tubemind-secure-mcp: Command for Claude Code

.claude/commands/dare-design.md

dare-design is a command for Claude Code from dewtech-technologies/tubemind-secure-mcp. It costs 0 tokens per session (866 once invoked), scanned A, original, MIT.

A command that creates or updates a project design document called DARE/DESIGN.md from a description of a project or feature. The document covers the system's purpose, requirements, people involved, and measurable goals.

In plain words
What is it for?
Use it to describe a new application, API, or feature and produce a documented design before implementation begins. It is useful for recording requirements, technical constraints, stakeholders, and success measures.
Why use it?
It removes the need to structure an early software design document by hand. It also checks the existing project files and preserves an existing design unless the user approves replacing it.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is dewtech-technologies/tubemind-secure-mcp's own configuration. It tells Claude Code how to work on tubemind-secure-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tubemind-secure-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/dewtech-technologies/tubemind-secure-mcp/main/.claude/commands/dare-design.md
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/tubemind-secure-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for dare-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/dewtech-technologies/tubemind-secure-mcp/dare-design/github.svg)](https://agentmods.dev/commands/dewtech-technologies/tubemind-secure-mcp/dare-design)
Your own site
<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.

agentmods 80×15 button for dare-design

Your own site · 80×15
<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>
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 866 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce 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

Measured today against content hash 79cb144c6ec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/commands/dare-design.md · 70 lines

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.md se 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.

Read the full file on GitHub · 70 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.

  1. today First seen · 70 lines · 0 tokens per session scan A 79cb144c6ec3

Subscribe to this mod's changes

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.

Related

dare-design compared with commands from other repositories

dare-design next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dare-designdewtech-technologies/tubemind-secure-mcpCommand0todayMITA0Claude Code
test-suitetravisjneuman/.claudeCommand1137d agoMITA7Claude Code
pull-repostravisjneuman/.claudeCommand1137d agoMITA13Claude Code
security-scantravisjneuman/.claudeCommand1137d agoMITA6Claude Code
assemble-teamtravisjneuman/.claudeCommand1137d agoMITA25Claude Code
standardize-claude-mdtravisjneuman/.claudeCommand1137d agoMITA18Claude Code
helptravisjneuman/.claudeCommand1137d agoMITA9Claude Code