What is dare-dag-runner?

A single command for building and running a directed acyclic graph, or DAG—a set of tasks arranged by dependencies so each task can run in the required order. It can also create an Excalidraw view of the result.

Use it to build `dare-dag.yaml`, run its tasks through the Ralph Loop, execute one task, or generate a final `dag-graph.excalidraw` file.

It removes the need to run separate commands for preparing the task file, executing tasks, and optionally creating a visual graph. You can also skip one stage or run only a selected task.

dare-dag-runner — Command by dewtech-technologies

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 commands/dewtech-technologies/dare-method/dare-dag-runner

Clone the repo

git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,357 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01357
Opus 5	$0.00000	$0.00678
Sonnet 5	$0.00000	$0.00271
Haiku 4.5	$0.00000	$0.00136

Measured 3d ago against content hash bddea0cc7565, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dare-dag-runner 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 3d 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.

implementations/claude/.claude/commands/dare-dag-runner.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dare-dag-runner

Wrapper agregador que cobre todo o ciclo do DAG num único comando: build do dare-dag.yaml (se necessário) → execução de todas as tasks via Ralph Loop → opcional visualização final em Excalidraw.

Esta skill existe por paridade conceitual com Antigravity e Cursor, que consolidam build + run numa única skill chamada dare-dag-runner. No Claude você também tem os comandos granulares /dare-dag-build, /dare-dag-run e /dare-dag-viz caso prefira controle fino.

Sem API keys. Você (Claude Code) usa o plano da IDE/CLI em que o usuário já está autenticado. O CLI dare apenas coordena estado, monta prompts e atualiza canvas.

Como usar

/dare-dag-runner                 # build + run completo, com viz opcional ao final
/dare-dag-runner --skip-build    # pula build, executa o yaml atual
/dare-dag-runner --skip-run      # só (re)gera o yaml, não executa
/dare-dag-runner --viz           # ao final, gera dag-graph.excalidraw
/dare-dag-runner --task task-003 # executa apenas uma task específica

Quando usar

Você quer rodar todo o ciclo sem se preocupar com comandos separados
Está começando a fase EXECUTE pela primeira vez num projeto
Quer paridade com o fluxo do Antigravity/Cursor (1 skill = ciclo completo)

Quando NÃO usar

Você quer só regerar o yaml (sem executar) → use /dare-dag-build
Você quer só executar o yaml atual (sem regerar) → use /dare-dag-run
Você quer só o diagrama Excalidraw → use /dare-dag-viz
O BLUEPRINT está desatualizado → atualize primeiro com /dare-blueprint

Pré-requisitos

DARE/BLUEPRINT.md existe e está aprovado (a fase build precisa dele)
dare disponível no PATH (npm i -g @dewtech/dare-cli)

O que fazer

Fase 1 — BUILD (se aplicável)

Se o yaml não existe ou está stale (BLUEPRINT mais novo que o yaml), execute o procedimento completo de /dare-dag-build:

Ler DARE/BLUEPRINT.md
Ler DARE/dare-dag.yaml atual (preservar ids)
Gerar o novo dare-dag.yaml obedecendo:
- id em kebab-case e único
- depends_on mínimo
- subtask_prompt self-contained
- Pelo menos 2 tasks no rank 0
- Cadeia linear é antipattern
- complexity honesta
- ANTI-STUB CONTRACT em cada spec (ver /dare-dag-build para detalhes)
Atualizar DARE/TASKS.md
Pedir aprovação ao usuário antes de executar.

Read the full file on GitHub · 118 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.

3d ago First seen · 118 lines · 0 tokens per session scan A bddea0cc7565

Subscribe to this mod's changes

dare-dag-runner is a command 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 1,357 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 2026-08-31.

Planning agentic-engineering ai-agents ai-assisted-development ai-coding anthropic claude

dare-dag-runner