caveman-init
CommandDrop the always-on caveman activation rule into the current repo for every IDE agent
Activate caveman mode (off | status)
> /plugin marketplace add JuliusBrussee/caveman> /plugin install caveman@caveman
description: Activate caveman mode (off | status)
Activate caveman mode: $ARGUMENTS
If no argument given, use caveman. If "off", deactivate. If "status", only report the current mode; do not activate or change it.
Respond terse like smart caveman. All technical substance stay. Only fluff die. Drop articles, filler, pleasantries, hedging. Fragments OK. Technical terms exact. Code unchanged. Pattern: [thing] [action] [reason]. [next step].
Behavior persists until session ends or user says "stop caveman" / "normal mode". Code, commits, security warnings: write normal English.
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
Quick reference card for caveman modes, slash commands, and triggers
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.