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/nullskymc/aurevoy/visualizenpx skills add nullskymc/Aurevoy --skill visualizegit clone --depth 1 https://github.com/nullskymc/AurevoyWhat 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 | $0.00079 | $0.01551 |
| Opus 5 | $0.00039 | $0.00776 |
| Sonnet 5 | $0.00016 | $0.00310 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
visualize 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize
使用 present_ui(kind="canvas") 将交互式可视化直接放入对话流。Canvas 在 sandbox iframe 中运行,HTML、CSS、JavaScript 与数据均不离开该片段;不要改为 HTML 文件附件,也不要声称它是应用页面。
数据与范围
- 先定位用户给出的 CSV、TSV、JSON、Excel 或工作区数据文件,读取少量样本与字段名,确认单位、时间范围、缺失值和唯一标识。
- 数据不存在时,简洁请求文件或路径。仅当用户明确说“随便生成”“示例”或“看看效果”时,才创建并标注为合成演示数据。
- 只保留支撑交互与详情的字段。大数据集先聚合、分箱或抽样,避免把原始大文件完整内联。
- 选择最小合适的图形:数值关系用散点/折线,分类比较用条形图,构成变化用堆叠图,密集类别用可选择网格;地理数据必须使用真实的 GeoJSON/经纬度与投影。
创建 Canvas
- 调用
present_ui,固定kind="canvas"。根对象只能有kind、id、fallbackText、props;title、description、html、css、script、state都必须放在props内。props.html必须是 HTML fragment(不是完整文档),交互时再提供script;给稳定的id,后续更新时复用它。 - 使用内联数据、CSS 和 JavaScript。不要使用
fetch、XHR、WebSocket、远程 CDN、外部图片、parent、top、opener或其他宿主窗口 API。 - 只添加用户要求的筛选、选择或参数控件;使用语义化的
label、select、input、button和原生键盘交互。筛选变化必须立刻更新主图、列表/表格和选中详情。 - 保持一个主视觉、紧凑的已选项详情和必要的图例。默认不做 KPI 卡;只有用户明确要求且指标随交互变化时,最多保留三个。不要堆砌装饰性状态块、搜索框或“重置”按钮。
- 让图表本身可读:标注轴、单位、关键值和多系列图例;颜色之外同时使用形状、文字或线型。为 SVG/Canvas 提供标题、描述或等价可访问文本。
- 设计为窄宽度也可用:避免固定视口高度、水平溢出、固定定位和内部滚动;控件在窄屏换行,表格过宽时提供响应式容器。
- 所有用户输入与交互状态保留在 Canvas 内。
window.aurevoy.state只读地提供初始状态;不要尝试向宿主发送消息或读取宿主数据。
Aurevoy 视觉语言
Canvas 是 Aurevoy 对话的一部分,不是独立网页或通用暗色 dashboard。外层卡片已经展示 props.title 与 props.description,因此 HTML fragment 内不要重复标题、日期横幅或第二层页面容器。
- 颜色必须使用 Canvas 已注入的主题变量:
--av-bg、--av-surface、--av-text、--av-muted、--av-border、--av-accent、--av-accent-contrast、--av-accent-soft-bg、--av-accent-soft-fg。不要硬编码整套浅色/深色调色板、Tailwind 色值、白色卡片或黑灰背景;深浅主题必须自然切换。 - 根节点保持透明、无边框、无阴影、全宽。只在必要的选中详情或少量动态指标上使用一个低强调 surface;不要给每条列表项、分组或布局容器重复套卡片。
- 延续项目的克制留白与 Mist Teal 强调:正文使用
--av-text,辅助信息用--av-muted,只将--av-accent用于当前选中态、关键标记和一个主要操作。不要把多种鲜艳颜色当作装饰。 - 片段内不使用
<h1>,也不重述用户请求。标题交给props.title;图例、坐标、数值和当前选中项才留在片段中。 - 控件必须使用原生
<button>、<input>、<select>、<textarea>,并保留浏览器焦点样式。不要用可点击的<div>、伪 tab 或仅靠颜色表达选中状态;筛选 tab 要用button,并提供aria-pressed或aria-selected。 - 列表或新闻流默认只展示摘要;点击或键盘选择一项后才显示该项详情。不要让全部条目在首屏同时展开。卡片点击区域应是明确的
button,而不是整个div。
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.
- 2d ago First seen · 54 lines · 79 tokens per session scan A 9128f9341d32
visualize is a skill published in the GitHub repository nullskymc/Aurevoy (10 stars, last pushed 26d ago), licensed MIT. It adds 79 tokens to every session and 1,551 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 2026-08-31.
Other skills, from other repositories
create_profile_style_skill
【META SKILL】分析当前剪辑逻辑与风格,总结并生成一个新的可复用 Skill 文件,存入剪辑技能库。Analyze the current editing logic and style, summarize and generate a new reusable Skill file, and store it in the editing skill library.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
Paper Writing Workflow
Workflow phases for paper-writing tasks: triage, material inventory, research question, literature review, paper outline, data analysis summary, figure storyline, reader testing, and finalize packet. Each phase is a short contract — read the relevant rows for the current task only.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
deep-researcher
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.
llmtornado-tutorial-generator
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.