#14 · Primary category： AI Coding Assistants
caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Project last updated：08/29/26
GitHub Stars
101.8K
Forks
5.9K
Contributors
43
License
Other
Why we included this project
Token costs add up fast when an AI coding agent narrates every answer, and this skill trims that waste directly. Install it once and the agent switches to terse caveman-speak, dropping filler and hedging while leaving code, commands, and error strings untouched. The repo shows before/after examples and independent measurements: roughly two-thirds fewer output tokens on prose, and a smaller but measurable cut on long agentic coding runs. It works with Claude Code, Codex, Cursor, and 30+ other agents, and because it is just a prompt-level skill, you can try it for a day and remove it just as easily. Anyone paying per token for heavy agent use is the obvious audience.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.