+ 
-
+
why use many token when few do trick
+
+ Make your AI coding agent talk like a caveman.
+ Same answers, ~50–65% fewer output tokens. Brain still big. Mouth small.
+
- Before/After • - Install • - What You Get • - Benchmarks • - Full install guide + See it · + Install · + Levels · + What you get · + Benchmarks · + Ecosystem · + Caveman 2
--- -A [Claude Code](https://docs.anthropic.com/en/docs/claude-code) skill/plugin (also Codex, Gemini, Cursor, Windsurf, Cline, Copilot, 30+ more) that makes agent talk like caveman — cuts **~50–65% of output tokens, measured** (65% average vs default verbose replies, ~50% median vs a plain "answer concisely" baseline — real Claude API token counts, see [Benchmarks](#benchmarks)), keeps full technical accuracy. Brain still big. Mouth small. - -> **Honest number warning:** caveman shrink **output** tokens only. Input tokens untouched by skill — whole-session savings smaller than the output number, and on terse tasks can be negative. Full truth: [docs/HONEST-NUMBERS.md](./docs/HONEST-NUMBERS.md). +Caveman is a skill/plugin for [Claude Code](https://docs.anthropic.com/en/docs/claude-code), Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and 30+ other agents. Install once. Agent drops the filler and answers in tight caveman-speak, keeping code, commands, and errors byte-for-byte exact. You save output tokens on every reply, forever. ## Before / After| + | 🗣️ Normal agent — 69 tokens | + Caveman agent — 19 tokens |
+|
|---|---|---|---|
| -### 🗣️ Normal Claude (69 tokens) - -> "The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object." +> The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object. | -+ |
-### Caveman Claude (19 tokens)
-
-> "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`."
+> New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`.
|
|
| + | -### 🗣️ Normal Claude - -> "Sure! I'd be happy to help you with that. The issue you're experiencing is most likely caused by your authentication middleware not properly validating the token expiry. Let me take a look and suggest a fix." +> Sure! I'd be happy to help you with that. The issue you're experiencing is most likely caused by your authentication middleware not properly validating the token expiry. Let me take a look and suggest a fix. | -+ |
-### Caveman Claude
-
-> "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"
+> Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:
|
|
-
-### Like this trick? Now get whole agent — **caveman-code**
-
-This skill shrink what agent **say**. **[caveman-code](https://github.com/JuliusBrussee/caveman-code)** shrink **everything** — full terminal coding agent, caveman top to bottom. **~2× fewer tokens than Codex** on identical tasks. 20+ providers · plan mode · autopilot goal loop · MIT.
-
-```bash
-npm install -g @juliusbrussee/caveman-code
-```
-
-[**▶ Try caveman-code now →**](https://github.com/JuliusBrussee/caveman-code) — *why use many token when whole agent save*
-
- |
|
-Maintainer detail (hook architecture, file ownership, CI sync) live in [CLAUDE.md](./CLAUDE.md).
+### Want the whole agent, not just its mouth? → caveman-code
-## Lobster, Meet Rock 🦞
-
-[**OpenClaw**](https://openclaw.ai) the self-host gateway. One box, many agent inside (Claude Code, Codex, Pi, OpenCode), wired to your Slack / Discord / iMessage / Telegram / whatever. Tagline: *"The lobster way."* Lobster strong. Lobster smart. Lobster also talk a lot.
-
-Caveman teach lobster brevity — same canonical installer, scoped to one agent:
+This skill shrinks what an agent **says**. **[caveman-code](https://github.com/JuliusBrussee/caveman-code)** shrinks **everything** — a full terminal coding agent, caveman top to bottom. **~2× fewer tokens than Codex** on identical tasks. 20+ providers, plan mode, autopilot goal loop, MIT.
```bash
-# macOS / Linux / WSL
-curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash -s -- --only openclaw
-
-# Windows (PowerShell): no Node? install Node ≥18 first, then
-npx -y github:JuliusBrussee/caveman -- --only openclaw
+npm install -g @juliusbrussee/caveman-code
```
-Two thing happen, no more:
+[**▶ Try caveman-code →**](https://github.com/JuliusBrussee/caveman-code)
-1. **Skill drop** at `~/.openclaw/workspace/skills/caveman/SKILL.md` — spec-correct frontmatter (`version`, `always: true`), discoverable by `openclaw skills list`. Skill not auto-inject (OpenClaw load skill on demand) — that why we also do step 2.
-2. **SOUL.md nudge.** Tiny marker-fenced block appended to `~/.openclaw/workspace/SOUL.md`. OpenClaw inject SOUL.md into *every* turn under "Project Context" (12K-per-file, 60K total — block well under). Lobster terse from message one. No `/caveman` per session. No nag.
+ |
+ Want your rock here? → Sponsor caveman +
-## License +## Star this repo +Caveman save you token, save you money. Star cost zero. Fair trade. ⭐ + +[](https://star-history.com/#JuliusBrussee/caveman&Date) + +--- + + +Docs: +Install matrix · +Honest numbers · +Contributing · +Maintainer guide · +Issues +
+