Borrowing it
Nothing to install: this file belongs to dewtech-technologies/tubemind-secure-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dewtech-technologies/tubemind-secure-mcp/main/.claude/commands/dare-design.mdgit clone --depth 1 https://github.com/dewtech-technologies/tubemind-secure-mcpWrote 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/tubemind-secure-mcp/dare-design)<a href="https://agentmods.dev/commands/dewtech-technologies/tubemind-secure-mcp/dare-design"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/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/tubemind-secure-mcp/dare-design"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/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 | $0.00866 |
| Opus 5.5 | $0.00000 | $0.00346 |
| Sonnet 5.5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00087 |
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 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 — 70 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.
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
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
2.7 Stack Técnica — tabela por camada com tecnologia e versão.
2.8 Integrações Externas — tabela: sistema, tipo, protocolo, direção, dados trocados, responsável. Inclua apenas integrações confirmadas; marque incertas como "A confirmar".
2.9 Restrições — prazo, orçamento de infra, limitações técnicas, compliance regulatório.
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 · 70 lines · 0 tokens per session scan A 79cb144c6ec3
dare-design is a command published in the GitHub repository dewtech-technologies/tubemind-secure-mcp (0 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 866 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 2026-11-18.
dare-design compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dare-designdewtech-technologies/tubemind-secure-mcp | Command | 0 | today | MIT | A | 0 | Claude Code |
| test-suitetravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 7 | Claude Code |
| pull-repostravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 13 | Claude Code |
| security-scantravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 6 | Claude Code |
| assemble-teamtravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 25 | Claude Code |
| standardize-claude-mdtravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 18 | Claude Code |
| helptravisjneuman/.claude | Command | 113 | 7d ago | MIT | A | 9 | Claude Code |