Jubba

founder @ many places just check my github | creator of caveman, the #1 most entertaining way to save tokens

[Jubba @JuliusBrussee]

My Claude Code skill hit #1 on Hacker News today.
It makes Claude talk like a caveman and cuts ~75% of output tokens.
700+ GitHub stars in 24 hours. Here's what I learned from the 200+ comments 🧵

[Jubba @JuliusBrussee]

btw, caveman cli agent is coming this week, ecosystem far from over

[Jubba @JuliusBrussee]

lol

[Jubba @JuliusBrussee]

1000 token CLAUDE.md × 100 sessions = 100,000 tokens on context you already wrote.

caveman-compress cut in half.

one command. run once. saves token forever.

/caveman-compress

[Jubba @JuliusBrussee]

caveman mass popular. mass token saved.
but caveman only talk different. not think different
so caveman built cavekit.
you say what want. cavekit write spec. agent build from spec. nothing guessed

why use many prompt when one spec do trick
https://t.co/uOUIIDxFE3

[Jubba @JuliusBrussee]

@elonmusk want adopt Caveman speak into @grok?

Many word bad. Few word good. Rock efficient. Token bill smaller. Brain hurt less.

Caveman open cave. Grok come visit?

[Jubba @JuliusBrussee]

@EthanBayya many thank.

[Jubba @JuliusBrussee]

caveman #1 on hackernews, GitHub (3k stars in under 48h), Twitter, posted to Chinese news. What the hell is going on?

[Jubba @JuliusBrussee]

inter-agent communication should default to caveman mode. ‘NEED DATA. SEND NOW. DONE.’ why are we burning tokens on grammar between machines

[Jubba @JuliusBrussee]

@om_patel5 Hahaha thanks for the shoutout!!!

[Hacker News 50 @betterhn50]

Talk like caveman https://t.co/3kqbLj9tYQ (https://t.co/ypiRasnhBv)

[Jubba @JuliusBrussee]

@Top10_Dev @GPT4 @CAVEMAN Appreciate the shoutout!

[Jubba @JuliusBrussee]

1.3k github stars in 24 hours, what is going on 😭

[Jubba @JuliusBrussee]

GitHub finds my caveman skill for claude important enough to give this popup lol

[Jubba @JuliusBrussee]

@Bondigthefirst caveman

https://t.co/z34ozdDM38

[Jubba @JuliusBrussee]

The wildest part: someone else posted it to HN. I didn't.
Built it as a joke in an afternoon. Turns out everyone hates LLM slop equally.

https://t.co/lB3IWeRPn7

[Jubba @JuliusBrussee]

My Claude Code skill hit #1 on Hacker News today.
It makes Claude talk like a caveman and cuts ~75% of output tokens.
700+ GitHub stars in 24 hours. Here's what I learned from the 200+ comments 🧵

[Jubba @JuliusBrussee]

#2 criticism: "output tokens aren't the real cost"
Fair. But scanning "New obj ref each render. Wrap in useMemo." beats reading four paragraphs starting with "I'd be happy to help you with that."
It's a readability tool as much as a cost tool.

[Jubba @JuliusBrussee]

@heyblake why use many token when few do trick

https://t.co/z34ozdDM38

[Jubba @JuliusBrussee]

@suni_code use caveman skill, it’s the method 🙏🙏🙏