Pular para o conteúdo
TakoAPI
Voltar às skills

tokenqrusher

por qsmtco

Coding Agents & IDEs
—Ainda sem avaliações
Sua avaliação

Resumo

Token optimization system for OpenClaw reducing costs 50-80%.

Descrição

O que esta skill faz

tokenQrusher reduces OpenClaw API token costs by 50-80% through two hooks: one that loads only the workspace files needed for a given message's complexity, and one that stretches heartbeat check intervals. All processing runs locally with no external calls.

Rather than manually trimming prompts, it classifies each message automatically and strips irrelevant context before the agent ever sees it.

Quando usá-la

  • Cutting monthly API bills for a busy personal OpenClaw agent
  • Loading minimal context for quick greetings and one-liners
  • Suppressing heartbeat polls during overnight quiet hours
  • Checking which files would load for a specific prompt before running it
  • Reducing API call volume for calendar and email polling

Exemplo de fluxo de trabalho

ENTRADA

User asks: 'hi'

AGENTE
  1. 1

    token-context hook fires on agent:bootstrap

  2. 2

    Classifies message complexity as 'simple' with 95% confidence

  3. 3

    Filters workspace files down to SOUL.md and IDENTITY.md

  4. 4

    Passes filtered file list to the agent instead of full context

SAÍDA

Agent bootstraps with 2 files instead of 7, saving up to 99% of context tokens for that message

Instalação

clawhub install qsmtco/tokenqrusher

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

Links