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/commands/dewtech-technologies/dare-method/dare-design)<a href="https://agentmods.dev/commands/dewtech-technologies/dare-method/dare-design"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/dare-method/dare-design/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/commands/dewtech-technologies/dare-method/dare-design"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/dare-method/dare-design.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 | $0.01059 |
| Opus 5.5 | $0.00000 | $0.00424 |
| Sonnet 5.5 | $0.00000 | $0.00212 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
dare-design 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dare-design
Gera ou atualiza o DARE/DESIGN.md a partir de uma descrição do projeto ou feature.
Equivalente no terminal:
dare design "<description>" --ai
Como usar
/dare-design Quero uma API REST de autenticação com JWT e refresh token
/dare-design Adicionar módulo de pagamentos com Stripe e webhook
O que fazer
1. Leia o contexto atual do projeto
package.json/composer.json/Cargo.toml/go.mod/requirements.txt— stack atual- Estrutura de pastas existente
DARE/DESIGN.mdse já existir — não sobrescreva sem aprovação explícita do usuário- Se
dare design --interactiveemitiu a seção## Perguntas de Planejamento (Analyst/PM), leia esse bloco antes de prosseguir
1b. Planejamento leve (Analyst → PM)
Se o bloco de questionário existir no DESIGN.md, conduza 1 passagem sequencial (sem runtime multi-agente):
- Analyst — uma rodada sobre escopo, ambiguidades e lacunas (
kind:'scope'|'ambiguity'|'gap'). - PM — uma rodada sobre requisitos e critérios de aceite.
Ordem sequencial: Analyst antes de PM; sem voltar, sem message pool, sem loop de troca. Marque inferências como 🟡 e lacunas não resolvidas como 🔴; fatos do CLI permanecem 🟢.
2. Gere DARE/DESIGN.md com as seguintes seções obrigatórias
2.1 Descrição — 3 a 5 frases claras: o que é, qual problema resolve, quem usa.
2.2 Objetivos e Métricas de Sucesso — tabela numerada (O-01, O-02…) com métrica verificável e meta numérica para cada objetivo. Evite objetivos vagos como "melhorar performance" — use "p99 < 200 ms".
2.3 Stakeholders — tabela: papel, nome/time, interesse principal.
2.4 Requisitos Funcionais — tabela numerada (RF-01, RF-02…) com prioridade MUST/SHOULD/COULD e critério de aceite verificável para cada um.
2.5 Requisitos Não-Funcionais — tabela numerada (RNF-01…) cobrindo: performance, disponibilidade, segurança (autenticação, rate limiting, segredos), observabilidade, manutenibilidade.
2.6 Requisitos de Segurança — tabela numerada (RS-01…). Inclua sempre:
- RS-01: validação de entrada (OWASP A03)
- RS-02: proteção de dados sensíveis / hash de senhas (OWASP A02)
- RS-03: controle de acesso por recurso (OWASP A01)
- RS-04: auditoria de dependências sem CVE HIGH/CRITICAL (OWASP A06)
- RS-05: secrets via variáveis de ambiente — nunca em código
- Adicione requisitos específicos do domínio do projeto
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 · 82 lines · 0 tokens per session scan A 238f51554cfb
dare-design is a command 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 1,059 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 commands, from other repositories
context
Command "context" from Vimalk0703/shipworthy, covering process, 1. context infrastructure, 2. regression fence health, 3. session signals and 4. context completeness.
diagnose
Command "diagnose" from Vimalk0703/shipworthy, covering process, example output, project diagnosis report, critical (fix immediately) and high (fix soon).
health
Command "health" from Vimalk0703/shipworthy, covering part 1: plugin installation health and part 2: project health.
validate
Command "validate" from Vimalk0703/shipworthy, covering /validate — pre-push validation gate, what this does, steps, when to run and output format.
retro
Command "retro" from Vimalk0703/shipworthy, covering process and important.
audit
Before executing this command, output.