What problem does it solve?
High token consumption from verbose AI outputs drives up API costs and slows down workflows for frequent use cases like code reviews, document summarization, and long context loading, forcing users to pay for unnecessary extra tokens.
Core Features & Use Cases
- Output Compression: Cuts response token usage by ~75% for code explanations, PRD summaries, and daily conversations without losing technical accuracy.
- Input Compression: Reduces memory file size by ~46% for long context loads and CLAUDE.md files to free up context window space.
- Sub-skills: Includes tools for generating one-line Git commit messages, one-sentence code reviews, and lifetime token savings tracking.
- Use Case: If you regularly process large codebases, run frequent code reviews, or load long context files for development work, this skill cuts your AI costs while preserving all critical information.
Quick Start
Ask the AI to enable caveman mode to receive all subsequent responses in ultra-concise, low-token formatting.