HomePricingHow it works
Log in

Token Optimization

Token Optimization reduces the amount of terminal output sent back to the AI agent. This preserves more of the model's context window during long sessions without changing the commands you ask the agent to run.

How it works

Supercode combines its Token Saver with a managed RTK installation. It installs and updates the optimizer automatically, validates it before use, and keeps it isolated from your shell configuration. If optimization is unavailable or unsafe for a command, the original command runs normally.

Enable Token Optimization

  • Open the Supercode menu and use the Token Optimization switch.
  • Alternatively, select Settings in the same menu. On the General page, find Command Optimization and use the Token optimization switch.
  • The Settings page shows installation, update, and retry status when action is required.

Availability

Token Optimization requires an active subscription and a supported local Cursor environment. The control is disabled when the current IDE, operating system, remote environment, or shell is not supported.