Leaderboard/Token Optimization/caveman
Last commit on September 14, 2026·Created on April 4, 2026

JuliusBrussee/caveman

Reduces token consumption for coding agents by stripping linguistic overhead.
Combined rank
#7
across all skills
In Token Optimization
#1
category rank
Stars
107k
+1.5% in last 7d
Forks
6.2k
+1.4% in last 7d
Watchers
246
+2.9% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

Caveman provides a proxy and prompt engineering framework that minimizes the number of tokens used during LLM communication. By adopting a compressed, primitive style of interaction, it helps AI agent builders and prompt engineers maintain utility while significantly lowering operational costs.

The system focuses on removing unnecessary words from agent prompts and responses, making the exchange of information between coding agents more efficient without sacrificing the core intent of the instruction.

WHO IT'S FOR
AI agent / automation builders
reducing token consumption for coding agents
Prompt engineers
optimizing LLM communication for efficiency
Backend / infrastructure engineers
managing LLM API costs and latency
Technical leads / architects
implementing efficient repository exploration tools
Repository contents

24 skill files

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.

Use this skill collection

Follow the documented setup, then try a first task.

I’m using

Unified installer for macOS, Linux, WSL, or Git Bash

Installs: Complete Caveman installation for every supported agent detected on the machine; the installer uses user scope except for Replit, whose documented location is the current project's .agents/skills. · Claude Code, Cursor, Codex, other supported installed agents

Before you start
  • Node.js 22.13 or newer
  • macOS, Linux, WSL, or Git Bash

Platform: macOS / Linux / WSL / Git Bash

  1. Run this command in a terminal. If installing for Replit, run it from that project's Shell because Replit uses the project-local .agents/skills location.

    curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/v2.7.0/install.sh | bash
README.md · Checked Sep 18, 2026INSTALL.md · Checked Sep 18, 2026

Give it something to do.

No starter task is available for this installation option.