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 agentmods add skills/xerrors/yuxi/html-previewnpx skills add xerrors/Yuxi --skill html-previewgit clone --depth 1 https://github.com/xerrors/YuxiWhat 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 | $0.00086 | $0.00782 |
| Opus 5 | $0.00043 | $0.00391 |
| Sonnet 5 | $0.00017 | $0.00156 |
| Haiku 4.5 | $0.00009 | $0.00078 |
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 yesterday.
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 Preview
将 Markdown 作为回答主体。只有可视化能明显降低理解成本时，才补充一个
html:preview 静态组件；标题、列表、表格或代码块已经足够清楚时，继续使用普通 Markdown。
按以下顺序输出：
- 先用普通 Markdown 写结论和必要解释。
- 顶格写开始围栏
```html:preview。围栏最多只能有 3 个前导空格，否则前端会把它当作源码。 - 在围栏内写自包含的静态
<style>和语义化 HTML。 - 顶格写结束围栏
```。 - 在围栏后用普通 Markdown 补充背景、风险、完整明细和来源。
内容边界
- 只输出静态 HTML/CSS，不编写 JavaScript，不使用表单、iframe、object 或 embed。
- 可以引用公开、稳定、无需登录的 HTTPS 图片或字体，但核心信息必须在外链失败时仍然可读。
- 不引用内网、临时地址、鉴权资源或包含用户凭证的链接。
- 不把组件当成完整网页或正文容器；不要制作导航栏、页脚、登录态、复杂按钮、营销页 Hero 或多屏页面。
- 不在组件中放长段叙事、完整报告、长表格或长列表。背景、推理、风险、明细和来源放在普通 Markdown 中。
- 用户询问 HTML 源码、教程示例或需要复制代码时，使用普通
html代码块，不使用html:preview。
布局约束
- 面向默认
800px × 360px尺寸设计，并允许容器宽度变化；前端最高显示到700px，超出后在预览内部滚动。 - 使用
max-width: 100%、box-sizing: border-box、弹性网格、换行和适度间距保持响应式。 - 不写死整体画布高度。核心信息应在默认尺寸内无需滚动即可读；放不下时减少内容。
- 最多展示 1 个短标题、3–5 个关键指标或一组简短对比。数据超过 6 项时，汇总为趋势、区间、异常点或 Top 3。
- 文字以短标签、数字、单位、状态词和极短备注为主；单条说明尽量不超过 20 个中文字符。
- 外层已经提供圆角、边框和裁切。不要再给最外层添加卡片壳、页面背景、大圆角、阴影、厚边框或额外外边距。
- 保持克制和可读，优先使用紧凑指标组、摘要表、对比条、状态标签、时间轴或简单关系图。
失败处理
如果内容无法在上述静态、安全和篇幅边界内表达，改用普通 Markdown，并明确说明限制。不要输出残缺围栏、不可访问资源或依赖脚本才能理解的预览。
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.
- yesterday First seen · 41 lines · 86 tokens per session scan A b481d22101eb
html-preview is a skill published in the GitHub repository xerrors/Yuxi (6,591 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 782 once invoked, about $0.0004 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
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
channel-bot
Work with messaging-channel bots (Telegram / Slack) — register a bot, route inbound messages through the AI agent, handle webhooks vs polling, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery.