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

caveman-help — Claude Code skill: what it does, install

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.

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

What caveman-help does

caveman-help lists the Caveman commands and explains the caveman, ultracave, and megacave modes. Use /caveman, /ultracave, /megacave, or /caveman status to change or inspect the current mode. Say “stop caveman” or “normal mode” to deactivate it.

The card also covers caveman-commit, caveman-review, caveman-compress, and caveman-help. The default mode can be set with CAVEMAN_DEFAULT_MODE or ~/.config/caveman/config.json; environment variables take priority over repository and user config. Claude Code and OpenCode read stored state, while other hosts use the conversation and mark the mode as not tracked by the host.

Install this skill when you want a compact command reference for Caveman. It is unnecessary if you only need a different response tone and do not use the Caveman commands.

What it helps with

  • find the Caveman mode commands
  • change response style during a session
  • check the active mode without changing it
  • set a default Caveman mode
  • look up related skill commands

Example prompts for the agent

  • Show `/caveman-help` and explain the available commands.
  • Run `/caveman status` without changing the current mode.
  • Set `CAVEMAN_DEFAULT_MODE=manual` for Claude Code.

How to install caveman-help

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/caveman-help/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/caveman-help/

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 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 caveman-learn JuliusBrussee This skill reads Caveman learn reports, proposes token-cost reductions, and asks for consent before each edit. Use it for heavy CLAUDE.md files or repeated context. Claude Code CX Codex Cursor +1 105,700installs

Similar

retro Matt Pocock Reviews a coding session and suggests changes to the agent environment for later runs. Use it after mistakes, slow repository navigation, or costly tool calls. Claude Code 276,027installs doc-coauthoring official anthropics Guides document drafting through context collection, section work, and a reader check. Use it for specs, RFCs, proposals, and decision documents. Claude Code Claude.ai 93,900installs internal-comms official anthropics internal-comms helps Claude write internal communications in the formats your company uses, from status reports to FAQs and incident reports. Claude Code Claude.ai 79,929installs slideshow heygen-com Build live HyperFrames decks with slides, fragment reveals, branching hotspots, and presenter notes. Use it when the output should be a presentation rather than a video. Claude Code CX Codex Cursor +1 415,500installs pr Matt Pocock Helps Claude Code structure a PR body with a change summary, before-and-after evidence, and a clear account of merge risk. Claude Code 167,125installs google-agents-cli-adk-code official Google A reference skill for building ADK agents with tools, callbacks, state, and workflows. Use it when an agent project needs concrete API patterns or code examples. Claude Code CX Codex Cursor +1 511,400installs 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 skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs

Questions about caveman-help

How do I install caveman-help in Claude Code?

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

What does caveman-help do?

It provides a reference for Caveman modes, related commands, and default-mode configuration. It triggers with /caveman-help or “caveman help”.

Which platforms support caveman-help?

The skill supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. Claude Code and OpenCode read stored mode state; other hosts use the current conversation.

Source text

SKILL.md · Apache-2.0 
---
name: caveman-help
description: >
  Quick-reference card for the three caveman skills and their commands.
  Trigger: /caveman-help or "caveman help".
---

# Caveman Help

Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in caveman style.

## Modes

| Mode | Trigger | What change |
|------|---------|-------------|
| **caveman** | `/caveman` | The voice. Answer first, no fluff, every fact kept. Default. |
| **ultracave** | `/ultracave` (alias `/caveman ultra`) | Grammar stripped. Fragments, one word when enough, each fact once. |
| **megacave** | `/megacave` (alias `/caveman wenyan`) | Classical Chinese 文言文. Far fewer characters, technical terms verbatim. |

Mode stick until changed or session end.
`/caveman status` reports current mode without changing it. Claude Code and the standalone OpenCode plugin read stored state; other hosts answer from the conversation and mark it `(not tracked by this host)`.

## Skills

| Skill | Trigger | What it do |
|-------|---------|-----------|
| **caveman-commit** | `/caveman-commit` | Terse commit messages. Conventional Commits. ≤50 char subject. |
| **caveman-review** | `/caveman-review` | One-line PR comments: `L42: bug: user null. Add guard.` |
| **caveman-compress** | `/caveman-compress <file>` | Compress .md files to caveman prose. 33.2% fewer tokens on the repo's five test files. |
| **caveman-help** | `/caveman-help` | This card. |

## Deactivate

Say "stop caveman" or "normal mode". Resume anytime with `/caveman`.

## Language

Keep user's language by default — reply in the language user writes, never switch regardless of example text or multilingual context elsewhere. Compress the style, not the language. Technical terms, code, commands, commit types, and exact error strings stay verbatim unless user ask for translation.

## Configure Default Mode

Default mode = `caveman`. Change it:

**Environment variable** (highest priority):
```bash
export CAVEMAN_DEFAULT_MODE=ultracave
```

**Config file** (`~/.config/caveman/config.json`):
```json
{ "defaultMode": "ultracave" }
```

For opt-in activation in Claude Code, set `defaultMode` to `manual`. Sessions start off; `/caveman` or `talk like caveman` activates caveman. `off` also disables bare-command activation. `manual` is a startup policy, not a mode. OpenCode still starts in caveman mode because its installer also supplies static activation rules.

Set `"off"` to suppress automatic and bare-command activation. Use `"manual"` when bare `/caveman` should activate.

Resolution: env var > repo config > user config > `caveman`. Legacy values `lite`, `full`, `ultra`, `wenyan*` still resolve.

## More

Full docs: https://github.com/JuliusBrussee/caveman

© 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