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.
git clone --depth 1 https://github.com/loonghao/auroraviewWrote 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/rules/loonghao/auroraview/02-tech-stack)<a href="https://agentmods.dev/rules/loonghao/auroraview/02-tech-stack"><img src="https://agentmods.dev/badge/rules/loonghao/auroraview/02-tech-stack/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/rules/loonghao/auroraview/02-tech-stack"><img src="https://agentmods.dev/badge/rules/loonghao/auroraview/02-tech-stack.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 | $0.01050 | $0.01050 |
| Opus 5.5 | $0.00420 | $0.00420 |
| Sonnet 5.5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
02-tech-stack 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
核心技术栈（2025）
- Windows: WebView2（Chromium Edge）+ Rust（windows-rs, webview2-com），以"父 HWND 子窗口"方式内嵌至 Qt 容器；UI 操作在 STA 线程执行
- 跨 DCC：Maya/3ds Max/Houdini/Nuke 使用 Qt 宿主；Blender 采用浮动工具窗
- Python 包：仅一个 .pyd（pyo3 + maturin），不引入第三方 Python 依赖
- 并发模型：Rust 侧消息桥与调度，Qt 负责事件循环；Rust 不接管消息泵
- 跨平台路线：macOS（WKWebView）、Linux（WebKitGTK 或 CEF/OSR）按需启用
- 最低需要支持python-3.7
- 我们的项目和环境管理使用
uv来管理 Python 依赖，使用just作为任务运行器
# 使用 just 运行任务
just build # 构建项目
just test # 运行测试
just lint # 运行代码检查
# 使用 uv 管理 Python 环境
uv pip install -e . # 安装 Python 包
uv run pytest # 运行 Python 测试
HTML / 静态资源加载策略
- 内联 HTML：
WebView.load_html(html: str)，适用于简单原型或不依赖本地静态资源的页面 - 本地静态站点：优先使用
WebView.load_url("file:///.../index.html")加载磁盘上的 HTML 文件；相对路径的图片/CSS/JS 由浏览器根据该文件路径解析 - DCC + Qt 场景：
QtWebView只是一个 Qt 宿主 QWidget，所有导航行为都委托给核心WebView：QtWebView.load_html(html: str)→WebView.load_html(html)（不再暴露base_url）QtWebView.load_url(url: str)→WebView.load_url(url)，其中url可以是http://或file:///URL
- 需要自定义相对路径解析时，推荐在 HTML 中使用
<base href="file:///.../">显式声明，而不是在 Python API 上引入base_url参数。
DCC 适配矩阵（Windows 优先）
- Maya 2025+（Qt6/PySide6）：QWidget.winId() → HWND；Qt 容器负责 resize/focus/DPI 事件
- 3ds Max（Qt）：QWidget.winId() → HWND；同 Maya 流程
- Houdini（PySide2/Qt5）：hou.qt.mainWindow().winId() → HWND；子 widget 作为容器
- Nuke（PySide2/Qt）：自定义 Panel 返回 QWidget；winId() → HWND
- Blender（非 Qt）：采用浮动/owned 顶层工具窗（Win32 + WebView2），提供置顶与尺寸钩子
Python 包与 API（零依赖）
- 单一 .pyd：pyo3 + maturin，ABI3（按 DCC Python 版本矩阵构建 wheel）
- API（示意）：
- create(parent_hwnd, x, y, w, h, url, opts) -> handle
- set_bounds(handle, x, y, w, h)
- navigate(handle, url)
- eval(handle, js)
- post_message(handle, json)
- on_message(handle, callback)
- dispose(handle)
Standalone 模式
- 保留现有 wry/tao 模式用于独立运行和开发调试
- 后续可迁移为 Win32 + WebView2 顶层窗口（不依赖 wry/winit），与 DCC 内嵌实现一致
Cargo Features（规划）
- 默认：win-webview2 + python-bindings
- 可选：wry-backend（standalone 兼容）
- 预留：mac-wkwebview、linux-webkitgtk、linux-cef（OSR）
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.
- 1mo ago First seen · 63 lines · 1,050 tokens per session scan A 5f53fb682cca
02-tech-stack is a cursor rule published in the GitHub repository loonghao/auroraview (47 stars, last pushed 18d ago), licensed MIT. It adds 1,050 tokens to every session, about $0.0042 per session on Opus 5.5. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.