Aller au contenu
TakoAPI
Retour aux skills

staratheris-arya-model-router

par staratheris

AI & LLMs
1.1kTéléchargements rapportés par clawskills.sh
1Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

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

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

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

AGENT
  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

SORTIE

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

Prérequis

  • OpenAI API key

Installation

clawhub install staratheris/staratheris-arya-model-router

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens