caveman

You can reduce token consumption by enforcing a terse, high-precision communication mode that removes filler while maintaining technical accuracy. This mode applies to software engineering, documentation, and debugging tasks where token economy and clarity matter.

The best way to enforce verbosity control in AI prompting is using deterministic phrasing rules with configurable intensity levels. Apply strict frontmatter-driven configuration to force concise responses, ensuring robust fallback to standard mode when brevity is not explicitly invoked.

Yes, you can configure conciseness intensity levels for technical documentation using six distinct modes: lite, full, ultra, wenyan-lite, wenyan-full, and wenyan-ultra. These settings allow varying verbosity control to match specific precision and token-efficiency requirements.

Auto-activation works for brevity requests in debugging tasks by triggering on specific prompts like caveman or /caveman, as well as on explicit requests for brevity. It automatically switches to concise mode and replies with minimal fluff while preserving technical accuracy.

You should not use terse communication mode when a task requires robust fallback to standard mode but lacks explicit invocation. Without strict frontmatter-driven configuration and deterministic phrasing rules, forcing conciseness may degrade technical accuracy in complex software engineering explanations.