token-optimizer

What problem does it solve?

This Skill dramatically reduces OpenClaw token usage and API costs by optimizing how your agent interacts with language models and manages context.

Core Features & Use Cases

• Context Optimization: Significantly cuts down on the amount of text loaded into your agent's memory, saving tokens and speeding up responses.
• Smart Model Routing: Ensures the cheapest, most appropriate model is used for each task, from simple chat to complex reasoning.
• Use Case: An agent processing customer support tickets can use this Skill to load only the relevant ticket information and use a cheap model for initial triage, reserving expensive models for complex problem-solving.

Quick Start

Generate an optimized AGENTS.md file to implement lazy context loading.