A faster way to answer simple messages before the big model wakes up

A faster way to answer simple messages before the big model wakes up

We looked at Claude Code and would like to share an idea and a working approach. The idea is small but it can make the agent feel much quicker and cheaper to run, especially for people who run models on their own computer.

Right now, every message you type wakes up the big language model, even when the message is simple. A greeting, a question about something already on the screen, or a clear request for one small action all pay the cost of a full model call. On a cloud service this costs money. On a home computer or a small graphics card it feels slow.

Our idea is to put a very small and fast decider in front of the big model. This decider does not write text. It looks at the message for a few tens of milliseconds and answers a few simple questions with a confidence score. Is this just chat. Does it need a tool. Can it be answered from what is already on screen. Is it complex or risky. When the decider is sure, the message takes a short and cheap path. When it is not sure, the message goes to the big model exactly as it does today. So the agent is never worse than before. It is only faster when the decider is confident.

We want to be honest about one thing. This public repository holds the changelog, plugins, and documentation rather than the agent source code, so we could not attach a code change here the way we did for some other projects. We have built this same idea as a working change inside other open agent harnesses, and we are glad to share the approach and the code with anyone who works on the Claude Code source.

The full idea, the license, and a note about why we chose not to patent it are here: https://github.com/Andrea-Bruno/harness-superfast

The idea is offered under a Creative Commons Attribution 4.0 license. If you take the idea or the code, we ask for one small thing. Please keep a short credit to Andrea Bruno and a link to the page above in your project documentation. That is the only condition. You are free to use it, change it, and ship it, including in a paid product.

We would be glad to hear what you think.