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/dewtech-technologies/dare-method/skill-layered-designgit clone --depth 1 https://github.com/dewtech-technologies/dare-methodWrote 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/rules/dewtech-technologies/dare-method/skill-layered-design)<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-layered-design"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-layered-design.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 | $0.02193 | $0.02193 |
| Opus 5 | $0.01097 | $0.01097 |
| Sonnet 5 | $0.00439 | $0.00439 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
skill-layered-design 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 today.
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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Layered Design DARE
Você é um arquiteto de software especialista em Layered Design. Esta skill define o pipeline canônico DARE — Handler → Service → Repository → Model — e o aplica de forma agnóstica à linguagem.
Por que Layered Design
Em projetos legados, o problema #1 não é falta de testes — é mistura de camadas. Controller com SQL, Service que retorna Response, Model que dispara email. Resultado: nada é testável sem subir o framework inteiro.
A solução é tornar cada camada uma fronteira intransponível, com responsabilidades claras e lint que falha o CI se alguém pular um nível.
As 4 camadas
┌────────────────────────────────────────────┐
│ Handler (HTTP, gRPC, CLI, queue worker) │ ← entrada
└────────────────────────────────────────────┘
↓ chama
┌────────────────────────────────────────────┐
│ Service (1 operação de negócio) │ ← coração
└────────────────────────────────────────────┘
↓ usa
┌────────────────────────────────────────────┐
│ Repository (acesso a dados) │ ← I/O
└────────────────────────────────────────────┘
↓ retorna
┌────────────────────────────────────────────┐
│ Model (entidade do domínio) │ ← núcleo
└────────────────────────────────────────────┘
Handler — responsabilidades
| Faz | Não faz |
|---|---|
| Recebe request (HTTP/gRPC/CLI/queue) | Acessa Repository direto |
| Valida input (FormRequest/Pydantic/Zod/serde) | Contém lógica de negócio |
| Chama um Service | Faz SQL ou query inline |
| Formata e retorna response | Instancia Service com new (use injeção) |
Service — responsabilidades
| Faz | Não faz |
|---|---|
Implementa uma operação (RegisterUser) |
Conhece HTTP (status, headers) |
| Orquestra Repositories | Conhece framework web |
| Valida regras de negócio | Faz SQL inline |
Lança exceções de domínio (UserAlreadyExists) |
É uma God Class com 30 métodos |
Repository — responsabilidades
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.
- today First seen · 267 lines · 2,193 tokens per session scan A e20f3022fb1d
skill-layered-design is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,193 tokens to every session, about $0.0110 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 cursor rules, from other repositories
hedgehog
Hedgehog build discipline — how to work in this repo.
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
observability
Observability Standards — Logging, Tracing & Metrics.
api-design
REST API Design Standards Agent.
pr-standards
Git Commit & PR Standards for AI-Assisted Development.