本文へスキップ
TakoAPI
スキル一覧に戻る

token-optimizer-qsmtco

qsmtco 作

Coding Agents & IDEs
—まだ評価がありません
あなたの評価

概要

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking.

説明

このスキルでできること

A toolkit for reducing token usage and API costs in OpenClaw deployments. Provides scripts for context lazy-loading, task-based model routing, heartbeat interval management, and daily budget tracking. All analysis runs locally with no network requests unless live pricing is explicitly requested.

Bundles context lazy-loading, model routing, heartbeat throttling, and budget tracking in one local toolkit, so cost reductions apply automatically without manually selecting a model for each request.

使いどころ

  • Automatically routing casual chat messages to cheaper model tiers
  • Reducing context token load by 80% for simple or repetitive prompts
  • Enforcing cheap models for all scheduled cronjobs and heartbeat checks
  • Monitoring daily API spend and switching models when a budget limit is hit
  • Spacing out periodic background checks to reduce unnecessary API calls

ワークフロー例

入力

User asks: debug this error in the logs

エージェント
  1. 1

    Runs model_router.py with the user prompt to classify task complexity

  2. 2

    Receives Standard tier recommendation based on the debug task pattern

  3. 3

    Runs token_tracker.py to check if daily budget is within limits

  4. 4

    Falls back to Haiku model if budget status is 'exceeded'

  5. 5

    Proceeds with the selected model for the session

出力

Request processed with the appropriate model tier and budget constraint enforced

要件

  • OPENROUTER_API_KEY environment variable (only needed to refresh live model pricing data)

インストール

clawhub install qsmtco/token-optimizer-qsmtco

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