本文へスキップ
TakoAPI
スキル一覧に戻る

staratheris-arya-model-router

staratheris 作

AI & LLMs
1.1kダウンロード数はclawskills.shが公開している値です
1閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

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

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

User asks: 'Router: analyze this 50-page spec for security gaps'

エージェント
  1. 1

    Classifies task as high complexity using router.py rules

  2. 2

    Compresses the spec into a concise brief to reduce token count

  3. 3

    Spawns a sub-agent configured with the pro model (openai/gpt-4.1)

  4. 4

    Passes the brief and task instructions to the sub-agent

  5. 5

    Returns the sub-agent's findings to the main conversation

出力

Security gap report from the pro model, with the main agent staying on the cheap tier throughout

要件

  • OpenAI API key

インストール

clawhub install staratheris/staratheris-arya-model-router

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク