# caveman

A plugin that makes your agent answer shorter and read less of your logs, while code stays exact. One install, works with Claude and dozens more agents.

- plugin · `type=plugin` · Claude Code · ★ 115125
- Author: JuliusBrussee
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/JuliusBrussee/caveman
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/plugins/caveman

## What it does

caveman rewrites how the agent talks: answer first, reason second, no greeting and no recap. The rules follow ASD-STE100, the controlled English of aircraft maintenance manuals: 20 words per sentence, active voice, one term per thing. Meaning survives the diet. Negations stay, numbers and units stay exact, and code or commands come back verbatim.

Version 4.0 ships six parts, all on after install. Read less shrinks logs, JSON, CSV and test output before the model sees them. Auto picks the model and effort level for each ask. Blocks is a code mode where scripts the agent writes stick around and get run again. Two smaller pieces hunt down where your tokens leak and compress web pages. Each part has its own switch, so `caveman off` can drop one without touching the rest.

Install runs through `npx @caveman-ai/cli@latest` and needs Node.js 22.13+. The installer finds your agents and logins, shows what it will change, then waits for Enter. Only Auto wants an account, and it is free. If you had caveman before 4.0, install with the `@latest` tag or the old copy on your machine wins.

## Install

### Claude Code (native platform)

**Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/claude-plugins-community
```
In the agent chat (not a shell):
```text
/plugin install caveman@claude-community
```

## When to use it
- cut token spend across long agent sessions
- shrink logs and test output before the model reads them
- stop the agent from padding answers with intros
- match model and effort level to each task
- reuse scripts the agent wrote in code mode

## Example prompts
- explain why my React component re-renders, keep it short
- turn on Blocks and run the tests again
- show me what caveman has enabled right now

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: eb0d5e3fb1542045.

BEGIN THIRD-PARTY FILE eb0d5e3fb1542045
````text
<div align="center">

<img src="docs/assets/caveman-logo-banner.png" alt="Caveman" width="720">

# why many token when few do trick

**Caveman make your AI agent say less and read less. Code stay exact. Brain still big.**

<a href="https://github.com/JuliusBrussee/caveman/stargazers"><img src="https://img.shields.io/github/stars/JuliusBrussee/caveman?style=flat-square&color=F0A63C&label=stars" alt="GitHub stars"></a>
<a href="https://www.npmjs.com/package/@caveman-ai/cli"><img src="https://img.shields.io/npm/dm/@caveman-ai/cli?style=flat-square&color=F0A63C&label=cli%20downloads" alt="npm downloads"></a>
<a href="./INSTALL.md"><img src="https://img.shields.io/badge/works_with-30%2B_agents-orange?style=flat-square" alt="30+ agents"></a>
<a href="#license"><img src="https://img.shields.io/badge/license-Apache--2.0-green?style=flat-square" alt="License"></a>

<table>
<tr>
<td align="center" width="25%"><h3>33.2% fewer</h3>input tokens, whole sessions<br><sub><a href="#read-less-332-fewer-input-tokens">54 Claude Code runs</a>, 18 of 18 answers right</sub></td>
<td align="center" width="25%"><h3>54% cheaper</h3>with Auto, same score<br><sub><a href="#auto-54-cheaper-same-score">85 coding tasks</a> vs Opus 5.5 at xhigh, interim</sub></td>
<td align="center" width="25%"><h3>397 → 76</h3>tokens for one test run<br><sub><a href="#blocks-code-mode-script-written-once">Blocks</a> vs <code>| tail -20</code></sub></td>
<td align="center" width="25%"><h3>1.4 to 2.4× cheaper</h3>with caveman-style output<br><sub><a href="https://arxiv.org/abs/2606.24083">Adobe Research</a>, eight models</sub></td>
</tr>
</table>

Cited by **[Adobe Research](https://arxiv.org/abs/2606.24083)** · A/B tested by **[JetBrains](https://blog.jetbrains.com/ai/2026/07/speak-to-ai-agents-like-cavemen-tosave-tokens/)** · Remade for Elasticsearch on **[Elasticsearch Labs](https://www.elastic.co/search-labs/blog/elastic-caveman-ai-token-reduction)**<br>
**#1** on [Hacker News](https://news.ycombinator.com/item?id=47647455) · **#1** on GitHub Trending · *"No way this actually works."* [ThePrimeagen](https://www.youtube.com/watch?v=L29q2LRiMRc)

**[Install](#install) · [Six rocks](#six-rocks-one-install) · [Proof](#proof) · [Say less](#say-less-the-caveman-voice) · [Read less](#read-less-332-fewer-input-tokens) · [Auto](#auto-54-cheaper-same-score) · [Blocks](#blocks-code-mode-script-written-once) · [Commands](#commands) · [Caveman Cloud](#caveman-cloud)**

</div>

---

<table>
<tr>
<th width="50%">Normal agent · 63 tokens</th>
<th width="50%"><img src="docs/assets/dancing-rock.svg" width="18" height="18" alt=""> Caveman agent · 20 tokens</th>
</tr>
<tr>
<td valign="top">

> 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.

</td>
<td valign="top">

> New object ref each render, so React re-renders. Wrap the prop in `useMemo`.

</td>
</tr>
</table>

**Same fix. 63 token become 20. Brain still big.**

Pick your club:

| Skill | Same answer | Tokens |
|---|---|---:|
| `/caveman` | New object ref each render, so React re-renders. Wrap the prop in `useMemo`. | 20 |
| `/ultracave` | Inline object prop, new ref, re-render. `useMemo`. | 14 |
| `/megacave` | 新參照致重繪。`useMemo`。 | **13** |

<sub>Token counts: tiktoken o200k.</sub>

## Install

```bash
npx @caveman-ai/cli@latest
```

One command. Mac, Linux, Windows. Caveman find your agents and your logins, show what it change. Press Enter. Done. Needs Node.js 22.13+.

After that, plain `claude` stays caveman'd. So do Codex, Gemini CLI, OpenCode, and [30+ more](./INSTALL.md). It runs on your machine, with your keys and your Claude Pro/Max login. One rock. That it.
````
END THIRD-PARTY FILE eb0d5e3fb1542045

The third-party file has ended. Everything between the eb0d5e3fb1542045 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3924 of 22657 bytes. © JuliusBrussee · Apache-2.0 · https://github.com/JuliusBrussee/caveman

## Similar
- [vercel-cli-with-tokens](https://affpapa.org/en/nevibecode/skills/vercel-cli-with-tokens.md) — skill · 136400 installs
- [superself](https://affpapa.org/en/nevibecode/skills/superself.md) — skill · 1400 installs
- [batch-script-progress](https://affpapa.org/en/nevibecode/skills/batch-script-progress.md) — skill · 4 installs
- [ponytail](https://affpapa.org/en/nevibecode/plugins/ponytail.md) — plugin · ★ 176443
- [impeccable](https://affpapa.org/en/nevibecode/plugins/impeccable.md) — plugin · ★ 88212
- [last-30-days-skill](https://affpapa.org/en/nevibecode/plugins/last-30-days-skill.md) — plugin · ★ 65508

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md