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 rules/wangtingyeye/llm-agent-study/swiftuigit clone --depth 1 https://github.com/WangTingYeYe/llm-agent-studyWhat 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 | $0.00000 | $0.00185 |
| Opus 5 | $0.00000 | $0.00093 |
| Sonnet 5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
swiftui 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.
What it actually says
description: 该规则解释了 SwiftUI 在 iOS、macOS、watchOS 和 tvOS 开发中的模式和最佳实践。 globs: **/*.swift alwaysApply: false
SwiftUI 规则
- 使用结构体（struct）创建视图，并保持其小巧和专注
- 使用 @State 管理简单的视图本地状态
- 使用带有 @Published 的 @ObservableObject 管理共享状态
- 使用 @Binding 将可变状态传递给子视图
- 创建自定义 ViewModifiers 实现可复用的样式
- 使用环境对象（environment objects）进行依赖注入
- 对大型集合使用 LazyVStack 和 LazyHStack
- 将复杂的视图逻辑提取到单独的组件中
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 · 21 lines · 0 tokens per session scan A 3e41f1e57379
swiftui is a cursor rule published in the GitHub repository WangTingYeYe/llm-agent-study (4 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 185 tokens. 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 cursor rules, from other repositories
android-viewmodel
Android ViewModel conventions — StateFlow, repository abstraction, coroutines, no LiveData.
cursorrules
ROLE: Android Development Expert EXPERIENCELEVEL: Advanced (10+ years) SPECIALTIES.
trove-swift
Swift 6 and SwiftUI coding conventions for iOS development. Auto-activates when working with Swift files. Covers @Observable, async/await, NavigationStack, Swift Testing, and accessibility.
20-android-kotlin
There is no Android SDK/NDK available in most sandboxed dev environments (including the one this codebase was originally scaffolded in). Kotlin code in this repo has generally not been compiled or run by an AI agent — only reviewed for logical consistency. Treat Kotlin changes as higher-risk than Rust changes until a…
getting-started
SDK setup, Swift Package Manager integration, Info.plist configuration, and first connection to Meta glasses.
swift-implementation
Swift and SwiftUI implementation expectations for app code.