Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SpaceZephyr/build-your-harness --skill view-your-harnessgit clone --depth 1 https://github.com/SpaceZephyr/build-your-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/spacezephyr/build-your-harness/view-your-harness)<a href="https://agentmods.dev/skills/spacezephyr/build-your-harness/view-your-harness"><img src="https://agentmods.dev/badge/skills/spacezephyr/build-your-harness/view-your-harness/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/spacezephyr/build-your-harness/view-your-harness"><img src="https://agentmods.dev/badge/skills/spacezephyr/build-your-harness/view-your-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00170 | $0.01773 |
| Opus 5 | $0.00085 | $0.00886 |
| Sonnet 5 | $0.00034 | $0.00355 |
| Haiku 4.5 | $0.00017 | $0.00177 |
Grade A, and why
view-your-harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
view-your-harness
把一个本地目录清点成一个能浏览、能搜、能点开的工作台。
跟另外两个是一套：star-your-harness 负责搭， better-your-harness 负责体检，这个负责日常看。
体检回答「我这儿哪里有问题」，工作台回答「我这儿都有什么」。后者是前者的前置—— 155 个 Skill 你根本记不住有哪些，2000 篇笔记散在 52 个目录里你也找不着， 这种时候需要的不是一份报告，是一个能翻的架子。
铁律
1. 只读。这个 Skill 不改用户任何文件。
服务端没有写、改、删接口，这是设计约束不是待办。「可操作」的边界就是打开和定位——
调系统的 open 把文件交给用户自己的编辑器和访达。用户要改东西，让他在编辑器里改，
或者去用 better-your-harness 的修复口令。不要为了「更方便」私自加写接口。
2. 所有路径都必须校验落在 root 之内。
serve.py 的 safe_join 会 resolve 后比对，越界返 403。Skill 卡片的绝对路径额外白名单
~/.claude 和 ~/.codex。改动服务端代码时不要绕过这一层——它是本地服务唯一的边界。
3. 数字只能来自 index.py，你不许在对话里编。
文件数、Skill 数、调用次数，全部以 index.json 为准。脚本没统计的量就说「未统计」。
流程
1. 起服务
python3 ~/.claude/skills/view-your-harness/scripts/serve.py <目录>
它会先跑一遍索引（几秒到半分钟，看目录大小），然后起服务、自动开浏览器。 终端会打印端口和实际盘的路径。Ctrl-C 停止。
常用参数：
| 参数 | 用途 |
|---|---|
--port 7799 |
指定端口。被占用会自动往后顺延，一般不用管 |
--no-open |
不自动开浏览器（远程/无头环境） |
--no-usage |
跳过会话日志统计。日志多的时候能快很多，代价是没有调用次数 |
这是个前台进程。 用 run_in_background 起，把 URL 报给用户，不要傻等它退出。
2. 交付
告诉用户三件事就够了：地址、盘的是哪个目录、按 Ctrl-C 停。 然后用一两句话说说清点结果里最扎眼的是什么（比如「155 个 Skill 里 130 个从未调用过」）。
**不要把文件清单在对话里念一遍。**清单就在页面上，念一遍等于把工作台又变回了聊天记录。
只要数据不要界面时
需要拿清点结果做别的分析（比如喂给另一个 Skill），单独跑索引器就行：
python3 ~/.claude/skills/view-your-harness/scripts/index.py <目录> -o /tmp/index.json
工作台里有什么
顶栏：目录路径、文件数、目录数、总体量、Skill 数、用过 / 没用过。
一个搜索框同时搜文件名、文档标题、Skill 名称和描述。按 / 聚焦，Esc 关抽屉。
文件页
- 左侧按文件数排的一级目录，点击下钻
- 卡片显示文档标题（Markdown 的 frontmatter title 或第一个
#，比文件名有用得多）、 类型、体量、最近改动 - 按类型筛（文档/代码/数据/图片/音视频/配置），按最近改动 / 体量 / 名称排
Skill 页
- 每个 Skill 一张卡：名字、description、真实调用次数、文件数、体量、最后更新
- 筛选：全部 / 用过 / 从未调用 / 元信息不全 / 项目级
- 左侧列出 Skill 的所有来源目录，以及
skills/根下的裸.md文件—— 那些不是 Skill，永远不会被加载，属于该清理的东西
抽屉：点任意卡片右侧滑出。文本文件看内容，图片直接显示，Skill 看 SKILL.md 全文。 三个动作：打开（交给系统默认程序）、在访达中显示、复制绝对路径。
同名 Skill 会被折叠。全局装一份、插件市场又带一份的情况很常见， 按 项目 > 全局 > 插件 留优先级最高的那条，否则「用过几个」会被重复计数， 出现「8 个用过但只有 10 次调用」这种自相矛盾的数字。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 124 lines · 170 tokens per session scan A 301de803a305
view-your-harness is a skill published in the GitHub repository SpaceZephyr/build-your-harness (29 stars, last pushed 25d ago), licensed MIT. It adds 170 tokens to every session and 1,773 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ask-opencli
A helper for asking Grok or Gemini through OpenCLI, which uses an already signed-in Chrome browser session instead of a paid API.
frontend-design
Create distinctive, production-grade web frontend interfaces with high design quality. Use when the user explicitly asks to build or substantially redesign a web component, page, or application. Only applies when repository inspection confirms that the visual surface is a browser-rendered web UI. Do not use for native…
playwright-automation
Browser automation and testing with Playwright. Use when testing web applications, automating browser tasks, taking screenshots, or validating UI behavior.
aside-notification-activation
Enable browser notifications on websites for monitoring and event-driven routine flows.
cli-anything-macrocli
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes macro run and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.