跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Caveman Repo

市场 已验证 活跃

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

0 个 Plugin
目的

To significantly reduce token consumption and improve response times for AI agents by enforcing concise, 'caveman-like' communication, leading to cost savings and faster interactions.

功能

  • Compresses AI agent output tokens by up to 75%
  • Maintains full technical accuracy with reduced verbosity
  • Offers multiple compression levels (lite, full, ultra, wenyan)
  • Provides specialized commands for commit messages, PR reviews, and file compression
  • Includes installation scripts for various platforms and agents

使用场景

  • Reducing LLM API costs by minimizing token usage
  • Improving response speed of AI agents
  • Generating concise and accurate commit messages
  • Creating brief and effective PR review comments
  • Compressing existing memory files for shorter session contexts

非目标

  • Reducing LLM thinking/reasoning tokens
  • Simplifying technical accuracy
  • Providing general-purpose text summarization outside of AI agent output
  • Reducing LLM's 'brain' size

安装

/plugin marketplace add juliusbrussee/caveman

质量评分

已验证
100 /100
about 24 hours ago 分析

信任信号

最近提交2 days ago
星标59.5k
许可证MIT
状态
查看源代码