caveman
An agent skill by JuliusBrussee, from JuliusBrussee/caveman. Tags: cli, copy-editing, local-workflow, writing.
What it does
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add JuliusBrussee/caveman --skill cavemanOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/JuliusBrussee/caveman
cp -r caveman/plugins/caveman/skills/caveman ~/.claude/skills/cavemanSafety box score
Grade A, minimal risk: 5 of 100 risk points, rated 2026-10-05. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
Style-only skill. It changes assistant tone and persistence inside chat, but ships no scripts, no network calls, no filesystem access, and no privilege changes. Main thing to know: it makes caveman mode persist for the session until explicitly turned off.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, code evaluation, or bundled scripts; only SKILL.md, YAML metadata, and SVG icons. |
| Network access | 0 (none) | No downloads, uploads, API calls, or remote fetch instructions in the shipped files. |
| Filesystem reach | 0 (none) | No reads, writes, deletes, or path edits outside the skill bundle; only static asset references like `./assets/caveman.svg`. |
| Secrets & credentials | 0 (none) | No credential handling, token access, `.env` usage, or prompts to paste secrets. |
| Privilege & persistence | 0 (none) | No sudo, global install, service registration, shell startup edits, or OS/git setting changes. |
| Instruction hijack surface | 1 (low) | It imposes a persistent persona and response constraints, e.g. `Every response, whole session, until user says "stop caveman"` and `Use $caveman to answer briefly`. |
| Irreversible actions | 0 (none) | It does not send messages, deploy, publish, pay, book, or delete anything; it only changes wording of replies. |
| Transparency | 0 (none) | Everything is readable text or SVG; no binaries, installers, minified blobs, or runtime-decoded code. |
Before installing
- Read `SKILL.md` to confirm you want session-persistent terse replies.
- Check whether your workflow depends on normal tone being restored automatically; it will not be.
- Verify the alias behavior in `SKILL.md` if you plan to use `/caveman ultra` or `/caveman wenyan`.
Rated 2026-10-05 by an automated review of 4 files from the skill's repository.
Source
- Repository
- JuliusBrussee/caveman (all skills from this repository)
- Path
- plugins/caveman/skills/caveman/SKILL.md
- Branch
- main
- Collection
- caveman
- Updated
- 2026-10-05
Related skills
- megacave — Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan.
- ultracave — Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra.
- caveman-stats — Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.
- agents-get-started — Use when a developer wants to create a new agent project or get started with AgentCore.
- copy-editing — When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content.
- google-docs — Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers.