staratheris-arya-model-router
bởi staratheris
AI & LLMsTóm tắt
Token-saver router: elige modelo (cheap/default/pro) y usa sub-agentes para tareas pesadas.
Mô tả
Kỹ năng này làm gì
Routes AI model selection between cheap, default, and pro tiers based on task complexity. For heavy tasks, it spawns sub-agents running a stronger model and can compress large context into a brief first to avoid passing unnecessary tokens to an expensive model.
Avoids paying for a powerful model on simple requests while still accessing one when the task actually requires it, without manually switching models.
Khi nào nên dùng
- Keeping daily chat interactions on a cheap model to reduce API spend
- Automatically escalating complex code analysis to a pro model
- Compressing a large document before routing it to an expensive model
- Running multi-step research through a sub-agent without inflating main context
- Forcing a specific model tier for a one-off request
Quy trình ví dụ
User asks: 'Router: analyze this 50-page spec for security gaps'
- 1
Classifies task as high complexity using router.py rules
- 2
Compresses the spec into a concise brief to reduce token count
- 3
Spawns a sub-agent configured with the pro model (openai/gpt-4.1)
- 4
Passes the brief and task instructions to the sub-agent
- 5
Returns the sub-agent's findings to the main conversation
Security gap report from the pro model, with the main agent staying on the cheap tier throughout
Yêu cầu
- OpenAI API key
Cài đặt
clawhub install staratheris/staratheris-arya-model-routerChạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.