Look up commands for concise response modes, commit messages, review comments, and Markdown compression. The reference also explains how to check the current mode, return to normal responses, and configure startup defaults.
Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
caveman-help displays a quick reference for concise response modes and commands for related skills. It explains the differences between caveman, which gives the main point first; ultracave, which removes grammar and answers in fragments; and megacave, which uses Classical Chinese. It also lists how to invoke the skills for short commit messages, one-line PR comments, and Markdown document compression.
Use it when you forget a command name or want to choose how much to shorten responses. The reference also covers checking the current mode, returning to normal responses, and configuring the default at startup.
/caveman-helpInvoking either displays the reference immediately. The help itself does not switch modes or save settings or state.
Status checks depend on the environment. Claude Code and the standalone OpenCode plugin read saved state. Other environments infer the mode from the conversation and indicate that they do not track it. In OpenCode, caveman still activates at startup even when manual is specified.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in caveman style.
| 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).
| 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. |
Say "stop caveman" or "normal mode". Resume anytime with /caveman.
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.
Default mode = caveman. Change it:
Environment variable (highest priority):
export CAVEMAN_DEFAULT_MODE=ultracave
Config file (~/.config/caveman/config.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.
Full docs: https://github.com/JuliusBrussee/caveman
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.
Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.
Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.
Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.