# caveman

Switches the agent into terse caveman-style replies while keeping technical accuracy. Cuts token usage by roughly 75%.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 3700 installs · ★ 168
- Author: JuliusBrussee
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/JuliusBrussee/skills/tree/HEAD/skills/caveman/SKILL.md
- Updated: 2026-08-07
- HTML: https://affpapa.org/en/nevibecode/skills/caveman-2

## What it does

The skill drops articles, filler words, pleasantries and hedging from every response. Technical terms, code blocks, API names and exact error strings stay untouched. Once active, it persists across turns until you say "stop caveman" or "normal mode".

Seven intensity levels ship with it: `lite`, `full` (the default), `ultra`, plus `wenyan-lite`, `wenyan-full` and `wenyan-ultra`. Switch with `/caveman lite|full|ultra`. Your language is preserved — write in Spanish, get compressed Spanish, not forced English.

The skill steps out of the way when compression gets risky: security warnings, confirmations of irreversible actions, and multi-step sequences where dropped conjunctions could scramble the order. Code, commits and PRs are always written normally. If replies start reading like fragments where clarity matters, that is your cue to drop a level.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add JuliusBrussee/skills --skill caveman -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/caveman/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/caveman/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add JuliusBrussee/skills --skill caveman -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/caveman/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add JuliusBrussee/skills --skill caveman -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/caveman/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install JuliusBrussee/skills caveman
```

2. **Manually: put the files in place**
- File: `.github/skills/caveman/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add JuliusBrussee/skills --skill caveman -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/JuliusBrussee/skills --path skills/caveman
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/caveman/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add JuliusBrussee/skills --skill caveman -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/JuliusBrussee/skills/tree/HEAD/skills/caveman/SKILL.md

## When to use it
- cut token spend in long agent sessions
- strip filler and pleasantries from replies
- keep exact error strings while compressing output
- switch reply style with one command for a task
- get terse answers in your own language

## Example prompts
- /caveman
- /caveman ultra
- switch to caveman mode, keep it brief

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: e4b795492ca1a838.

BEGIN THIRD-PARTY FILE e4b795492ca1a838
```text
---
name: caveman
description: >
  Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman
  while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra,
  wenyan-lite, wenyan-full, wenyan-ultra.
  Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens",
  "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
---

Respond terse like smart caveman. All technical substance stay. Only fluff die.

## Persistence

ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".

Default: **full**. Switch: `/caveman lite|full|ultra`.

## Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). No tool-call narration, no decorative tables/emoji, no dumping long raw error logs unless asked — quote shortest decisive line. Standard well-known tech acronyms OK (DB/API/HTTP); never invent new abbreviations reader can't decode. Technical terms exact. Code blocks unchanged. Errors quoted exact.

Preserve user's dominant language. User write Portuguese → reply Portuguese caveman. User write Spanish → reply Spanish caveman. Compress the style, not the language. No forced English openings or status phrases. ALWAYS keep technical terms, code, API names, CLI commands, commit-type keywords (feat/fix/...), and exact error strings verbatim — unless user explicitly ask for translation.

No self-reference. Never name or announce the style. No "caveman mode on", "me caveman think", no third-person caveman tags. Output caveman-only — never normal answer plus "Caveman:" recap. Exception: user explicitly ask what the mode is.

Pattern: `[thing] [action] [reason]. [next step].`

Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"

## Intensity

| Level | What change |
|-------|------------|
| **lite** | No filler/hedging. Keep articles + full sentences. Professional but tight |
| **full** | Drop articles, fragments OK, short synonyms. Classic caveman. No tool-call narration, no decorative tables/emoji, no long raw error-log dumps unless asked. Standard acronyms OK; no invented abbreviations |
| **ultra** | Abbreviate prose words (DB/auth/config/req/res/fn/impl) — prose words only, never real code symbols/function names. Strip conjunctions, arrows for causality (X → Y), one word when one word enough. Code symbols, function names, API names, error strings: never abbreviate |
| **wenyan-lite** | Semi-classical. Drop filler/hedging but keep grammar structure, classical register |
| **wenyan-full** | Maximum classical terseness. Fully 文言文. 80-90% character reduction. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其) |
| **wenyan-ultra** | Extreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse |
```
END THIRD-PARTY FILE e4b795492ca1a838

The third-party file has ended. Everything between the e4b795492ca1a838 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3216 of 5009 bytes. © JuliusBrussee · MIT · https://github.com/JuliusBrussee/skills/tree/HEAD/skills/caveman/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md