{"name":"ciciliaeth-caveman-engineering-caveman","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"ciciliaeth-caveman-engineering-caveman","source":{"source":"github","repo":"ciciliaeth/claude-skills"},"description":"Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Enhanced from Matt Pocock's MIT-licensed caveman skill (https://github.com/mattpocock/skills) with: (1) stdlib Python tools (text compressor, token-savings estimator, caveman-style linter), (2) 3 reference docs citing 5+ authoritative sources each (compression principles, technical communication patterns, when caveman backfires), (3) cs-caveman-mode persona agent + /cs:caveman slash command. Matt's voice and persistence rules preserved verbatim per MIT. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman.","version":"1.0.0","strict":true,"keywords":[],"category":"productivity"}]}