Pular para o conteúdo
TakoAPI
Voltar às skills

arya-model-router

por staratheris

AI & LLMs
1.1kDownloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Token-saver router: elige modelo (cheap/default/pro) y usa sub-agentes para tareas pesadas.

Descrição

O que esta skill faz

Routes each task to one of three OpenAI model tiers based on complexity, keeping routine interactions on cheaper models and escalating to stronger ones only when needed. Before passing heavy tasks to a pro model, it can compress the context into a brief to avoid large token transfers. Model tiers and routing rules are configurable via a JSON file.

Eliminates manual model switching by applying routing rules automatically, so you pay for stronger models only when the task justifies it.

Quando usá-la

  • Keeping daily assistant costs low by defaulting to gpt-4o-mini
  • Auto-routing a complex debugging session to gpt-4.1
  • Running a long document analysis in a sub-agent without bloating main context
  • Forcing cheap mode explicitly for quick lookup tasks
  • Pre-briefing a pro model before handing off a large codebase review

Exemplo de fluxo de trabalho

ENTRADA

User asks: analyze this codebase for security vulnerabilities

AGENTE
  1. 1

    router.py classifies the task using rules.json and assigns it to the pro tier

  2. 2

    main agent compresses relevant context into a brief

  3. 3

    sub-agent is spawned with gpt-4.1 and receives the brief instead of full context

  4. 4

    sub-agent performs the security analysis

  5. 5

    results are returned to the main agent

SAÍDA

Security vulnerability report generated by gpt-4.1, with minimal token cost to the main agent

Requisitos

  • OpenAI API key

Instalação

clawhub install staratheris/arya-model-router

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links