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/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/cursorrules)<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/cursorrules"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/cursorrules/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/rules/dewtech-technologies/dare-method/cursorrules"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/cursorrules.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 | $0.01667 | $0.01667 |
| Opus 5.5 | $0.00667 | $0.00667 |
| Sonnet 5.5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
cursorrules 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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regras Globais do Projeto DARE
Este arquivo define as regras e convenções globais que o Cursor deve seguir em todos os prompts. Ele é lido automaticamente pelo Cursor IDE em cada conversa.
Método DARE (Design → Architect → Review → Execute)
Este projeto segue o Método DARE para desenvolvimento com IA. O fluxo é:
- Design (Humano Define): Cria
DARE/DESIGN.mdcom requisitos. - Architect (IA Planeja): Gera
DARE/BLUEPRINT.mdcom arquitetura. - Review (Humano Valida): Aprova ou ajusta o Blueprint.
- Execute (IA Implementa): Lê
DARE/EXECUTION/task-*.mde implementa o código.
Você (a IA) é responsável pelas fases 2 e 4. O humano sempre valida antes de avançar.
Estrutura de Diretórios
projeto/
├── .cursorrules # Este arquivo
├── .cursor/
│ ├── rules/ # Skills e regras por stack
│ │ ├── skill-laravel-api.mdc
│ │ ├── skill-python-api.mdc
│ │ ├── skill-go-api.mdc
│ │ └── skill-vue-frontend.mdc
│ └── commands/ # Os 4 comandos DARE
│ ├── generate-design.md
│ ├── generate-blueprint.md
│ ├── generate-tasks.md
│ └── execute-task.md
├── DARE/
│ ├── DESIGN.md # Requisitos aprovados
│ ├── BLUEPRINT.md # Arquitetura aprovada
│ ├── TASKS.md # Visão geral das tarefas
│ └── EXECUTION/ # Especificações isoladas
│ ├── task-001.md
│ ├── task-002.md
│ └── ...
├── templates/ # Templates para documentos
├── examples/ # Exemplos de código-base
└── [resto do projeto]
Convenções Globais
Tipagem e Linguagem
- Sempre use tipagem forte (Type Hints) em todas as linguagens.
- Prefira exceções bem definidas a valores
null. - Escreva comentários explicando o porquê, não o o quê.
Tratamento de Erros
- Erros de validação devem retornar status 422 com detalhes dos campos.
- Erros de autenticação devem retornar 401.
- Erros de autorização devem retornar 403.
- Erros internos devem retornar 500 com mensagem genérica (nunca exponha detalhes internos).
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.
- 1mo ago First seen · 203 lines · 1,667 tokens per session scan A fa26b96b7acf
cursorrules is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,667 tokens to every session, about $0.0067 per session on Opus 5.5. 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
beads
This project uses Beads (bd) for issue tracking.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.