Caveman Mode
Always-on personality override that forces terse, blunt, filler-free replies
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 24, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · 9a8e333
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 24, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Ran the same 'how do I revert the last commit' prompt with and without it: the baseline answer was ~55 words with a preamble and a sign-off, the skill collapsed it to ~13 words with no filler and dropped articles, exactly on spec. The transformation is reliable, but the SKILL.md declares itself 'always active for every response' with no way to scope it, so it also flattens tasks that need detail such as a formal report. The README's headline Claude.ai install tells you to download a caveman-mode.skill file that does not exist in the repo; only the Claude Code cp command actually works. Pure prose skill, no bundled scripts, nothing unsafe.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 3/5
- Output vs. baseline 6/10
- Docs & honesty 3/5
What Caveman Mode does
A personality-override skill that rewrites every Claude reply into short caveman-style sentences: 3-6 words, no articles, no preamble or sign-offs. It declares itself always active once installed, so it applies to all responses rather than triggering on a task. Useful when you want maximum brevity and zero filler.
How to install Caveman Mode
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Caveman Mode
-
/caveman-modeAlways-on personality override that forces terse, blunt, filler-free replies
It also activates on plain-language prompts like these:
-
Turn on caveman mode for all your replies from now on -
Answer short. No fluff. Caveman style only, always. -
Enable terse blunt replies, no preamble, no sign-offs
Frequently asked questions
- Is the Caveman Mode skill free?
- Yes. The skill itself is free from tohmsc/caveman-mode. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Caveman Mode work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 24, 2026. Verdict: Works with setup. Ran the same 'how do I revert the last commit' prompt with and without it: the baseline answer was ~55 words with a preamble and a sign-off, the skill collapsed it to ~13 words with no filler and dropped articles, exactly on spec. The transformation is reliable, but the SKILL.md declares itself 'always active for every response' with no way to scope it, so it also flattens tasks that need detail such as a formal report. The README's headline Claude.ai install tells you to download a caveman-mode.skill file that does not exist in the repo; only the Claude Code cp command actually works. Pure prose skill, no bundled scripts, nothing unsafe.
- What is the Caveman Mode SkillProof Score?
- 6.8/10 — installs cleanly 5/5, triggers reliably 3/5, output vs. baseline 6/10, docs & honesty 3/5.
- How do I install Caveman Mode?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Caveman Mode with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.