Intelligent model routing for Claude Code sessions. Recommends optimal model (Opus/Sonnet/Haiku) and effort level based on task complexity. Delegates mechanical work to cheaper subagents. Maximizes quality-per-dollar across the entire session. Trigger on: any new session, "save tokens", "cheaper model", "delegate this", "use sonnet", "effort level", "cost", or automatically when task complexity is
/plugin marketplace add scoobydont-666/shared-claude-skills
O comando exato pode variar conforme o repositório. Confira o README no GitHub.
Para o autor da skill
Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.
[](https://www.skillteca.com.br/skills/session-miser?utm_source=badge&utm_medium=readme&utm_campaign=badge)
Habilidade de pesquisa de segurança em Modo Equipe que orquestra 3 caçadores de vulnerabilidades e 2 engenheiros de PoC para auditar um código, provar explorabilidade, classificar causas raiz e calibrar a severidade. É utilizada para revisão de segurança, pesquisa de vulnerabilidades, auditoria de explorabilidade e validação de modelo de ameaças.
Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assessment, and remediation guidance across the full spectrum of web security threats.
Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA.
Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.
Alerta por categoria
1 email curto, só com as skills novas de Segurança. 4 minutos de leitura, sem spam, cancela com 1 clique.
Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.
Use the cheapest model that can do the job well. Opus for thinking, Sonnet for doing, Haiku for fetching.
| Task Type | Model | Effort | Why |
|---|---|---|---|
| Architecture, design, complex reasoning | Opus | high | Needs deep reasoning |
| Security audits, code review with judgment | Opus | medium | Quality-sensitive |
| Code generation (new features, complex logic) | Opus or Sonnet | mediu |
[Description truncada. Veja o README completo no GitHub.]
