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-dnagit 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-dna)<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-dna"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-dna.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 | $0.00000 | $0.00889 |
| Opus 5 | $0.00000 | $0.00445 |
| Sonnet 5 | $0.00000 | $0.00178 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
skill-dna 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: DNA — Convenções do Projeto (brownfield)
Camada semântica da extração de DNA. Roda depois do comando dare dna, que já varreu o código
e extraiu os fatos de convenção. Sua função é transformar fatos em regras acionáveis — o "como esse
codebase faz as coisas" que uma nova feature deve respeitar.
Pré-requisito: rodar
dare dnaantes (geraDARE/PROJECT-DNA.mdeDARE/dna-facts.json). Se não existirem, peça para rodardare dnaprimeiro.
Quando usar
- Projeto legado que vai adotar o DARE para novas features, sem reescrever o existente.
- Acabou de rodar
dare dnae oPROJECT-DNA.mdtem seções<!-- AGENT -->em aberto.
O que fazer
1. Carregar os fatos (não re-varrer tudo)
- Leia
DARE/dna-facts.json— fonte determinística (tooling, naming, camadas, testes, libs, commits). - Abra 2-5 arquivos representativos por camada (controller, service, model, teste) para inferir o que o CLI não detecta (tratamento de erro, validação, estilo de teste).
2. Preencher DARE/PROJECT-DNA.md
Substitua cada <!-- AGENT: ... -->:
- Convenções de Nomenclatura — confirme o estilo + exceções.
- Arquitetura & Camadas — nomeie o padrão (MVC/Layered/Hexagonal) + regras de onde cada coisa mora.
- Padrões de Teste — onde ficam, naming, assertions reais, mocks/fixtures.
- Tratamento de Erros & Validação — como erros são tratados e inputs validados (exemplos reais).
- Regras de Ouro — o que SEMPRE e NUNCA fazer neste codebase.
- ⚠️ Incertezas — convenções ambíguas que o humano precisa decidir.
Não toque nos fatos determinísticos do CLI (tooling, tabela de naming, libs).
3. Apresentar ao usuário
Resumo: arquitetura nomeada, regras de ouro, inconsistências. O PROJECT-DNA.md vira referência para
skill-feature-design e skill-execute respeitarem o legado.
Regras de ouro
- Descritivo, não aspiracional — como o código É, não como deveria ser.
- Exemplos reais — cite arquivos/trechos do projeto.
- Sinalize inconsistência — não invente um padrão único onde o legado mistura.
- Não re-varra — os fatos já estão em
dna-facts.json. - Preserve o determinístico — não reescreva tooling/naming/libs do CLI.
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.
- yesterday First seen · 64 lines · 0 tokens per session scan A e950e47063ac
skill-dna 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 889 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.
Other cursor rules, from other repositories
hedgehog
Hedgehog build discipline — how to work in this repo.
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
api-design
REST API Design Standards Agent.
observability
Observability Standards — Logging, Tracing & Metrics.
scala-backend
Scala Backend Execution Agent (Cats Effect / Tapir / Doobie).