🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
> /plugin marketplace add JuliusBrussee/caveman> /plugin install caveman@caveman
Repo: JuliusBrussee/caveman
What's inside
Caveman is a skill/plugin for 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.
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.
New object ref each render. Inline object prop = new ref = re-render. Wrap in
useMemo.
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.
Bug in auth middleware. Token expiry check use
<not<=. Fix:
Same fix. Third of the words. Nothing technical lost.
┌────────────────────────────────────────────┐
│ output tokens saved █████████ 65% │
│ input tokens saved ░░░░░░░░░ 0% │
│ technical accuracy █████████ 100% │
│ vibes █████████ OOG │
└────────────────────────────────────────────┘
Caveman no make brain smaller. Caveman make mouth smaller. Shrinks what the agent says, not what it knows.
That 65% is the prose number, measured on replies like the ones above. On a full agentic coding run, where most of the output is code and tool calls, it's 8.5%. Same skill, different workload — mechanism below.
One command. Finds every agent on your machine. Installs for each.
# macOS · Linux · WSL · Git Bash
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash
# Windows · PowerShell 5.1+
irm https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.ps1 | iex
~30 seconds. Needs Node ≥18. Skips agents you no have. Safe to re-run.
Prefer one agent at a time? Each has its own path:
# Claude Code plugin
claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@caveman
# Gemini CLI extension
gemini extensions install https://github.com/JuliusBrussee/caveman --consent
# Cursor / Windsurf / Cline / Codex / 30+ more, via the skills registry
npx skills add JuliusBrussee/caveman -a cursor
The full per-agent matrix, all flags, dry-run, and uninstall live in INSTALL.md.
[!TIP] Turn it on: type
/cavemanor say "talk like caveman". Turn it off: say "normal mode". On Claude Code, Codex, and Gemini it's already on from message one. No command needed.
Install broke? Open your agent in this repo and say: "Read CLAUDE.md and INSTALL.md, install caveman for me." Agent read repo, agent fix own brain. Snake eat tail.
Six levels. Switch anytime with /caveman <level>. Level sticks until you change it or the session ends.
| Level | Same sentence, shrunk |
|---|---|
| normal agent | You should wrap the object in useMemo, since a new reference is created on every render. |
lite | Wrap object in useMemo. New ref created every render. |
full (default) | New ref each render. Wrap object in useMemo. |
ultra | New ref/render. useMemo it. |
wenyan | New ref every render, so wrap in useMemo — rendered in classical Chinese, shorter still. |
[!NOTE] Speak your tongue. Caveman keeps your language. Write Portuguese, caveman grunt Portuguese. Spanish, French, same. It compresses the style, never translates.
wenyanmode is the exception on purpose: classical Chinese packs the most meaning per token.
| Command | What it does |
|---|---|
/caveman [lite|full|ultra|wenyan] | Compress every reply. Level sticks for the session. |
/caveman-commit | Conventional Commit messages, ≤50-char subject. Why over what. |
/caveman-review | One-line PR comments: L42: 🔴 bug: user null. Add guard. |
/caveman-stats | Real session token usage, lifetime savings, USD. Tweetable line with --share. |
/caveman-compress <file> | Rewrite a memory file (like CLAUDE.md) into caveman-speak. Cuts ~46% input tokens every session after. Code, URLs, paths byte-preserved. |
caveman-shrink | MCP middleware. Wraps any MCP server, compresses its tool descriptions. npm. |
cavecrew-* | Caveman subagents (investigator, builder, reviewer). ~60% fewer tokens than vanilla, so main context lasts longer. |
[!TIP] On Claude Code the statusline shows
[CAVEMAN] ⛏ 12.4k— that's your lifetime tokens saved, updated on every/caveman-stats. Silence it withCAVEMAN_STATUSLINE_SAVINGS=0.
Real token counts from the Claude API. Average 65% output reduction across 10 chat-style prompts (range 22–87%), measured against default verbose replies. Output tokens only, committed and reproducible in benchmarks/ and evals/. This is one-question-one-answer, not a full agentic coding run — for that number, see JetBrains below.
| Task | Normal | Caveman | 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% |
[!IMPORTANT] Honest number warning. Caveman only shrinks output tokens. Input and reasoning tokens are untouched, and the skill itself adds ~1–1.5k input tokens per turn. So whole-session savings run smaller than the output number, and on already-terse workloads they can go net-negative. The real win is readability and speed. Cost savings are the bonus. When caveman wins, when it loses, and how to measure it yourself: docs/HONEST-NUMBERS.md.
JetBrains ran the skill against 86 tasks from SkillsBench in July 2026 — real coding work, auto-graded by each task's own tests, Claude Code on claude-sonnet-5, skill forced on for every reply.
| Workload | Output tokens saved | Measured by |
|---|---|---|
| Chat-style prose | 65% | us, table above |
| Agentic coding run | 8.5% | JetBrains, 86 tasks |
Both numbers are real. They measure different workloads, and the gap is mechanical: caveman compresses narration and leaves code, diffs, tool calls, and error strings byte-exact. In a chat answer, narration is the whole reply. In an agentic run it's the thin layer between tool calls, so that's all there is to squeeze. An output-only skill has a low ceiling on work that is mostly not prose.
Pick the number that matches your workload:
Quality was unaffected: across 86 auto-graded tasks the two arms were statistically indistinguishable. Small mouth, same brain — checked by someone who didn't ship it.
Two things follow:
/caveman-compress and caveman-shrink chip at that side; the skill alone never will.Turns out short isn't just cheaper. A March 2026 paper, Brevity Constraints Reverse Performance Hierarchies in Language Models, tested 31 models and found that constraining large models to brief answers improved accuracy by ~26 points on some benchmarks. Sometimes less word = more correct.
| File | Original | Compressed | Saved |
|---|---|---|---|
claude-md-preferences.md | 706 | 285 | 59.6% |
project-notes.md | 1145 | 535 | 53.3% |
claude-md-project.md | 1122 | 636 | 43.3% |
todo-list.md | 627 | 388 | 38.1% |
mixed-with-code.md | 888 | 560 | 36.9% |
| Average | 898 | 481 | 46% |
Every session after, that file loads ~46% smaller. Input tokens saved forever, not just one reply.
This skill shrinks what an agent says. 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.
npm install -g @juliusbrussee/caveman-code
Five tools, one idea: agent do more with less.
| Repo | What it shrinks |
|---|---|
| caveman (you here) | What the agent says |
| caveman-code | The whole agent, end to end |
| cavemem | What the agent remembers, across sessions |
| cavekit | The build loop — spec-driven, no guessing |
| cavegemma | The compression baked into weights (Gemma fine-tune) |
JuliusBrussee/skills — works in Claude Code, Cursor, Gemini, Cline, Copilot, 40+ agents:
| Skill | What |
|---|---|
| caveman | This one. Speak less, say more. |
| grill-me | Agent grills your plan before you build the wrong thing. |
| interface-kit | Build UI that looks good, loads fast, works for everyone. |
| junior-to-senior | Adversarial review pass. Junior output in, senior output out. |
| loop-factory | Spec-driven task loop — inbox → active → archive. |
npx skills@latest add JuliusBrussee/skills
OpenClaw is a self-host gateway: one box, many agents inside, wired to Slack / Discord / iMessage / Telegram. Lobster strong. Lobster smart. Lobster also talk a lot.
Same installer, scoped to one agent:
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash -s -- --only openclaw
Two things happen, no more: a caveman skill lands in the workspace, and a tiny marker-fenced block is appended to SOUL.md (OpenClaw injects it every turn, so the lobster is terse from message one — no /caveman per session). Custom path? OPENCLAW_WORKSPACE=/your/path. Uninstall with the same line plus --uninstall; your other workspace content stays untouched. Lobster claw still sharp. Lobster mouth now small.
Caveman make token small. Caveman 2 make it provable.
Today's savings numbers (including /caveman-stats) are local estimates. Caveman 2 measures and verifies them across a whole team — real receipts, real dashboard, real proof the tokens went down. Building it now.
The JetBrains result is the argument for it. 65% and 8.5% are both correct, and neither one is your number — one harness, one model, one task set, and your stack is none of those. The fix is not a better README claim, ours or anyone's. It's a baseline on your own traffic and a receipt at the end of the month.
Join the waitlist → caveman.so
/caveman./caveman-stats reads your session log, counts tokens saved, writes the number to your statusline./caveman-compress rewrites memory files (like CLAUDE.md) so every future session starts with a smaller context. Save tokens forever, not just once.Hook architecture, file ownership, and CI sync are documented for maintainers in CLAUDE.md.
Caveman no phone home. No telemetry, no analytics, no accounts, no backend. After install, zero network calls — the skill is a prompt, the hooks are local scripts, and /caveman-stats reads a log already on your disk. Install-time fetches (GitHub plus your agents' own registries) are spelled out in SECURITY.md.
Caveman free forever. Sponsors keep the rock sharp.
Caveman save you token, save you money. Star cost zero. Fair trade. ⭐
.claude-plugin/
marketplace.json
plugin.json
.codex/
config.toml
hooks.json
.editorconfig
.gitattributes
.github/
FUNDING.yml
ISSUE_TEMPLATE/
bug_report.md
feature_request.md
workflows/
ci.yml
sync-skill.yml
.gitignore
agents/
AGENTS.md
cavecrew-builder.md
cavecrew-investigator.md
cavecrew-reviewer.md
benchmarks/
prompts.json
requirements.txt
results/
.gitkeep
run.py
CLAUDE.md
cli/
install.js
lib/
openclaw.js
opencode-agent.js
settings.js
CODE_OF_CONDUCT.md
commands/
caveman-commit.md
caveman-commit.toml
caveman-init.md
caveman-init.toml
caveman-review.md
caveman-review.toml
caveman-stats.md
caveman-stats.toml
caveman.md
caveman.toml
CONTRIBUTING.md
dist/
caveman.skill
docs/
.nojekyll
assets/
atlas-cloud-dark.svg
atlas-cloud.svg
caveman-logo-banner.png
dancing-rock-32.png
dancing-rock.svg
star-history.png
HONEST-NUMBERS.md
index.html
install-windows.md
evals/
llm_run.py
measure.py
plot.py
prompts/
en.txt
README.md
snapshots/
results.json
gemini-extension.json
GEMINI.md
INSTALL.md
install.ps1
install.sh
LICENSE
package.json
plugins/
caveman/
.codex-plugin/
plugin.json
agents/
cavecrew-builder.md
cavecrew-investigator.md
cavecrew-reviewer.md
assets/
caveman-small.svg
caveman.svg
skills/
cavecrew/
SKILL.md
caveman/
caveman-compress/
scripts/
__init__.py
__main__.py
benchmark.py
cli.py
compress.py
detect.py
validate.py
SKILL.md
caveman-stats/
SKILL.md
agents/
openai.yaml
assets/
caveman-small.svg
caveman.svg
SKILL.md
README.md
SECURITY.md
skills/
skills-lock.json
cavecrew/
README.md
SKILL.md
caveman/
caveman-commit/
README.md
SKILL.md
caveman-compress/
README.md
scripts/
__init__.py
__main__.py
benchmark.py
cli.py
compress.py
detect.py
validate.py
SECURITY.md
SKILL.md
caveman-help/
README.md
SKILL.md
caveman-review/
README.md
SKILL.md
caveman-stats/
README.md
SKILL.md
README.md
SKILL.md
src/
hooks/
cavecrew-model-overrides.js
caveman-activate.js
caveman-config.js
caveman-mode-tracker.js
caveman-parse.js
caveman-stats.js
caveman-statusline.ps1
caveman-statusline.sh
checksums.sha256
install.ps1
install.sh
package.json
README.md
uninstall.ps1
uninstall.sh
mcp-servers/
caveman-shrink/
compress.js
index.js
package.json
README.md
spawn-options.js
plugins/
opencode/
commands/
caveman-commit.md
caveman-compress.md
caveman-help.md
caveman-review.md
caveman-stats.md
caveman.md
package.json
plugin.js
README.md
rules/
caveman-activate.md
caveman-openclaw-bootstrap.md
tools/
caveman-init.js
tests/
caveman-compress/
claude-md-preferences.md
claude-md-preferences.original.md
claude-md-project.md
claude-md-project.original.md
mixed-with-code.md
mixed-with-code.original.md
project-notes.md
project-notes.original.md
todo-list.md
todo-list.original.md
installer/
e2e.dryrun.test.mjs
e2e.freshinstall.test.mjs
hermes.test.mjs
opencode-agent.test.mjs
opencode.test.mjs
ps1-pipe.test.mjs
slash-commands.test.mjs
unit.argv.test.mjs
unit.settings.test.mjs
test_cavecrew_model_overrides.js
test_caveman_init.js
test_caveman_parse.js
test_caveman_stats.js
test_compress_safety.py
test_detect.py
test_hooks.py
test_mcp_shrink.js
test_mode_tracker_stdin.js
test_mode_tracker.py
test_repo_local_config.js
test_symlink_flag.js
test_validate_inline.py
verify_repo.pyA Claude Code plugin that turns natural language into blueprints, blueprints into parallel build plans, and build plans into working software with automated iteration, validation, and cross-model peer review.
@juliusbrusseeFAQ
caveman is a Claude Code plugin with 11 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes cavecrew, caveman-compress, caveman-stats. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.