skill-bugfix-design

skill-bugfix-design is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 0 tokens per session (682 once invoked), scanned A, original, MIT.

A method for diagnosing bugs in existing projects and planning small, targeted fixes. It focuses on comparing the current and expected behavior, finding the root cause, and assessing regression risk.

In plain words
What is it for?
Use it to investigate reported bugs, identify affected code and data flows, and define the smallest correction supported by logs, traces, and the codebase.
Why use it?
It helps avoid changes that only hide a symptom or create new problems elsewhere.

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-bugfix-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-bugfix-design

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-bugfix-design.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-bugfix-design)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-bugfix-design"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-bugfix-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00682
Opus 5 $0.00000 $0.00341
Sonnet 5 $0.00000 $0.00136
Haiku 4.5 $0.00000 $0.00068

Measured today against content hash a5cfb1b89072, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-bugfix-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-bugfix-design.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Bugfix Design para Projetos Existentes

Objetivo

Esta skill ensina você (a IA) a diagnosticar um bug relatado em um projeto existente, encontrar a causa raiz e planejar uma correção cirúrgica que resolva o problema sem introduzir novos erros.

Quando Usar

  • Quando o usuário relata um bug ou comportamento inesperado no sistema.
  • Quando o comando /generate-bugfix-design for invocado.

Como Diagnosticar o Bug

O diagnóstico é a etapa mais crítica. Uma correção sem diagnóstico adequado apenas esconde o sintoma.

Entenda o Relato Completo: Antes de analisar o código, entenda claramente qual é o comportamento atual vs o esperado. Se o usuário não forneceu um stack trace ou log, pergunte por ele.

Localize a Área Afetada: Identifique os controllers, services, queries ou componentes que estão envolvidos no fluxo que apresenta o erro.

Encontre a Causa Raiz: Não trate o sintoma. Descubra por que o erro acontece. As causas mais comuns são:

Tipo de Causa Exemplos
Lógica de Negócio Condição incorreta, cálculo errado
Banco de Dados Query N+1, deadlock, dados inconsistentes
Validação Input não validado, tipo incorreto
Concorrência Race condition, falta de lock
Segurança Injeção de SQL, XSS, IDOR

Como Gerar o Design do Bugfix

O documento DARE/DESIGN-Bugfix-[Nome].md deve ser cirúrgico e preciso. Ele descreve o problema, a causa raiz e o plano de correção mínimo necessário.

Seção Conteúdo
Descrição Comportamento atual vs esperado
Causa Raiz Explicação técnica do porquê ocorre
Arquivos a Modificar Lista exata de arquivos que serão alterados
Riscos O que mais pode quebrar com a correção
Plano de Ação Passos cirúrgicos da correção
Testes Validation Gates + Testes de Regressão

Regras de Ouro

  1. Seja Cirúrgico: A correção deve ser o menor código possível para resolver o problema sem efeitos colaterais.
  2. Causa Raiz: Nunca trate apenas o sintoma. Se a causa raiz não for corrigida, o bug voltará.
  3. Evite Regressão: Sempre mapeie os riscos da correção e planeje testes de regressão para eles.
  4. Adicione Testes: Se o bug ocorreu, é porque faltava um teste. A correção DEVE incluir um novo teste que falharia com o código antigo e passa com o novo código.

Read the full file on GitHub · 52 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 · 52 lines · 682 tokens per session scan A a5cfb1b89072

Subscribe to this mod's changes

skill-bugfix-design is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 682 tokens. 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.