# caveman — Token-Saving Claude Code Skill

> caveman is a Claude Code skill that compresses replies and cuts output tokens ~65% on average. Install via curl/PowerShell; toggle /caveman modes.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

1. Install the verified entrypoint:

```bash
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash
```

2. Run a first local check:

```bash
In Claude Code: /caveman full
```

3. Add a repeatable verification step:

```bash
In Claude Code: /caveman-stats
```

---

## Intro

caveman is a verified GitHub-backed asset sourced from `JuliusBrussee/caveman` with 58,095 stars and a MIT license snapshot. Best for: teams paying for long agent sessions and wanting faster, terser answers without losing technical accuracy. Works with: Claude Code and other agent CLIs; Node.js 18+ (per repo install docs). Setup time: 2 minutes.

### Quantitative notes

- ~65% output token reduction (repo benchmark)
- Setup time ~2 minutes

---

## Deep Dive

### What it solves

Use this when you need a **repeatable, team-shareable workflow** instead of one-off agent prompts. The goal is to make installation, first-run validation, and rollback **predictable**.

### Minimal mental model

- Treat the GitHub repo as the source of truth: install instructions, configs, and upgrade paths live there.
- Keep your first run small: one command, one verification, one rollback plan.
- Capture a baseline: setup time, first successful run, and one real task completed end-to-end.

### Safe rollout checklist

1. **Verify source**: confirm repo URL, stars, and license match what you expect.
2. **Install** using the Quick Use commands above.
3. **Prove it works** with the verification command; save the output in a note or issue.
4. **Operationalize**: document owner, upgrade command, and rollback command.

### Troubleshooting (common)

- **Install succeeds but nothing shows up**
  - Likely cause: the tool needs a restart/reload (CLI/IDE) or a config file in the right path.
  - Fix: restart the client, then re-run the verification step.

- **Works on one machine, fails on another**
  - Likely cause: Node/Python/Docker versions differ or missing system dependencies.
  - Fix: pin versions (Node/Python), and copy a minimal known-good config.

- **Token cost or latency is worse than expected**
  - Likely cause: tool schemas or verbose outputs get injected into context.
  - Fix: prefer smaller steps, cache results, and keep tool responses concise when possible.


---

### FAQ

**Q: Does it reduce reasoning quality?**
A: The repo notes it targets output tokens; treat it as a delivery/verbosity control rather than a reasoning upgrade.

**Q: How do I roll back?**
A: Disable by switching back to normal mode in your agent, or remove the installed skill files per the repo's uninstall guidance.

**Q: When should I avoid it?**
A: Avoid it for long-form docs where verbosity is required; keep a 'normal mode' preset for writing tasks.

---

## Source & Thanks

> GitHub: https://github.com/JuliusBrussee/caveman
> Owner avatar: https://avatars.githubusercontent.com/u/104168679?v=4
> License (SPDX): MIT
> Stars (verified via `api.github.com/repos/JuliusBrussee/caveman`): 58,095


---

<!-- ZH -->

# caveman——省 Token 的 Claude Code 技能

> caveman 是 Claude Code 技能：把回答压缩成更短、更快读的风格，README 基准显示平均可减少约 65% 输出 token。脚本一键安装，/caveman 可切换多档模式。

## 快速使用

1. 安装（以仓库为准）：

```bash
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash
```

2. 首次运行/检查：

```bash
In Claude Code: /caveman full
```

3. 可重复验证：

```bash
In Claude Code: /caveman-stats
```

---

## 简介

caveman 已核验来源于 `JuliusBrussee/caveman`（58,095 stars，许可证 MIT）。适合：经常跑长会话、token 成本敏感、希望回答更短更快但不牺牲技术准确性的团队。兼容：Claude Code 等代理 CLI；Node.js 18+（以仓库安装说明为准）。装机时间：2 分钟。

### 量化信息

- 输出 token 平均减少约 65%（仓库基准）
- 装机约 2 分钟

---

## 深度说明

### 解决什么问题

把“找到项目 → 安装 → 首次验证 → 回滚/升级”变成可复用流程，避免只靠一次性提示词或截图操作。

### 最小心智模型

- GitHub 仓库是事实来源：安装、配置、升级、已知问题都以它为准。
- 第一次只做最小闭环：一个命令安装、一个命令验证、一个可回滚方案。
- 记录基线：装机耗时、首次成功输出、完成 1 个真实任务的证据。

### 安全推广清单

1. **核验来源**：确认仓库 URL / stars / license 与预期一致。
2. 按“快速使用”完成安装与首次检查。
3. 跑通“验证命令”，把输出留档。
4. 标注 owner，并写清升级/回滚步骤。

### 常见排障

- **装了但看不到效果**
  - 常见原因：需要重启 CLI/IDE 或配置文件路径不对。
  - 处理：重启后再跑一遍“验证命令”。

- **一台机器能跑，另一台不行**
  - 常见原因：Node/Python/Docker 版本差异或缺少系统依赖。
  - 处理：固定版本，并拷贝最小可用配置。

- **token 成本/延迟超预期**
  - 常见原因：工具 schema 或输出过长被塞进上下文。
  - 处理：拆小步骤、缓存结果、尽量让工具输出更短。


---

### FAQ

**Q: 会影响推理质量吗？**
A: 仓库说明主要压缩的是输出 token；把它当作“表达/啰嗦度控制”，不是推理增强。

**Q: 怎么回滚？**
A: 切回 normal mode，或按仓库卸载说明移除安装的 skill 文件。

**Q: 哪些场景不建议用？**
A: 需要长文叙述/教学时不建议；保留一个 normal mode 预设用于写作类任务。

---

## 来源与感谢

> GitHub：https://github.com/JuliusBrussee/caveman
> Owner avatar：https://avatars.githubusercontent.com/u/104168679?v=4
> 许可证（SPDX）：MIT
> GitHub stars（已通过 `api.github.com/repos/JuliusBrussee/caveman` 核验）：58,095


---
Source: https://tokrepo.com/en/workflows/caveman-token-saving-claude-code-skill
Author: Skill Factory