caveman

why use many token when few do trick

Install • Benchmarks • Before/After • Intensity Levels • Skills • Compress • Evals • Why

---

A Claude Code skill/plugin and Codex plugin that makes agent talk like caveman — cutting ~75% of output tokens while keeping full technical accuracy. Now with 文言文 mode, terse commits, one-line code reviews, and a compression tool that cuts ~45% of input tokens every session.

Based on the viral observation that caveman-speak dramatically reduces LLM token usage without losing technical substance. So we made it a one-line install.

Before / After

🗣️ 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."	🪨 Caveman Claude (19 tokens) "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."	🪨 Caveman Claude "Bug in auth middleware. Token expiry check use < not <=. Fix:"

Same fix. 75% less word. Brain still big.

Sometimes too much caveman. Sometimes not enough:

🪶 Lite "Your component re-renders because you create a new object reference each render. Inline object props fail shallow comparison every time. Wrap it in useMemo."

🪨 Full "New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo."

🔥 Ultra "Inline obj prop → new ref → re-render. useMemo."

📜 Wenyan-Full "物出新參照，致重繪。useMemo .Wrap之。"

Same answer. You pick how many word.

Benchmarks

Real token counts from the Claude API (reproduce it yourself):

Task	Normal (tokens)	Caveman (tokens)	Saved
Explain React re-render bug	1180	159	87%
Fix auth middleware token expiry	704	121	83%
Set up PostgreSQL connection pool	2347	380	84%
Explain git rebase vs merge	702	292	58%
Refactor callback to async/await	387	301	22%
Architecture: microservices vs monolith	446	310	30%
Review PR for security issues	678	398	41%
Docker multi-stage build	1042	290	72%
Debug PostgreSQL race condition	1200	232	81%
Implement React error boundary	3454	456	87%
Average	1214	294	65%

Range: 22%–87% savings across prompts.

Important

Caveman only affects output tokens — thinking/reasoning tokens are untouched. Caveman no make brain smaller. Caveman make mouth smaller. Biggest win is readability and speed, cost savings are a bonus.

Science back caveman up

A March 2026 paper "Brevity Constraints Reverse Performance Hierarchies in Language Models" found that constraining large models to brief responses improved accuracy by 26 percentage points on certain benchmarks and completely reversed performance hierarchies. Verbose not always better. Sometimes less word = more correct.

Install

npx skills add JuliusBrussee/caveman

npx skills supports 40+ agents — Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, and more. To install for a specific agent:

npx skills add JuliusBrussee/caveman -a cursor
npx skills add JuliusBrussee/caveman -a github-copilot
npx skills add JuliusBrussee/caveman -a cline
npx skills add JuliusBrussee/caveman -a windsurf
npx skills add JuliusBrussee/caveman -a codex

Or with Claude Code plugin system:

claude plugin marketplace add JuliusBrussee/caveman
claude plugin install caveman@caveman

Codex:

1. Clone repo
2. Open Codex in repo
3. Run /plugins
4. Search Caveman
5. Install plugin

Note

Windows Codex users: Clone repo → VS Code → Codex Settings → Plugins → find Caveman under local marketplace → Install → Reload Window. Also enable git config core.symlinks true before cloning (requires developer mode or admin).

Install once. Use in all sessions after that. One rock. That it.

Usage

Trigger with:

• /caveman or Codex $caveman
• "talk like caveman"
• "caveman mode"
• "less tokens please"

Stop with: "stop caveman" or "normal mode"

Intensity Levels

Sometimes full caveman too much. Sometimes not enough. Now you pick:

Level	Trigger	What it do
Lite	/caveman lite or $caveman lite	Drop filler, keep grammar. Professional but no fluff
Full	/caveman full or $caveman full	Default caveman. Drop articles, fragments, full grunt
Ultra	/caveman ultra or $caveman ultra	Maximum compression. Telegraphic. Abbreviate everything

Level stick until you change it or session end.

文言文 (Wenyan) Mode

Caveman go ancient. Classical Chinese literary compression — same technical accuracy, but in the most token-efficient written language humans ever invented.

Level	Trigger	What it do
Wenyan-Lite	/caveman wenyan-lite	Semi-classical. Grammar intact, filler gone
Wenyan-Full	/caveman wenyan	Full 文言文. Maximum classical terseness
Wenyan-Ultra	/caveman wenyan-ultra	Extreme. Ancient scholar on a budget

English:  "Your component re-renders because you create a new object reference each render."
Caveman:  "New object ref each render. Wrap in useMemo."
Wenyan:   "物出新參照，致重繪。useMemo Wrap之。"

Same answer. Different era. Fewer token.

What Caveman Do

Thing	Caveman Do?
English explanation	🪨 Caveman smash filler words
Code blocks	✍️ Write normal (caveman not stupid)
Technical terms	🧠 Keep exact (polymorphism stay polymorphism)
Error messages	📋 Quote exact
Git commits & PRs	✍️ Write normal
Articles (a, an, the)	💀 Gone
Pleasantries	💀 "Sure I'd be happy to" is dead
Hedging	💀 "It might be worth considering" extinct

Caveman Skills

Caveman not just talk different. Caveman have tools:

caveman-commit

Terse commit messages. Conventional Commits format. Subject ≤50 chars. Body only when "why" not obvious.

❌  "feat: add a new endpoint to get user profile information from the database"

✅  feat(api): add GET /users/:id/profile

Trigger: /caveman-commit or just ask for a commit message.

caveman-review

One-line code review comments. Location, problem, fix. No throat-clearing.

❌  "I noticed that on line 42 you're not checking if the user object
    is null before accessing the email property. This could potentially
    cause a crash if the user is not found in the database."

✅  L42: 🔴 bug: user can be null after .find(). Add guard before .email.

Severity prefix tell you what matter:

• 🔴 bug: — broken, will cause incident
• 🟡 risk: — works but fragile
• 🔵 nit: — style, author can ignore
• ❓ q: — genuine question

Trigger: /caveman-review or ask for a code review.

Evals

Caveman not just claim 75%. Caveman prove it.

The evals/ directory has a three-arm eval harness that measures real token compression against a proper control — not just "verbose vs skill" but "terse vs skill". Because comparing caveman to verbose Claude conflate the skill with generic terseness. That cheating. Caveman not cheat.

# Run the eval (needs claude CLI)
uv run python evals/llm_run.py

# Read results (no API key, runs offline)
uv run --with tiktoken python evals/measure.py

Snapshots committed to git. CI runs free. Every number change reviewable as diff. Add a skill, add a prompt — harness pick it up automatically.

Why

┌─────────────────────────────────────┐
│  TOKENS SAVED          ████████ 75% │
│  TECHNICAL ACCURACY    ████████ 100%│
│  SPEED INCREASE        ████████ ~3x │
│  VIBES                 ████████ OOG │
└─────────────────────────────────────┘

• Faster response — less token to generate = speed go brrr
• Easier to read — no wall of text, just the answer
• Same accuracy — all technical info kept, only fluff removed (science say so)
• Save money — ~71% less output token = less cost
• Fun — every code review become comedy

How It Work

Caveman not dumb. Caveman efficient.

Normal LLM waste token on:

• "I'd be happy to help you with that" (8 wasted tokens)
• "The reason this is happening is because" (7 wasted tokens)
• "I would recommend that you consider" (7 wasted tokens)
• "Sure, let me take a look at that for you" (10 wasted tokens)

Caveman say what need saying. Then stop.

Caveman Compress

Caveman makes Claude speak with fewer tokens. Caveman Compress makes Claude read fewer tokens.

Your CLAUDE.md loads on every session start. A 1000-token project memory file costs you tokens every single time you open a project. Caveman Compress rewrites those files into caveman-speak so Claude reads less — without you losing the human-readable original.

/caveman:compress CLAUDE.md

CLAUDE.md          ← compressed (Claude reads this every session — fewer tokens)
CLAUDE.original.md ← human-readable backup (you read and edit this)

How it works

A Python pipeline that shells out to claude --print for the actual compression, then validates the result locally — no tokens wasted on checking.

detect file type (local)  →  compress with Claude (1 call)  →  validate (local)
                                                                    ↓
                                                              if errors: targeted fix (1 call, cherry-pick only)
                                                                    ↓
                                                              retry up to 2×, restore original on failure

What's preserved exactly

Code blocks, inline code, URLs, file paths, commands, headings, table structure, dates, version numbers — anything technical passes through untouched. Only natural language prose gets compressed.

Compress benchmarks

File	Original	Compressed	Saved
claude-md-preferences.md	706	285	59.6%
project-notes.md	1145	535	53.3%
claude-md-project.md	1122	687	38.8%
todo-list.md	627	388	38.1%
mixed-with-code.md	888	574	35.4%
Average	898	494	45%

Full-circle token savings

Tool	What it cuts	Savings
caveman	Output tokens (Claude's responses)	~65%
compress (/caveman:compress)	Input tokens (memory files loaded per session)	~45%
Both together	The whole conversation	Output + input both shrunk

Compress is built in with the caveman plugin — no separate install needed.

• Use /caveman for caveman mode
• Use /caveman:compress <filepath> for memory-file compression

Security

caveman-compress is flagged as Snyk High Risk due to subprocess and file I/O patterns detected by static analysis. This is a false positive — see SECURITY.md for a full explanation of what the skill does and does not do.

See the full caveman-compress README for install, usage, and validation details.

Star This Repo

If caveman save you mass token, mass money — leave mass star. ⭐

Also by Julius Brussee

• Blueprint — specification-driven development for Claude Code. Natural language → blueprints → parallel builds → working software.
• Revu — local-first macOS study app with FSRS spaced repetition, decks, exams, and study guides. revu.cards

License

MIT — free like mass mammoth on open plain.