skill-feature-design

skill-feature-design is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 619 tokens per session, scanned A, original, MIT.

Analisa projetos existentes para planejar a adicao de novas features usando o Metodo DARE. Ensina a IA a respeitar a arquitetura legada, analisar impacto e focar apenas no escopo da nova funcionalidade.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/dewtech-technologies/dare-method/skill-feature-design
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Cursor.

Wrote 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.

agentmods badge for skill-feature-design

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-feature-design.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-feature-design)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-feature-design"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-feature-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 619 This file is loaded in full into every session.
When invoked 619 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00619 $0.00619
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured today against content hash fd682983b4d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-feature-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.

implementations/cursor/.cursor/rules/skill-feature-design.mdc · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Feature Design para Projetos Existentes

Objetivo

Esta skill ensina você (a IA) a analisar o contexto de um projeto que já existe e planejar a inserção de uma nova feature de forma segura, isolada e respeitando os padrões já estabelecidos.

Quando Usar

  • Quando o usuário pede para adicionar uma funcionalidade nova em um projeto existente.
  • Quando o comando /generate-feature-design for invocado.

Como Analisar o Projeto Existente

O primeiro passo é sempre entender o que já existe antes de propor qualquer coisa nova.

Identifique a Stack e Arquitetura: Leia os arquivos de configuração do projeto (composer.json, package.json, etc.) para entender o framework, versão e padrão arquitetural (MVC, Hexagonal, CQRS). Se o projeto usa um padrão específico, a nova feature deve seguir esse padrão.

Analise o Banco de Dados: Leia as migrations ou esquemas existentes para entender as tabelas relacionadas à feature solicitada. Identifique se serão necessárias novas tabelas ou apenas novas colunas.

Verifique Dependências Chave: Entenda quais bibliotecas de terceiros já estão em uso (ex: Sanctum para auth, Spatie para permissões) e que podem ser aproveitadas pela nova feature.

Como Gerar o Design da Feature

O documento DARE/DESIGN-Feature-[Nome].md deve ser focado e conciso. Ele não descreve o sistema inteiro, apenas o impacto da nova feature.

Seção Conteúdo
Contexto Como a feature se conecta ao que já existe
Novos Arquivos Controllers, Models, Services a serem criados
Arquivos Modificados O que muda no código legado
Banco de Dados Novas tabelas ou colunas
Segurança Proteções OWASP específicas para a feature
Restrições O que não pode ser tocado

Regras de Ouro

  1. Siga o Padrão Local: Se o projeto usa um padrão antigo ou específico, adapte a feature a ele, a menos que o usuário solicite refatoração explícita.
  2. Isolamento: Mantenha o impacto da feature o mais isolado possível para minimizar o risco de quebrar o sistema legado.
  3. Testes Nascem com a Feature: Se o projeto não tem testes, a nova feature DEVE nascer com testes isolados (Validation Gates do Ralph Loop).
  4. Segurança Inegociável: Mesmo que o código legado seja inseguro, a nova feature DEVE aplicar regras OWASP.

Read the full file on GitHub · 44 lines

Changes

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.

  1. today First seen · 44 lines · 619 tokens per session scan A fd682983b4d5

Subscribe to this mod's changes

skill-feature-design is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 619 tokens to every session, about $0.0031 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.