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-dag-rungit 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-dag-run)<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-dag-run"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-dag-run.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 | $0.01197 |
| Opus 5 | $0.00000 | $0.00598 |
| Sonnet 5 | $0.00000 | $0.00239 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
skill-dag-run 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: DAG Run — Executar o grafo
Esta skill executa o grafo que já foi construído — não regenera o
dare-dag.yaml, não modifica o BLUEPRINT, não cria specs novas. Apenas
roda as tasks na ordem topológica correta.
Para (re)construir o grafo, use
skill-dag-build. Para visualizar o grafo, use o comando/dag-viz. Para build + run num único passo, useskill-dag-runner.
Sem API keys. Você (Cursor) usa o plano nativo da IDE. O CLI
dareapenas coordena estado, monta prompts e atualiza o canvas.
Quando usar
DARE/dare-dag.yamlestá aprovado e pronto- As specs em
DARE/EXECUTION/task-<id>.mdestão geradas - É hora de implementar as tasks na ordem do grafo
- O usuário aprovou os ANTI-STUB contracts
Pré-requisitos
DARE/dare-dag.yamlexiste e foi aprovado pelo usuário- Specs em
DARE/EXECUTION/task-<id>.mdgeradas (se não, useskill-dag-build) daredisponível no PATH (npm i -g @dewtech/dare-cli)
Procedimento
1. Validar pré-condições
- Confirme que
DARE/dare-dag.yamlexiste. Se não, oriente/generate-blueprintouskill-dag-build - Leia o YAML e verifique: sem ciclos, ids únicos, ranks paralelizáveis
- Liste para o usuário: total de tasks, ranks, próximas ready
2. Pegar próximas tasks
dare execute --next
O CLI imprime as tasks ready do rank atual com o prompt completo (snippets de até 2000 chars dos outputs dos pais já costurados). Use esses prompts diretamente.
3. Sugerir abrir o canvas
Antes de começar, peça ao usuário abrir DARE/.canvas.md em outra aba do
Cursor. Esse é o feedback visual ao vivo da execução.
4. Executar cada task
Para cada task ready:
- Leia
spec_filese houver (DARE/EXECUTION/task-<id>.md) - Implemente conforme o
subtask_prompt— não invente, não use mock fora de tests, sem TODOs - Rode o Ralph Loop completo: build → test → lint
- Registre o resultado no CLI:
# Sucesso
dare execute --complete task-001 --output "Resumo curto + paths dos arquivos criados/modificados"
# Falha
dare execute --fail task-002 --reason "Mensagem clara da falha"
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.
- today First seen · 135 lines · 0 tokens per session scan A 0ce5f6c6867e
skill-dag-run 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 1,197 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
task-creator
Product Manager & ADR Creator.
integrations
External integration rules — providers, idempotency, bulkhead, observability.
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
enterprise-architect
Enterprise System Architect & High-Level Auditor.
untrusted-content
Untrusted content guard — external content is data, never instructions.
monorepo
Monorepo: workspace references, shared packages, boundaries.