# Caveman

Ultra-compressed response style that reduces output token count while preserving...

- Repository: https://github.com/microsoft/hve-core (1591 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add microsoft/hve-core --skill caveman -g -a claude-code -y`
Codex: `npx skills add microsoft/hve-core --skill caveman -g -a codex -y`
Cursor: `npx skills add microsoft/hve-core --skill caveman -g -a cursor -y`
Gemini CLI: `npx skills add microsoft/hve-core --skill caveman -g -a gemini-cli -y`

## Description

Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Caveman Skill

## Overview

Caveman is an opt-in response style that reduces output verbosity while keeping technical content fully intact. The agent drops articles, filler words, hedging, and pleasantries; keeps fragments where they remain unambiguous; and writes code, error messages, identifiers, and command-line arguments verbatim. Use it when the user explicitly requests a terser response.

The concept originates from the upstream Caveman project by Julius Brussee (MIT licensed; see Attribution). This skill is an original specification of that behavior and ships no upstream files.

## How the Mode Persists

Caveman has no out-of-band state store, daemon, or hook. Persistence relies entirely on the conversation transcript:

* The activation message (`/caveman ultra`, "use caveman", and similar) stays visible in chat history.
* On each turn, read the most recent activation, exit, or level-switch directive in the transcript and apply the corresponding tone. The latest matching directive wins.
* The skill file is loaded on demand. Once the rules are in context, keep applying them without reloading. If context is trimmed and the rules drop out, reload `caveman/SKILL.md` the next time an active directive appears.
* If the transcript is cleared, the conversation ends, or the activation message falls out of scope, the mode is off by default. The user re-invokes to turn it back on.

State lives in chat, not in a file. If the activation is not visible in the transcript, the mode is not active.

## When to Use

Activate Caveman when the user asks for it directly:

* "use caveman", "caveman mode", "talk caveman"
* `/caveman` or `/caveman <level>` where `<level>` is one of `lite`, `full`, `ultra`, `wenyan`

Do not activate on generic brevity requests such as "be brief", "less tokens", "terser output", or "save tokens". Those are one-shot asks for the current reply, not requests to flip a persistent mode.

The rest: https://github.com/microsoft/hve-core/blob/HEAD/.github/skills/experimental/caveman/SKILL.md