JuliusBrussee/caveman

🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

aianthropiccavemanclaudeclaude-codellmmemeprompt-engineeringskilltokens

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push today.

	Repository	Stars	Language	License	Activity
1	affaan-m/ECCThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code	★ 283.1k	JavaScript	MIT	Active
2	NousResearch/hermes-agentThe agent that grows with you	★ 254.9k	Python	MIT	Active
3	DietrichGebert/ponytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.	★ 166.9k	JavaScript	MIT	Active
4	thedotmack/claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and inject	★ 101.6k	TypeScript	Apache-2.0	Active
5	asgeirtj/system_prompts_leaksDocumented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Goog	★ 69.9k	Python	CC0-1.0	Active
6	Significant-Gravitas/AutoGPTAutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on w	★ 187.6k	Python	Other	Active
7	rtk-ai/rtkCLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies	★ 83.9k	Rust	Apache-2.0	Active
8	diegosouzapw/OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, Min	★ 78k	TypeScript	MIT	Active