A task-planning tool for the DARE method. It turns an approved BLUEPRINT into a task list, a dependency graph, and detailed task files for execution; a dependency graph records which tasks must come first.

Use it after approving `DARE/BLUEPRINT.md` to prepare work for `dare execute` and its subagents.

It keeps the human plan, executable order, and task instructions consistent, reducing failures caused by missing dependencies or mismatched task details.

dare-tasks — Skill 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 skills/dewtech-technologies/dare-method/dare-tasks

Any agent

npx skills add dewtech-technologies/dare-method --skill dare-tasks

Clone the repo

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

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,626 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	$0.00076	$0.02626
Opus 5	$0.00038	$0.01313
Sonnet 5	$0.00015	$0.00525
Haiku 4.5	$0.00008	$0.00263

Measured 2d ago against content hash b0de7fedb434, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dare-tasks 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 2d 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/antigravity/.agents/skills/dare-tasks/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DARE Tasks Skill

Você é o especialista em decomposição de projetos do método DARE. Seu papel é quebrar o BLUEPRINT aprovado em tasks atômicas e gerar simultaneamente os três artefatos da fase de execução, garantindo consistência entre eles.

Quando usar esta skill

BLUEPRINT.md foi aprovado pelo usuário
Necessário criar o plano de execução (tasks + grafo + specs)
Terceira fase do Método DARE (transição A → E)

Pré-requisitos

Antes de gerar, leia também a skill dare-dag-runner — ela contém as regras inegociáveis do grafo (depends_on mínimo, complexity, prompt self-contained, limites de 2000/4000 chars, ranks paralelos).

Os 3 artefatos sempre juntos

Arquivo	Para quê	Lido por
`DARE/TASKS.md`	Visão humana com tabela e progresso	Humano
`DARE/dare-dag.yaml`	Grafo executável	CLI `dare execute`
`DARE/EXECUTION/task-<id>.md`	Spec detalhada por task	Subagente ao executar

Os três precisam estar consistentes: mesmos ids, mesmas depends_on, mesmas complexity. Inconsistência aqui quebra a execução.

Como usar

Passo 1: Ler o BLUEPRINT aprovado

Leia DARE/BLUEPRINT.md. Extraia:

Fases do plano de execução
Endpoints, modelos de dados, schemas
Estrutura de diretórios
Decisões arquiteturais
Estratégia de testes

Passo 2: Decompor em tasks atômicas

Cada task deve:

Ser pequena o suficiente para uma conversa única (15–60 min de trabalho)
Ter dependências reais e mínimas (não falsas)
Ser testável isoladamente
Incluir validações de segurança apropriadas
Ter complexity honesta (LOW/MED/HIGH)

Passo 3: Gerar `DARE/TASKS.md` (visão humana)

# Tasks: [Nome do Projeto]

## Visão Geral
- Total de Tasks: [N]
- Ranks paralelos: [N]
- Tempo estimado: [horas]

## Tabela de Status

| ID       | Título                      | Status      | Depends On       | Complexity |
|----------|-----------------------------|-------------|------------------|------------|
| task-001 | Setup project structure     | ⏳ PENDING  | —                | LOW        |
| task-002 | DB migrations               | ⏳ PENDING  | —                | MED        |
| task-003 | Auth controllers            | ⏳ PENDING  | task-001, 002    | HIGH       |
| ...      | ...                         | ...         | ...              | ...        |

## Tarefas por Fase

### Phase 1: Setup
- task-001: Setup project structure
- task-002: DB migrations

### Phase 2: Auth
- task-003: Auth controllers (deps: 001, 002)
- ...

## Próximas Etapas
1. Revisar e aprovar este TASKS.md
2. Executar paralelo: `dare execute --parallel`
3. Ou task isolada: `/dare-execute task-001`

Read the full file on GitHub · 266 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.

2d ago First seen · 266 lines · 76 tokens per session scan A b0de7fedb434

Subscribe to this mod's changes

dare-tasks is a skill published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,626 once invoked, about $0.0004 per session on Opus 5. 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.

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

write-test-plan

Generate a QA/UAT test plan from product specifications and task definitions, covering acceptance testing, integration flows, and exploratory testing. Unit tests are out of scope (handled by write-unit-tests skill).

andresharpe/dotbot · 43 tokens

implement-telegram-bot

Implement Telegram bot interactions with command handlers, message parsing, and inline keyboards for conversational interfaces.

andresharpe/dotbot · 23 tokens

setup-background-job

Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection.

andresharpe/dotbot · 22 tokens

write-unit-tests

Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.

andresharpe/dotbot · 26 tokens

blazor-component-design

Design Blazor components with proper parameter binding, event callbacks, lifecycle management, and render optimization. Use when creating new Blazor Server or WASM components, refactoring component hierarchies, implementing cascading values, or optimizing component rendering performance.

andresharpe/dotbot · 53 tokens

hedgehog-planning-intake

Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…

skyf0xx/hedgehog · 374 tokens