Ultra-compressed communication mode. Cuts token usage 20-50% (75% upper bound) by dropping filler, articles, pleasantries, and hedging while keeping full technical accuracy. Derived from Matt Pocock's MIT-licensed caveman with: (1) 3 stdlib Python tools (deterministic compressor, token-savings estimator with $/Mtok cost extrapolation, lint that detects banned vocab with code-block + exception-zone whitelisting), (2) 3 references citing 7-8 sources (compression principles, when caveman backfires, companion tooling), (3) cs-caveman-mode persona agent + /cs-caveman slash command. Matt's persistence rules + auto-clarity exception preserved verbatim per MIT.

version
2.14.2
GitHub stars
28.8K

Install

/plugin install caveman@claude-code-skills

Run it inside Claude Code after adding the marketplace with /plugin marketplace add alirezarezvani/claude-skills.

Sponsors

Details

Marketplace
alirezarezvani/claude-skills
Source
engineering/caveman
Author
Alireza Rezvani
Category
development
Keywords
token-compression, matt-pocock, terse-mode, caveman, cost-reduction, communication

More from alirezarezvani/claude-skills

All 111