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 rules/proyecto26/projectx/nestjs-rulesgit clone --depth 1 https://github.com/proyecto26/projectxWhat 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 | $0.02117 | $0.02117 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00423 | $0.00423 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
nestjs-rules 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NestJS Backend Services Rules
Project Structure
- This is a monorepo using pnpm and Turborepo
- NestJS apps are compiled with CommonJS (required for NestJS)
- Apps:
auth,order,product - All apps use NestJS 11.x with TypeScript 5.9.x
Critical: TypeScript Imports for Dependency Injection
❌ NEVER use type imports for services
// ❌ WRONG - Type imports are erased at compile time
import type { ConfigService } from '@nestjs/config';
import type { ClientService } from '@projectx/workflows';
import { type AuthService } from '@projectx/core';
// ✅ CORRECT - Regular imports for dependency injection
import { ConfigService } from '@nestjs/config';
import { ClientService } from '@projectx/workflows';
import { AuthService } from '@projectx/core';
When to use type imports:
- ✅ For interfaces and type aliases only
- ✅ For DTOs used only in type positions
- ✅ For types that are never instantiated
When NOT to use type imports:
- ❌ For classes decorated with
@Injectable() - ❌ For services used in constructor injection
- ❌ For any class that needs to exist at runtime
- ❌ For guards, interceptors, pipes, or filters
Module Configuration
Always export services that are used in other modules
@Module({
providers: [MyService],
exports: [MyService], // ✅ Export if used elsewhere
})
ConfigModule should be global
ConfigModule.forRoot({
isGlobal: true, // ✅ Makes ConfigService available everywhere
load: [appConfig, swaggerConfig, temporalConfig],
validate: (config) => validateConfiguration(config, EnvironmentVariables),
})
Temporal Integration
All services use Temporal workflows
- Task queue configured via environment variable:
temporal.taskQueue - Workflow client accessed via
ClientServicefrom@projectx/workflows - Always check if workflow client is initialized before use
Workflow client pattern:
getWorkflowClient() {
const workflowClient = this.clientService.client?.workflow;
if (!workflowClient) {
throw new HttpException(
'The workflow client was not initialized correctly',
HttpStatus.INTERNAL_SERVER_ERROR,
);
}
return workflowClient;
}
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 · 257 lines · 2,117 tokens per session scan A 3092dd044678
nestjs-rules is a cursor rule published in the GitHub repository proyecto26/projectx (83 stars, last pushed 4mo ago), licensed MIT. It adds 2,117 tokens to every session, about $0.0106 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 cursor rules, from other repositories
ai-development
CodeSpirit AI功能开发规范 - AI表单填充、长任务处理、LLM集成.
js
CodeSpirit JavaScript 开发规范 - AMIS集成、模块模式、API请求、Token管理.
controller
CodeSpirit 控制器开发规范 - API控制器特性、路由、响应格式和操作特性.
database
CodeSpirit 数据库与 EF Core 迁移规范 - 多数据库支持、DbContext 设计、迁移命令.
dependency-injection
CodeSpirit 依赖注入规范 - Scrutor自动注册、生命周期管理.
api-design
CodeSpirit API 设计规范 - RESTful、路由、响应格式等.