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 instructions/hmake98/nestjs-starter/claude-mdgit clone --depth 1 https://github.com/hmake98/nestjs-starterWrote 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/instructions/hmake98/nestjs-starter/claude-md)<a href="https://agentmods.dev/instructions/hmake98/nestjs-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/hmake98/nestjs-starter/claude-md.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 5.1 | $0.06232 | $0.06232 |
| Opus 5 | $0.03116 | $0.03116 |
| Sonnet 5 | $0.01246 | $0.01246 |
| Haiku 4.5 | $0.00623 | $0.00623 |
Grade A, and why
nestjs-starter CLAUDE.md 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 6d 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 — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file gives Claude Code complete context to work in this repository without scanning source files each session.
Stack
NestJS 11 · Prisma 7 + @prisma/adapter-pg (pg Pool, no Prisma binary engine) · PostgreSQL · Redis (ioredis via CacheService) · BullMQ · JWT (passport-jwt, argon2) · nestjs-pino · nestjs-i18n · Sentry · Swagger (non-production only) · TypeScript 6 · Node ≥20
Commands
npm run dev # nest start --watch
npm run build # nest build → dist/
npm start # node dist/main
npm test # jest --coverage --runInBand --forceExit
npm run lint:fix # eslint --fix
npm run format # prettier --write
npm run db:generate # prisma generate --config prisma/prisma.config.ts
npm run db:migrate # prisma migrate dev
npm run db:migrate-prod # prisma migrate deploy
npm run seed:admin # npm run cli -- seed:admin
npm run remove:admin # npm run cli -- remove:admin
Directory Structure
src/
├── app/
│ ├── app.module.ts ← root module (see Module Wiring below)
│ ├── controllers/
│ │ └── health.controller.ts
│ └── enums/
│ └── app.enum.ts ← APP_ENVIRONMENT enum
├── common/
│ ├── common.module.ts ← imports ConfigModule + all infra; exports DatabaseModule, CacheModule
│ ├── config/ ← registerAs() factories; never import elsewhere directly
│ │ ├── index.ts ← barrel: [AppConfig, AuthConfig, DocConfig, RedisConfig, SeedConfig]
│ │ ├── app.config.ts ← 'app.*' keys
│ │ ├── auth.config.ts ← 'auth.accessToken.*' / 'auth.refreshToken.*' keys
│ │ ├── doc.config.ts ← 'doc.*' keys
│ │ ├── redis.config.ts ← 'redis.*' keys
│ │ └── seed.config.ts ← 'seed.admin.*' keys
│ ├── bullmq/ ← BullMqModule (shared Redis connection)
│ ├── cache/
│ │ ├── cache.module.ts
│ │ ├── constants/cache.constant.ts ← REDIS_CLIENT token
│ │ └── services/cache.service.ts ← CacheService (ioredis wrapper)
│ ├── database/
│ │ ├── database.module.ts ← provides + exports DatabaseService, UserRepository
│ │ ├── services/database.service.ts ← PrismaClient via PrismaPg adapter
│ │ ├── repositories/user.repository.ts
│ │ ├── interfaces/user.interface.ts ← UserEntity, CreateUserInput, UpdateUserInput
│ │ └── enums/role.enum.ts ← re-exports Prisma Role as UserRole
│ ├── doc/
│ │ └── decorators/
│ │ ├── doc.api-endpoint.decorator.ts ← @ApiEndpoint (THE decorator for all methods)
│ │ ├── doc.response.decorator.ts
│ │ ├── doc.generic.decorator.ts
│ │ └── doc.paginated.decorator.ts
│ ├── logger/
│ │ └── services/logger.service.ts
│ ├── message/
│ │ └── services/message.service.ts ← i18n resolution
│ ├── request/
│ │ ├── request.module.ts ← registers 3 APP_GUARDs
│ │ ├── constants/request.constant.ts ← PUBLIC_ROUTE_KEY, ROLES_KEY
│ │ ├── decorators/
│ │ │ ├── auth-user.decorator.ts ← @AuthUser()
│ │ │ ├── public.decorator.ts ← @PublicRoute()
│ │ │ └── roles.decorator.ts ← @AllowedRoles([...])
│ │ ├── guards/
│ │ │ ├── jwt-access.guard.ts
│ │ │ ├── jwt-refresh.guard.ts ← used only on refresh endpoint
│ │ │ └── roles.guard.ts
│ │ └── interfaces/request.interface.ts ← IAuthUser, IRequest
│ └── response/
│ ├── response.module.ts
│ ├── dtos/
│ │ ├── response.success.dto.ts ← ApiSuccessResponseDto<T>
│ │ ├── response.generic.dto.ts ← ApiGenericResponseDto
│ │ ├── response.paginated.dto.ts
│ │ └── response.error.dto.ts
│ ├── filters/response.exception.filter.ts
│ ├── interceptors/response.interceptor.ts
│ └── services/
│ ├── response.serializer.service.ts
│ └── response.sentry.service.ts
├── modules/
│ ├── auth/
│ │ ├── auth.module.ts
│ │ ├── controllers/auth.public.controller.ts
│ │ ├── dtos/
│ │ │ ├── auth.login.dto.ts ← UserLoginDto
│ │ │ ├── auth.signup.dto.ts ← UserCreateDto extends UserLoginDto
│ │ │ └── auth.response.dto.ts ← TokenDto, AuthResponseDto, AuthRefreshResponseDto
│ │ ├── providers/
│ │ │ ├── jwt-access.strategy.ts
│ │ │ └── jwt-refresh.strategy.ts
│ │ └── services/auth.service.ts
│ └── user/
│ ├── user.module.ts
│ ├── controllers/
│ │ ├── user.public.controller.ts ← GET /v1/user/profile, PUT /v1/user
│ │ └── user.admin.controller.ts ← DELETE /v1/admin/user/:id
│ ├── dtos/
│ │ ├── user.dto.ts ← UserResponseDto, UserGetProfileResponseDto, UserUpdateProfileResponseDto
│ │ └── user.update.dto.ts ← UserUpdateDto
│ └── services/user.service.ts
├── workers/
│ ├── worker.module.ts
│ └── schedulers/midnight.scheduler.ts
└── migration/
├── migration.module.ts
└── seeds/user.seed.ts
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.
- 6d ago First seen · 588 lines · 6,232 tokens per session scan A 00a98ec20272
nestjs-starter CLAUDE.md is an instructions file published in the GitHub repository hmake98/nestjs-starter (61 stars, last pushed 3mo ago), licensed MIT. It adds 6,232 tokens to every session, about $0.0312 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 2026-08-30.
Other instructions, from other repositories
StateCore CLAUDE.md
Claude Code instructions for yul761/StateCore, covering statecore — claude context, what this is, commands, running locally and enable semantic retrieval (optional).
ai-website-cloner-template copilot-instructions.md
Instructions for JCodesMore/ai-website-cloner-template, covering this is not the next.js you know, website reverse-engineer template, what this is, tech stack and commands.
ai-website-cloner-template AGENTS.md
Instructions for JCodesMore/ai-website-cloner-template, covering this is not the next.js you know, website reverse-engineer template, what this is, tech stack and commands.
agent-skills-standard CLAUDE.md
Claude Code instructions for HoangNguyen0403/agent-skills-standard, covering agent protocol and self-learning protocol.
toBeBetterJavaer AGENTS.md
AGENTS.md instructions for itwanger/toBeBetterJavaer, covering 工具权限设置, 工具使用规则, 获取网页内容, 图片生成 / 文章配图 and 回复风格偏好.
nextarter-tailwind AGENTS.md
AGENTS.md instructions for agustinusnathaniel/nextarter-tailwind, covering next.js: always read docs before coding, ai agent guidance: nextarter-tailwind, 1. mental model for agents, implementation delegation and tooling strategy.