slimclaw

Analyze prompts and optimize token usage with windowing, caching, and routing.

8|1|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/evansantos/slimclaw --skill slimclaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: slimclaw
Source: https://github.com/evansantos/slimclaw/tree/main
Command: npx skills add https://github.com/evansantos/slimclaw --skill slimclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

SlimClaw reduces token costs by intelligently windowing conversation history, injecting cache breakpoints, and routing to cost-effective models across providers.

Core Features & Use Cases

  • Hybrid routing with ClawRouter integration and heuristic fallback for robust model selection and cost optimization.
  • Per-model dynamic pricing insights, latency tracking, and a real-time dashboard for visibility.
  • Cache breakpoint injection and smart windowing to minimize token usage in long conversations.

Quick Start

Configure SlimClaw in your OpenClaw setup and start the dashboard to begin observing token savings and routing decisions.

Frequently Asked Questions about slimclaw

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reduce token costs in long-running chats with multiple providers?

To reduce token costs in long-running chats, apply conversation history windowing and inject cache breakpoints. This minimizes active token counts sent to providers, lowering overall expenses and improving latency.

What is smart routing for cost optimization across multi-provider models?

Smart routing for cost optimization analyzes prompts and directs requests to cost-effective models based on dynamic pricing and latency tracking. It uses heuristic fallbacks to ensure robust model selection across providers.

Does smart routing work with OpenClaw deployments?

Yes, smart routing works with OpenClaw deployments. It targets multi-provider model setups within OpenClaw, using ClawRouter integration and heuristic fallback to optimize token usage and reduce costs.

How do I set up a dashboard to observe token savings and routing decisions?

To observe token savings and routing decisions, configure the optimization tool in your OpenClaw setup and start the real-time dashboard. It exposes a command interface and provides visibility into latency and pricing insights.

When should I use cache breakpoint injection for token optimization?

Use cache breakpoint injection for token optimization during long-running chats to minimize token usage. It works alongside conversation windowing to reduce the active context window size sent to multi-provider models.