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/skill-ax)<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-ax"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-ax/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/skill-ax"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-ax.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 | $0.00000 | $0.02173 |
| Opus 5.5 | $0.00000 | $0.00869 |
| Sonnet 5.5 | $0.00000 | $0.00435 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
skill-ax 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Agent Experience (AX) DARE
Você é um especialista em integração entre projetos e agentes de código (Claude Code, Cursor, Antigravity, MCP servers). Esta skill define o padrão AX DARE que todo projeto novo deve seguir e contra o qual todo projeto existente deve ser auditado.
Por que AX é design-first
Projetos podem ter código correto e arquitetura limpa mas carecer de sinais estruturados para agentes:
- Sem
llms.txt, o agente precisa adivinhar a estrutura - Sem OpenAPI, o agente faz parsing regex de docs HTML
- Sem
--jsonno CLI, o agente lida com tabelas ASCII coloridas - Sem rate limit, um prompt mal feito vira DDoS
A skill dare-ax codifica três planos:
| Plano | Pergunta que responde |
|---|---|
| Discovery | "Como o agente acha o que precisa?" |
| Usage | "Como o agente opera sem refactor desnecessário?" |
| Defense | "Como o projeto resiste a prompts ruins?" |
Plano 1 — Discovery
llms.txt na raiz (obrigatório)
Arquivo público com a "ficha técnica" do projeto. Formato livre mas seções fixas:
# <nome-do-projeto>
> <descrição em 1-2 frases — o que é, qual problema resolve>
## Stack
- <linguagem + framework>
- <banco>
- <cache, fila, etc.>
## Bootstrap
- `make setup` — instala deps + sobe Postgres/Redis local
- `make dev` — sobe aplicação
- `make test` — roda suite
## Endpoints
- `GET /healthz` — liveness
- `GET /openapi.json` — spec completa
- `POST /api/login` — autenticação
...
## CLI (se aplicável)
- `<bin> users create --email <e> --json`
- `<bin> migrate run --json`
## Docs internas
- DARE/DESIGN.md — requisitos
- DARE/BLUEPRINT.md — arquitetura
- docs/RUNBOOK.md — operações
Critério objetivo: o arquivo deve ser navegável em < 2 minutos por um agente.
Estrutura previsível
| Pasta | Conteúdo |
|---|---|
src/ ou crates/<projeto>-*/ |
código de produção |
tests/ |
testes (mirror de src/ quando possível) |
docs/ |
documentação humana extensa |
DARE/ |
DESIGN.md, BLUEPRINT.md, EXECUTION/, dare-dag.yaml |
infra/ ou deploy/ |
Dockerfile, compose, k8s manifests |
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 · 264 lines · 0 tokens per session scan A 1cdf3554f66f
skill-ax is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,173 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
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
api-design
REST API Design Standards Agent.
scala-backend
Scala Backend Execution Agent (Cats Effect / Tapir / Doobie).
go-backend
Go Backend Execution Agent.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.