skill-dag-build

skill-dag-build is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 0 tokens per session (1,689 once invoked), scanned A, original, MIT.

Regenera APENAS o DARE/dare-dag.yaml a partir do BLUEPRINT.md já existente — sem refazer o blueprint nem as specs. Use quando o BLUEPRINT mudou pouco mas o grafo precisa refletir o novo estado, ou para experimentar uma decomposição diferente.

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-dag-build
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-dag-build

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-dag-build.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-dag-build)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-dag-build"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-dag-build.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 1,689 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 $0.01689
Opus 5 $0.00000 $0.00844
Sonnet 5 $0.00000 $0.00338
Haiku 4.5 $0.00000 $0.00169

Measured today against content hash c7b94cc73f4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-dag-build 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-dag-build.mdc · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: DAG Build — Regerar o grafo

Esta skill regenera apenas o DARE/dare-dag.yaml a partir do BLUEPRINT existente. Não refaz o blueprint, não refaz specs, não executa nada.

Para executar o grafo, use a skill skill-dag-runner (rule) ou o comando /run-dag. Para visualizar o grafo, use o comando /dag-viz. Para build + run num único passo, use skill-dag-runner que cobre ambos.

Quando usar

  • O BLUEPRINT foi ajustado e o grafo precisa refletir
  • Você quer experimentar uma decomposição diferente sem refazer o blueprint
  • O dare-dag.yaml ficou inconsistente com EXECUTION/task-*.md
  • Precisa adicionar/remover/reordenar tasks no grafo
  • A complexidade ou as dependências de tasks mudaram

Pré-requisitos

  • DARE/BLUEPRINT.md existe e está aprovado
  • (Opcional) DARE/EXECUTION/task-*.md específicas serão preservadas se não forem mencionadas

Procedimento

1. Ler DARE/BLUEPRINT.md

Obrigatório. Se faltar, peça ao usuário rodar /generate-blueprint antes.

2. Ler DARE/dare-dag.yaml atual (se existir)

Para preservar ids já em uso e não confundir o usuário com renomeações desnecessárias.

3. Gerar o novo dare-dag.yaml

Schema canônico:

title: "<Nome do Projeto> - Development Tasks"
version: "1.0.0"

limits:
  parent_context_chars: 2000
  task_output_chars: 4000
  timeout_seconds: 600

models:
  cursor:      { HIGH: gpt-5.3-codex,     MED: composer-2,       LOW: auto-low }
  claude:      { HIGH: claude-sonnet-4-5, MED: claude-haiku-4,   LOW: claude-haiku-4 }
  antigravity: { HIGH: gemini-2.5-pro,    MED: gemini-2.5-flash, LOW: gemini-2.5-flash }

tasks:
  - id: task-001
    title: "..."
    depends_on: []
    complexity: LOW
    spec_file: EXECUTION/task-001.md
    subtask_prompt: |
      <self-contained>

Regras inegociáveis:

  • id em kebab-case e único
  • depends_on mínimo — só quando filha literalmente precisa do output do pai
  • subtask_prompt self-contained
  • Pelo menos 2 tasks no rank 0 (paralelismo desde o início)
  • Cadeia linear é antipattern — quebre dependências sempre que possível
  • complexity honesta — não inflar nem deflar

Read the full file on GitHub · 174 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 · 174 lines · 0 tokens per session scan A c7b94cc73f4a

Subscribe to this mod's changes

skill-dag-build 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 1,689 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.