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-blueprint.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-blueprint)<a href="https://agentmods.dev/commands/dewtech-technologies/tubemind-secure-mcp/dare-blueprint"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/dare-blueprint/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-blueprint"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/dare-blueprint.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 | $0.01610 |
| Opus 5.5 | $0.00000 | $0.00644 |
| Sonnet 5.5 | $0.00000 | $0.00322 |
| Haiku 4.5 | $0.00000 | $0.00161 |
Grade A, and why
dare-blueprint 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.
This is a copy
95% identical to dare-blueprint — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dare-blueprint
Gera somente DARE/BLUEPRINT.md a partir do DARE/DESIGN.md.
Tasks, DAG e specs de execução são geradas depois com
/dare-tasks, após aprovação humana do Blueprint.
Como usar
/dare-blueprint
/dare-blueprint --stack node-nestjs+react
O que fazer
1. Ler DARE/DESIGN.md
Obrigatório. Se não existir, peça para rodar /dare-design primeiro.
Extraia e use durante todo o comando:
- Stack técnica (linguagem, framework, versões)
- Requisitos funcionais priorizados (RF-*)
- Requisitos de segurança (RS-*)
- Integrações externas confirmadas
- Restrições e escopo
2. Gerar DARE/BLUEPRINT.md
Siga o template templates/BLUEPRINT-template.md. Seções obrigatórias:
2.1 Visão Geral da Arquitetura
- Diagrama Mermaid da arquitetura
- Tabela de decisões arquiteturais com justificativa (não apenas "escolha X")
2.2 Stack Técnica Definida — versões fixas, não ranges
2.3 Estrutura de Pastas — árvore completa dos arquivos que serão criados
2.4 Modelo de Dados — entidades, campos tipados, relacionamentos, índices necessários
2.5 Contratos de API — tabela completa: método, rota, auth, request body, response, status codes
2.6 Plano de Execução (Fases) — cada fase com:
-
Nome e objetivo
-
Critério de DONE — comportamento verificável e testável (não "código feito")
-
Lista de entregáveis concretos
Fase 1 é sempre containerização (Dockerfile + docker-compose + healthcheck) Fase N-1 é sempre auditoria de segurança e dependências
2.7 Validation Gates por Stack
| Stack | Build | Test | Lint/Audit |
|---|---|---|---|
| Rust/Axum | cargo build |
cargo test --workspace |
cargo clippy && cargo audit |
| Node/NestJS | npm run build |
npm test |
npx eslint src && npm audit --audit-level=high |
| Python/FastAPI | verificar imports | pytest |
ruff check . && pip-audit |
| PHP/Laravel | php artisan config:cache |
php artisan test |
./vendor/bin/phpstan && composer audit |
| Go | go build ./... |
go test ./... |
golangci-lint run |
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 · 135 lines · 0 tokens per session scan A 048d38b83419
dare-blueprint 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 1,610 tokens. A static security scan graded it A with 0 findings. It is 95% identical to dare-blueprint, differing in 6 lines, and is treated as a copy.
dare-blueprint compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dare-blueprintdewtech-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 |