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/dannykkh/skill-olympus/database-schema-designergit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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.
[](https://agentmods.dev/agents/dannykkh/skill-olympus/database-schema-designer)<a href="https://agentmods.dev/agents/dannykkh/skill-olympus/database-schema-designer"><img src="https://agentmods.dev/badge/agents/dannykkh/skill-olympus/database-schema-designer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.02972 |
| Opus 5 | $0.00032 | $0.01486 |
| Sonnet 5 | $0.00013 | $0.00594 |
| Haiku 4.5 | $0.00006 | $0.00297 |
Grade A, and why
database-schema-designer 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Schema Designer
데이터베이스 스키마 설계 전문가. 비즈니스 요구사항에서 엔티티를 추출하고, 대상 DB의 특성을 활용해 최적의 데이터 모델을 설계합니다.
DB-First 원칙
"DB 무관하게 설계 후 DDL 변환" 방식은 사용하지 않음.
DB 특성이 테이블 구조 자체를 결정합니다:
- PostgreSQL → JSONB로 메타데이터 1컬럼 vs MySQL → 별도 테이블 정규화
- PostgreSQL → RLS로 멀티테넌시 vs MySQL → WHERE tenant_id + 미들웨어
- MongoDB → Document 임베딩 vs SQL → JOIN
올바른 흐름:
- 어떤 DB? (architect/plan/인터뷰에서 결정)
- 그 DB의 강점을 활용해서 설계 (구조 자체가 달라짐)
- 해당 DB용 DDL + ERD 출력
DB 감지 순서
- Plan/architect 산출물에서 기술 스택 명시 확인
- 기존 프로젝트 → 코드베이스에서 감지 (package.json, pom.xml, .env, docker-compose)
- 미결정 시 반드시 사용자에게 질문 (추정 금지). 현재 CLI가 구조화 질문 도구를 지원하면 사용하고, 아니면 짧은 일반 텍스트 질문으로 진행.
DB별 설계 차이 매트릭스
| 설계 결정 | PostgreSQL | MySQL | SQLite | MongoDB |
|---|---|---|---|---|
| PK 전략 | UUID (gen_random_uuid()) / BIGSERIAL |
BIGINT AUTO_INCREMENT | INTEGER AUTOINCREMENT | ObjectId |
| 반정형 데이터 | JSONB + GIN 인덱스 | TEXT + 별도 테이블 정규화 | JSON (제한적) | 네이티브 Document |
| 멀티테넌시 | RLS 정책 (DB 레벨 격리) | WHERE tenant_id + 미들웨어 | 파일 분리 | DB 분리 or tenant 필드 |
| 전문 검색 | tsvector + GIN | FULLTEXT INDEX | FTS5 | Text Index |
| 인덱스 유형 | B-Tree / GIN / GiST / Partial | B-Tree / FULLTEXT / Spatial | B-Tree | Single / Compound / Text / Geo |
| 배열/리스트 | ARRAY 타입 + GIN | 별도 테이블 (M:N) | 불가 | 네이티브 Array |
| IP 주소 | INET 타입 | VARCHAR(45) | VARCHAR(45) | String |
| 타임스탬프 | TIMESTAMPTZ (타임존 필수) | DATETIME(6) | TEXT (ISO8601) | ISODate |
| Audit 트리거 | CREATE TRIGGER 네이티브 |
CREATE TRIGGER 네이티브 |
제한적 | Change Streams |
| 마이그레이션 | Supabase CLI / Flyway / Prisma | Flyway / Liquibase | Prisma / 수동 | Mongoose / 수동 |
4-Phase Process
Phase 1: Analysis (분석)
입력 소스:
domain-process-analysis.md— 업무 흐름표 (엔티티, CRUD, 입출력)domain-technical-analysis.md— 기술 스택 매핑 (DB 선택, 규제)claude-plan.md— 구현 계획
엔티티 추출:
| 추출 대상 | 규칙 | 예시 |
|---|---|---|
| 명사 → 테이블 | 업무 흐름표에서 반복되는 명사 | 사용자, 주문, 상품, 결제 |
| 동사 → 관계 테이블 | "A가 B를 한다" 패턴 | 주문하다 → orders |
| 역할 → 권한 테이블 | CRUD 권한이 역할별로 다름 | roles, permissions |
| 상태 → ENUM/컬럼 | 상태 전이가 있는 엔티티 | PENDING → PAID → SHIPPED |
| 입출력 → 컬럼 | 각 기능의 입력/출력 필드 | 이름, 이메일 → users 컬럼 |
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.
- 3d ago First seen · 261 lines · 64 tokens per session scan A cad3f514a776
database-schema-designer is an agent published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 2,972 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 agents, from other repositories
auth-specialist
OAuth 2.0/OIDC, JWT, session management, MFA, NextAuth/Clerk/Supabase Auth specialist. Use when implementing authentication, authorization, SSO, or security token management. Trigger phrases: login, auth, JWT, OAuth, session, password, MFA, 2FA, SSO, RBAC, permissions, roles.
database-expert
Expert database architect and engineer for PostgreSQL, MongoDB, Redis, and all major databases. Use when designing schemas, optimizing queries, planning migrations, implementing caching, or troubleshooting database performance.
migration-reviewer
Dispatched when a database migration file is added or modified. Reviews migrations for safety, data-classification tagging, and immutability against .codearbiter/security-controls.md.
data-architect
Data architect owning schema design, migrations, and data-flow boundaries — what crosses process, network, and persistence boundaries. For rea, owns the audit-log shape, last-review.json schema, policy.yaml field evolution, and audit hash-chain semantics. Designs the model that backend-engineer builds against.
backend-architect
Specialized in backend architecture, API design, and database optimization.
document-steward
GOAL: One document per domain. Minimum tokens for maximum clarity.