Caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
Optimize any text — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search. If you can measure it, you can optimize it.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.