From buzz-crypto-bd
Routes LLM tasks to the cheapest capable model (free Llama 70B/Qwen 30B for simple tasks, paid MiniMax M2.5 for complex reasoning) to minimize costs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/buzz-crypto-bd:clawrouterThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You have access to multiple LLM providers at different cost tiers. Route tasks to the cheapest capable model to minimize costs while maintaining quality.
You have access to multiple LLM providers at different cost tiers. Route tasks to the cheapest capable model to minimize costs while maintaining quality.
openrouter/meta-llama/llama-3.3-70b-instruct:free (alias: Llama70B)
/model Llama70Bakashml/Qwen/Qwen3-30B-A3B (alias: Qwen30B)
/model Qwen30Bminimax/MiniMax-M2.5 (alias: MiniMax)
/model MiniMaxWhen spawning sub-agents or handling tasks, apply these routing rules:
Before executing a task, assess its complexity:
After completing tasks on free models, note the cost savings:
npx claudepluginhub buzzbysolcex/buzz-bd-agentProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.