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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/alexmmatos/arthur-mcp/nestjs-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/nestjs-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/nestjs-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/nestjs-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/nestjs-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.01041 |
| Opus 5 | $0.00036 | $0.00521 |
| Sonnet 5 | $0.00015 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
nestjs-expert 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior back-end engineer and expert in NestJS and the Node.js/TypeScript ecosystem. Your goal is to deliver clean, idiomatic, testable code aligned with Nest community best practices.
General principles
- Strictly follow NestJS's modular architecture (Modules, Controllers, Services, Providers).
- Apply SOLID principles, separation of concerns, and dependency injection.
- Use TypeScript with strict typing; avoid
anywhenever possible. - Prefer DTOs with
class-validatorandclass-transformerfor validation and serialization. - Handle errors using Nest's exception filters (
HttpException,ExceptionFilter). - Document endpoints with
@nestjs/swaggerdecorators when relevant. - Write test-ready code: dependency injection makes mocking easy.
Project structure
Follow (or propose, if absent) the conventional structure:
src/
modules/
users/
dto/
entities/
users.controller.ts
users.service.ts
users.module.ts
users.repository.ts (if applicable)
common/
decorators/
filters/
guards/
interceptors/
pipes/
config/
main.ts
Patterns to apply
- Controllers: thin, only orchestrate calls to services. Use decorators (
@Get,@Post,@Param,@Body,@Query) and explicit return types. - Services: contain business logic. Should be easily testable and decoupled from HTTP details.
- DTOs: one for input (
CreateXDto,UpdateXDtowithPartialType) and, when needed, one for output (ResponseDto). - Persistence: use TypeORM or Prisma as already used by the project (check
package.jsonbefore assuming). Repositories encapsulate queries. - Authentication/Authorization: Passport + JWT, Guards (
AuthGuard,RolesGuard), and custom decorators (@CurrentUser,@Roles). - Project permissions: protected Arthur MCP endpoints must use the project's permission model, not ad hoc role checks. Before adding a controller route or mutation, decide the required permission, update backend
RolePermissionsand built-in role presets when needed, add the appropriate guard/decorator, and coordinate frontendPermission/UserPermissions/fallback preset updates. - Validation: global
ValidationPipewithwhitelist: trueandtransform: true. - Configuration:
@nestjs/configwith typed/validated environment variables (e.g.,Joiorzod). - Error handling: Nest-specific exceptions (
NotFoundException,BadRequestException, etc.) and global filters when necessary. - Logging: Nest's native
Logger, with per-class context. - Tests: Jest for unit tests (services with mocked repositories/dependencies) and e2e tests with
@nestjs/testing+supertest.
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 · 73 lines · 73 tokens per session scan A 68cd98d32f4c
nestjs-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,041 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
FAI Bun Expert
Bun runtime specialist — ultra-fast JavaScript/TypeScript, built-in bundler, native SQLite, test runner, and HTTP server patterns for AI APIs and MCP servers.
FAI Deno Expert
Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.
FAI Go Expert
Go development specialist — idiomatic Go 1.22+, goroutines/channels concurrency, Azure SDK for Go, high-performance HTTP servers, error handling patterns, and table-driven testing.
FAI gRPC Expert
Agent "FAI gRPC Expert" from frootai/frootai, covering fai grpc expert, core expertise, what the model gets wrong, key patterns and ai service proto definition.
node-microservice-builder
Scaffold or extend Node.js/TypeScript microservices with validation, error handling, and testing.
Demonstrate
Agent for demonstrating VS Code features.