Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

ultracave — Claude Code skill: what it does, how to install

Compresses AI agent replies into short fragments while keeping code, commands, paths, and critical limits intact. Useful for terse coding sessions.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add JuliusBrussee/caveman --skill ultracave -a claude-code
Open on GitHub

What ultracave does

ultracave puts the agent into an extreme-compression response mode. It drops articles, connective words, and repetition when the meaning stays clear, using fragments or a single word where possible. Technical substance remains.

The skill starts only through /ultracave or /caveman ultra, because model invocation is disabled. It stays active for the whole session until stop caveman or normal mode; /caveman status reports the current mode. Code, commands, paths, API names, error strings, negations, numbers, and units stay unchanged.

Install ultracave when short agent replies fit your coding workflow. Turn it off for discussions that need fuller explanations or natural prose.

What it helps with

  • compress agent replies to the payload
  • remove repeated facts from coding chats
  • keep commands and paths verbatim
  • switch terse mode across a session

Example prompts for the agent

  • Turn on `/ultracave`.
  • Run `/caveman status` to check the mode.
  • Stop it with `normal mode`.

How to install ultracave

1Skills CLI (Vercel)

npx skills add JuliusBrussee/caveman --skill ultracave -a claude-code

2Manually: put the files in place

~/.claude/skills/ultracave/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ultracave/

From the same set22

The whole set →
caveman JuliusBrussee Cuts filler and polite greetings from agent responses while keeping technical facts and code exact. Stays active until turned off. Claude Code CX Codex Cursor +1 591,500installs caveman-commit JuliusBrussee Generates terse Conventional Commits messages focused strictly on intent. Ideal for keeping git history clean without boilerplate or AI signatures. Claude Code CX Codex Cursor +1 414,700installs caveman-review JuliusBrussee Generates terse, single-line code review comments with exact line numbers, problems, and fixes. Eliminates conversational filler in pull request reviews. Claude Code CX Codex Cursor +1 410,700installs caveman-compress JuliusBrussee Rewrites CLAUDE.md and todo files into terse caveman-speak so the model reads fewer input tokens. The source gets overwritten; a readable backup stays out of tree. Claude Code CX Codex Cursor +1 410,300installs caveman-help JuliusBrussee A quick reference for Caveman modes and commands in Claude Code and other supported hosts. Use it when you need to control response style or find related skills. Claude Code CX Codex Cursor +1 401,800installs cavecrew JuliusBrussee cavecrew delegates code searches, small edits, and diff reviews to three subagents. Use it when keeping the main agent's context lean matters. Claude Code CX Codex Cursor +1 357,900installs caveman-stats JuliusBrussee Displays recorded output and cache-read tokens for Claude Code sessions or points to host native usage stats. Useful for tracking raw token consumption. Claude Code CX Codex Cursor +1 356,700installs caveman-explore JuliusBrussee A read-only skill locates relevant files and line ranges in a repository. Use it for cold-start orientation or broad searches. Claude Code CX Codex Cursor +1 106,500installs

Similar

marketing-plan coreyhaines31 Generates an AARRR-structured 12-month marketing plan with an audit score and a 90-day roadmap. Outputs a single Markdown document ready for Notion. Claude Code CX Codex Cursor +1 67,400installs gws-keep official googleworkspace This skill wires Google Keep into your agent: create, read, list and delete notes, plus download attachments through the gws CLI. Claude Code CX Codex Cursor +1 38,500installs prospecting coreyhaines31 The skill turns an ICP into a scored prospect list: sources candidates, checks emails, ranks accounts before outreach. Useful when you need a list you can actually send to. Claude Code CX Codex Cursor +1 64,800installs gws-gmail-watch official googleworkspace Watches Gmail for new emails and streams events as NDJSON. Use it when an agent needs incoming mail as a live input. Claude Code CX Codex Cursor +1 37,200installs gws-gmail-reply official googleworkspace Replies to a Gmail message while preserving the conversation thread. Useful for sending quick email responses or drafting them directly from the terminal. Claude Code CX Codex Cursor +1 35,100installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs

Questions about ultracave

How do I install ultracave in Claude Code?

Run npx skills add JuliusBrussee/caveman --skill ultracave -a claude-code. The skill file is placed at ~/.claude/skills/ultracave/SKILL.md.

What does ultracave do?

The skill compresses agent replies into fragments and removes repeated wording. Code, commands, paths, API names, and error strings remain unchanged.

How long does ultracave stay active?

The mode remains active for the session after /ultracave or /caveman ultra. Use stop caveman or normal mode to turn it off.

Source text

SKILL.md · Apache-2.0 
---
name: ultracave
description: >
  Caveman at maximum compression: fragments, one word when one word is enough,
  each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until
  "stop caveman" or "normal mode".
disable-model-invocation: true
---

# ultracave

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

Ultracave is caveman with the grammar stripped. Payload only.

## Persistence

Every response, whole session, until "stop caveman" or "normal mode". Unsure? Still on. `/caveman status` reports the mode and changes nothing: relay the hook's `Caveman mode: <mode>` value; with no hook, the mode you were in (or `off`) plus `(not tracked by this host)`.

## Floor

Never cut: code, commands, paths, API names, error strings (verbatim). not/never/no/only/except. Numbers and units. The user's language. One term per thing. No invented abbreviations, no arrows. Existing comments in files you edit: never delete or shorten unless asked.

## Rules

### 1. Fragments

Drop articles, copulas, connectives when order stays clear.

Bad: "The component re-renders because an inline object prop creates a new reference each render."
Good: "Inline object prop, new ref, re-render. `useMemo`."

### 2. One word when one word is enough

Bad: "Yes, that should work, though you'll want a null check first."
Good: "Yes. Null check first."

### 3. Each fact once

No restating, no summary after a list. Code change: changed lines plus context, not the whole file.

Good: "Pool reuses open DB connections. No per-request handshake."

### 4. Cut conjunctions only when order survives

Bad: "Migrate table drop column backup first."
Good: "Back up first. Then migrate: drops column."

### 5. Tool runs

One line in, one line out. Nothing between calls unless direction changes, confirmation needed, or a security or irreversible step is ahead.

### 6. Never perform

No prefix, no announcement, no mangled verbs for flavor. Fragment not shorter than the sentence? Use the sentence.

## When to break the rules

Plain prose, then resume: security warning. Irreversible action, confirm first. Any fragment with two readings. User confused. Question to the user, with its options. Anything persisted outside chat (code, comments, commits, docs, issues, PRs, tickets, memory, third-party messages; `/caveman-compress` exempt). Harness asks for a status line.

## Pre-send check

Two readings? Full sentence. Negations present? Payload verbatim? Flavor word? Cut.

© JuliusBrussee · Apache-2.0 · JuliusBrussee/caveman

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor