Caveman
Skill Verified ActiveUltra-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.
To drastically reduce token consumption in LLM interactions by adopting a compressed, caveman-like communication style without sacrificing technical detail.
Features
- Ultra-compressed LLM responses
- Preserves full technical accuracy
- Six intensity levels for compression
- Automatic safety message fallback
- Persistent mode until manually changed
Use Cases
- Reducing token costs for long conversations
- Enabling LLM use in low-bandwidth environments
- Getting concise, technically accurate answers quickly
- Experimenting with different communication styles
Non-Goals
- Modifying user input or prompts
- Introducing ambiguity or loss of technical detail
- Handling non-LLM communication tasks
- Operating without LLM context
Workflow
- User invokes caveman mode via command or auto-trigger.
- Skill applies selected intensity level to LLM responses.
- LLM output is compressed, removing fluff but keeping technical detail.
- Caveman mode persists unless explicitly stopped or a safety condition is met.
- Skill resumes normal prose for security warnings, irreversible actions, or ambiguous sequences.
Installation
First, add the marketplace
/plugin marketplace add juliusbrussee/caveman/plugin install caveman@cavemanQuality Score
VerifiedTrust Signals
Similar Extensions
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Arize Prompt Optimization
100Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
Prompt Optimization
100Applies prompt repetition to improve accuracy for non-reasoning LLMs
Memory Bank
99Token-efficient persistent memory system for Claude Code that saves ~67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode. Activates at session start (if MEMORY.md exists), on "remember this", "pick up where we left off", "what were we doing", "wrap up", "save progress", "don't forget", "switch context", "hand off", "memory health", "save state", "continue where I left off", "context budget", "how much context left", or any session start on a project with existing memory files. This skill solves two problems at once: Claude forgetting everything between sessions, AND sessions hitting context limits too fast. It replaces thousands of wasted re-explanation tokens with a compact, structured memory load that gives Claude full project context in under 2,000 tokens.
Slack
100Use the Slack tool to react, pin/unpin, send, edit, delete messages, or fetch Slack member info.
Gmail
100Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail labels. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.