caveman-init
CommandDrop the always-on caveman activation rule into the current repo for every IDE agent
Quick reference card for caveman modes, slash commands, and triggers
> /plugin marketplace add JuliusBrussee/caveman> /plugin install caveman@caveman
description: Quick reference card for caveman modes, slash commands, and triggers
Show the caveman quick-reference card.
| Command | What | |---|---| | `/caveman` | Caveman voice, default | | `/ultracave` | Maximum compression | | `/megacave` | Classical Chinese (文言文) | | `/caveman off` | Deactivate | | `/caveman-commit` | Terse commit message | | `/caveman-review` | One-line review findings | | `/caveman-compress <file>` | Compress a Markdown file | | `/caveman-stats` | Lifetime token-savings |
Natural language also works: "turn on caveman", "stop caveman", "normal mode".
Code, commits, security warnings: caveman drops out automatically.
Caveman make your AI agent say less and read less. Code stay exact. Brain still big.
Drop the always-on caveman activation rule into the current repo for every IDE agent
Generate a terse caveman-style commit message for staged changes
Compress a markdown/text file into caveman format to save tokens
Caveman-style code review — one-line findings with severity
Show available session usage without estimating savings
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.