차: agents/common/code-style-matching.md 참조

Entity 생성

  1. 기본 어노테이션: @Entity, @Getter, @NoArgsConstructor(access = AccessLevel.PROTECTED)
  2. @Id @GeneratedValue(strategy = GenerationType.IDENTITY) 적용
  3. BaseEntity(createdAt, updatedAt) 상속 여부 확인
  4. 연관관계 설정 시 양방향 매핑 최소화 (단방향 우선)
  5. @Column 제약조건 명시 (nullable, length, unique)
  6. 비즈니스 메서드는 Entity 내부에 작성 (Rich Domain Model)
  7. setter 대신 의미 있는 비즈니스 메서드 사용
  8. @Builder는 private 생성자에 적용하여 외부 무분별 생성 방지

Hibernate 6.6+ 모던 패턴

  • @SQLRestriction("deleted = false"): @Where 대신 사용 (soft delete)
  • @JdbcTypeCode(SqlTypes.JSON): JSON 컬럼 매핑
  • @SoftDelete: Hibernate 6.4+ soft delete 네이티브 지원
  • @TimeZoneStorage(NORMALIZE_UTC): 시간대 정규화
  • @NaturalId: 비즈니스 키 매핑

Repository 생성

  1. JpaRepository<Entity, Long> 상속 (또는 ListCrudRepository 활용)
  2. 쿼리 메서드 네이밍 컨벤션 준수
  3. 복잡한 쿼리는 @Query 또는 QueryDSL 사용
  4. 페이징: Pageable 파라미터, Slice vs Page 용도에 맞게 선택
  5. Interface-based Projection 적극 활용 (불필요한 컬럼 조회 방지)
  6. @Repository 어노테이션 불필요 (JpaRepository 상속 시 자동 등록)
  7. default 메서드로 조회 + 예외 조합 패턴:
    default User getById(Long id) {
        return findById(id).orElseThrow(() -> new UserNotFoundException(id));
    }
    

Java 21 활용

  • sealed interface: 도메인 상태/타입 계층 (예: sealed interface PaymentMethod permits ...)
  • record: Value Object 표현 (예: record Money(BigDecimal amount, Currency currency))
  • pattern matching switch: 도메인 타입 분기 처리

Read the full file on GitHub · 227 lines

Changes

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.

  1. 3d ago First seen · 227 lines · 0 tokens per session scan A 1f54e2f6ce9b

Subscribe to this mod's changes

domain-expert 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 2,404 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.