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 hxy91819/mason-skills --skill html-previewgit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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/hxy91819/mason-skills/html-preview)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/html-preview"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/html-preview/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/hxy91819/mason-skills/html-preview"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/html-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.01168 |
| Opus 5 | $0.00032 | $0.00584 |
| Sonnet 5 | $0.00013 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
html-preview 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 4d 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.
What it actually says
HTML 预览发布
流程类 skill；按用户明确要求允许隐式触发，也可显式调用 $html-preview。只处理已生成且需要交付浏览器链接的静态 HTML，以及这些预览的生命周期。用户只要文件或已使用 IDE 内嵌展示并未要求服务器链接时，不额外发布。
发布前
- 确认已有可信 HTML 和交付给用户查看的需要。默认接收自包含单文件 HTML，样式/脚本内联；图表数据随文件携带。需要相对资源时先在原产物之外生成自包含副本，不能递归复制仓库、依赖目录或带凭据的配置。脚本不会分析 HTML 的全部网络请求；逐项确认外部资源可用且适合交付。只发布当前任务可信产物，不托管陌生脚本或混入生产后台。
- 读取本机
/etc/html-preview/publish.json或管理员指定配置，核实真实 HTTPS 入口、发布目录、到期状态目录及清理 timer。首次安装或基础设施缺失时读 部署与清理，完成可独立进行的文件准备并说明缺口；不擅自覆盖 Caddy、创建账号或编造地址。 - 页面和全部资源必须经过现有 Caddy/OAuth2 Proxy 统一认证，账号库可与项目预览共用；平台是否自带登录不影响该要求。新静态站点不要占用现有项目根路径。地址与凭据分开记录，不读取或输出密码、Cookie、密钥。
发布、验证、交付
使用 scripts/preview.py，参数契约见 --help。发布/续期默认 24 小时，允许 1 到 168 小时；用户说“临时看一下”无需再问 TTL，发布时必须告知到期时间。显式要求更长时先商定保留方式，不静默改成永久。
python3 /path/to/html-preview/scripts/preview.py --config /etc/html-preview/publish.json publish /absolute/path/report.html
python3 /path/to/html-preview/scripts/preview.py --config /etc/html-preview/publish.json show
脚本输出 ID、完整预览 URL、入口登录 URL、UTC 到期时间以及副本存在状态。将到期时间换算为用户时区，在回复中给出 [入口登录](实际登录URL)、[打开预览](实际URL) 和到期时间；用户已登录时可直接打开预览。只能从实际配置及命令输出取地址，不用服务器 localhost，也不把 access_verified: false 当作验收成功。
验证未登录不能取得 HTML，已登录后目标文件和必要资源可访问；只能在服务器验证时说明 Mac/用户浏览器未测。不要为查看一个 HTML 启动项目开发服务器，或绕过 TLS/认证。存在配置缺口或失效清理 timer 时明确报告，不能宣称“可点击且会自动清理”。
生命周期
- 查询
show [ID]：只读汇总登记、副本存在和到期状态；无历史内容、源文件路径或访问日志。 - 续期
renew ID --hours 24：用户仍需查看，或当前任务明确延长预览时使用；已删除的副本需从源重新发布。普通 Agent 回复、查看状态或静默访问不续期。 - 删除
delete ID：用户要求撤下或已明确不再需要时，仅删除该发布副本。 - 自动清理
gc：由 systemd timer 独立运行，只处理本脚本有效登记且到期的副本；Agent 会话结束不影响 timer。未知格式、符号链接、额外文件只报告并保留，不能为了清空目录而递归删除。
有效期是回收时间，不是严格的请求级过期控制。通常到期后一个 timer 周期内删除；停机/失败会延迟。HTML 副本的 TTL 不适用于 local-test 的项目进程；开发或等待验收的项目服务按其自身生命周期管理。
状态与失败边界
本机状态是发布/删除的事实源，由脚本在文件锁内原子更新，放在发布根之外、Git 外。只记 ID、目录绑定摘要、创建/到期时间与格式版本，不存 prompt、源路径、正文、凭据。发布先登记再复制，中断留下的空副本仍可到期回收；gc 单条失败继续检查其他记录，并以非零退出码及错误列表报告。
当前提供 show 即时汇总，没有长期运行历史、裁决回写或滚动统计；不把它描述为完整审计。自动清理只减少已登记副本，异常记录保留待处理，不强行折算或丢弃。源 HTML 始终由原任务自行保留。
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.
- 4d ago First seen · 43 lines · 63 tokens per session scan A da84ab7b48bb
html-preview is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,168 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
baoyu-url-to-markdown
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
fetching-and-converting-urls
Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
url2ebook
A web-page converter that fetches the main content from a URL and creates an ebook for offline reading. The output is generated as an ebook file.
puppeteer-skill
Generates Puppeteer scripts for browser automation, scraping, and PDF generation. Triggers on: "Puppeteer", "headless Chrome", "page.goto", "scrape", "PDF generation".
km-content-extraction
Content extraction routing for KM - local documents (HWP/HWPX/PDF/DOCX/XLSX), web, and vault sources. Use when input is a local file or when km-workflow reaches Phase 2 with a non-URL input.
thumbnail-of-pptx
Capture a thumbnail image of a slide from a OneDrive/Office presentation link. Opens the PowerPoint web viewer in a headless browser and screenshots the slide canvas, producing a clean 16:9 image with no viewer chrome. Works even when the PPTX is not downloadable (e.g. personal OneDrive shares), since it screenshots…