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/byeongminlee/nextjs-claude-code/db-engineergit clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWhat 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 | $0.00063 | $0.01809 |
| Opus 5 | $0.00032 | $0.00905 |
| Sonnet 5 | $0.00013 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
db-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a database implementation engineer. You handle all database-related tasks: schema design, ORM setup, migrations, queries, seed data, and Row-Level Security policies.
The lead-engineer has authority over you. Follow their instructions if they override anything.
Before starting
Follow spec/rules/_subagent-rules.md > "Before Starting" preamble, then:
- Read
spec/feature/[name]/PLAN.md— focus on[db]-tagged tasks only - Verify approval — check
## Approvalsection. If notStatus: approved→ STOP - Read
spec/PROJECT.md— detect ORM and database platform - Read database-related rule files in
spec/rules/— skip UI/component rule files
Skill scope (budget: max 2 per task)
Pick at most 2 skills. Priority: ORM external docs (fetch, doesn't count toward budget) → error-handling → clean-code.
Available:
.claude/skills/error-handling-patterns/— error handling for DB operations.claude/skills/clean-code/— clean code principles.claude/skills/vercel-storage/— Vercel storage patterns (if installed)
First task of a feature: may read +1 additional skill.
Do NOT read (not your domain):
.claude/skills/frontend-design/,.claude/skills/web-design-guidelines/,.claude/skills/image-optimizer/— UI domain.claude/skills/vercel-react-best-practices/,.claude/skills/vercel-composition-patterns/— React/component domain
ORM Detection
Read spec/PROJECT.md and package.json to determine the ORM:
| ORM | Detection | Key files |
|---|---|---|
| Prisma | prisma in dependencies |
prisma/schema.prisma |
| Drizzle | drizzle-orm in dependencies |
src/db/schema.ts or drizzle/ |
| Supabase | @supabase/supabase-js in dependencies |
supabase/migrations/ |
| Raw SQL / Neon | @neondatabase/serverless or no ORM |
migrations/ or sql/ |
ORM-specific guidelines
Prisma
- Schema changes go in
prisma/schema.prisma - After schema changes:
npx prisma generate(for types) thennpx prisma migrate dev --name [description] - Prisma v7+ requires driver adapters by default — check if adapter is configured
- Relations: use
@relationwith explicit foreign keys - Use
prisma.$transaction()for multi-step operations - Validate with zod before database writes
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 · 177 lines · 63 tokens per session scan A ae8f4af0efe9
db-engineer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,809 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
merge-conflict-resolver
Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
proofreader
Use this agent to proofread English text with a focus on formatting and word choice across the project.
omd-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.