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.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
The most efficient coding agent. Same model, same work, smaller bill. 21% cheaperthan CodexTerminal-Bench 4, per solved task 14% cheaperthan Claude CodeTerminal-Bench 4, 97 vs 83 solved 76% cheaperthan Claude Codefull workday, 4 connected apps Same model on both sides: GPT-6.1 Sol against Codex, Opus 5.5 against Claude Code. Our own runs, November 2026, at list prices. How we measured Every coding agent in one window. Free on the subscriptions and keys you already have. Download Caveman Code for Mac · Read the launch post Caveman make your AI agent say less and read less. Code stay exact. Brain still big. 33.2% fewerinput tokens, whole sessions54 Claude Code runs, 18 of 18 answers right 54% cheaperwith Auto, same score85 coding tasks vs Opus 5.5 at xhigh, interim 397 → 76tokens for one test runBlocks vs | tail -20 1.4 to 2.4× cheaperwith caveman-style outputAdobe Research, eight models Cited by Adobe…
Read the full README ↗ · Preview checked 2026-11-16T20:53:02.537Z
Inside the original README — Document outline
- New: Caveman Code. Free.
- why many token when few do trick
- Install
- Six rocks, one install
- Proof
- Say less: the caveman voice
- Read less: 33.2% fewer input tokens
- Auto: 54% cheaper, same score
- Blocks: code mode, script written once
- Smaller rocks
- Commands
- Caveman Cloud
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
🪨 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.
Repository facts
- Owner
- JuliusBrussee
- Primary language
- Go
- Stars
- 120,314
- Forks
- 7,011
- Open issues + pull requests
- 158
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-04-04T10:03:00.000Z
- Last push
- 2026-10-01T19:57:24.000Z
Topics and intended use
Owner-supplied topics: ai, anthropic, caveman, claude, claude-code, llm, meme, prompt-engineering, skill, tokens
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-11-15T12:22:37.391Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.