Tag: llm-optimization

Caveman is a Claude Code skill that cuts 75% of AI output tokens by making agents talk in terse 'caveman speak' while preserving 100% technical accuracy. Install in 30 seconds, save on inference costs, and iterate faster.

rtk is a high-performance Rust CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single binary, zero dependencies, 100+ supported commands, and integrations with 13 AI coding tools including Claude Code, Copilot, and Cursor.