JuliusBrussee/caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
A skill is a folder of written instructions your AI agent reads when it needs them. Installing one copies those files into your agent’s skills directory. Nothing runs. More about skills.
Not available through Techandria. Techandria only installs commits a person has approved. This one has not been.
You can still get the code from the source and read it yourself:
git clone https://github.com/JuliusBrussee/cavemanDiscovery metadata only. Nothing has been scanned or approved, so this is a listing — not a recommendation to run the code.
The badge shows this project's current review state and updates on its own — including if the state changes. It links back to this page.
[](https://techandria.com/project/JuliusBrussee/caveman)No README could be fetched from GitHub for this repository.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
The agent that grows with you
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.