Caveman
Claude Code plugin that cuts token usage by ~65% by forcing ultra-compact responses. Three compression levels: light, full, ultra. Same technical accuracy, less filler.
Strengths
- Immediate ~65% reduction in output tokens without changing your workflow
- Three adjustable levels depending on context (light for reviews, ultra for pure code)
- One-command install, zero configuration after
Limitations
- Compressed responses can lose readability for beginners
- Doesn't affect reasoning tokens, real session gain is ~4-10%
Best for
- Devs who regularly hit their Claude Code session limits
- Long vibe-coding sessions where narrative responses slow the flow