database-schema-designer

database-schema-designer is an agent for coding agents from Dannykkh/skill-olympus. It costs 64 tokens per session (2,972 once invoked), scanned A, original, MIT.

A database-design specialist that turns business requirements into entities, relationships, tables, database definitions, and migration plans. An ERD, or entity-relationship diagram, shows how the data entities connect.

In plain words
What is it for?
Use it to extract entities, normalise data, create an ERD, write DDL, and plan database migrations.
Why use it?
It helps turn vague business needs into an organised database structure and plan changes to that structure over time.

Agent

Part of the skill-olympus plugin — 13 skills, 2 commands, 41 agents 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/dannykkh/skill-olympus/database-schema-designer
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Or install skill-olympus, the plugin that ships this one along with the rest of its 13 skills, 2 commands, 41 agents.

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 database-schema-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dannykkh/skill-olympus/database-schema-designer.svg)](https://agentmods.dev/agents/dannykkh/skill-olympus/database-schema-designer)
Your own site
<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>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00064 $0.02972
Opus 5 $0.00032 $0.01486
Sonnet 5 $0.00013 $0.00594
Haiku 4.5 $0.00006 $0.00297

Measured 3d ago against content hash cad3f514a776, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/database-schema-designer.md · 261 lines

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:

  1. 어떤 DB? (architect/plan/인터뷰에서 결정)
  2. 그 DB의 강점을 활용해서 설계 (구조 자체가 달라짐)
  3. 해당 DB용 DDL + ERD 출력

DB 감지 순서

  1. Plan/architect 산출물에서 기술 스택 명시 확인
  2. 기존 프로젝트 → 코드베이스에서 감지 (package.json, pom.xml, .env, docker-compose)
  3. 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

Read the full file on GitHub · 261 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 · 261 lines · 64 tokens per session scan A cad3f514a776

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories