Перейти к содержимому
TakoAPI
Назад к навыкам

token-saver-75plus

от mariovallereyes

Web & Frontend Development
560Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Always-on token optimization + model routing protocol.

Описание

Что делает этот навык

A model routing protocol that silently classifies every request into one of four tiers and dispatches work to the cheapest capable model via sessions_spawn. Applies strict output compression at every tier. Targets 75% or more reduction in token usage compared to running all tasks on a single premium model.

Automatically picks the cheapest model that can handle each task, so users don't overpay for simple work or under-provision for complex tasks.

Когда его использовать

  • Routing bulk CSV or list processing to free Groq instead of a paid model
  • Automatically sending code generation tasks to Codex while handling yes/no questions inline
  • Cutting response length on status checks to one or two lines
  • Escalating multi-agent coordination tasks to Opus without manual model switching
  • Parallelizing multiple tool calls to avoid sequential token overhead

Пример сценария

ВВОД

User asks: Refactor this 200-line Python class to use dataclasses and add type hints

АГЕНТ
  1. 1

    Classifies request as T3 (code generation, multi-step)

  2. 2

    Spawns Codex via sessions_spawn with full file content and detailed spec in the task string

  3. 3

    Codex returns refactored file

  4. 4

    Orchestrator returns result directly with no prose wrap-up

  5. 5

    Appends token/tier/route metadata if measurement mode is on

ВЫВОД

Complete refactored Python file with dataclasses and type hints, no preamble

Установка

clawhub install mariovallereyes/token-saver-75plus

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки