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 nongjun/awesome-harness-engineering --skill macosgit clone --depth 1 https://github.com/nongjun/awesome-harness-engineeringWrote 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/nongjun/awesome-harness-engineering/macos)<a href="https://agentmods.dev/skills/nongjun/awesome-harness-engineering/macos"><img src="https://agentmods.dev/badge/skills/nongjun/awesome-harness-engineering/macos/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/nongjun/awesome-harness-engineering/macos"><img src="https://agentmods.dev/badge/skills/nongjun/awesome-harness-engineering/macos.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 | $0.00044 | $0.00470 |
| Opus 5.5 | $0.00018 | $0.00188 |
| Sonnet 5.5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
macOS应用 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.
This is a copy
100% identical to macOS应用 — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
macOS 应用开发模式
适用场景
使用 Swift/SwiftUI 开发 macOS 桌面应用时。
核心原则
- 沙箱优先——App Store 要求沙箱化，提前规划权限需求
- 原生体验——遵循 macOS 人机界面指南，菜单栏、快捷键、拖拽都要支持
- 后台能力——macOS 应用可以后台运行，注意内存和 CPU 占用
- 多窗口——macOS 用户期望多窗口支持，不要做成单窗口
SwiftUI 模式
- 用 @State、@Binding、@ObservedObject 管理状态
- 复杂状态用 @EnvironmentObject 跨视图共享
- 列表用 LazyVStack/LazyHStack 做懒加载
- 导航用 NavigationSplitView（macOS 三栏布局）
数据持久化
- 简单配置用 UserDefaults 或 @AppStorage
- 结构化数据用 SwiftData 或 Core Data
- 文件操作需申请沙箱权限，用 NSOpenPanel/NSSavePanel
- 敏感数据（密码、Token）存 Keychain
网络通信
- 用 URLSession 或 Alamofire 做 HTTP 请求
- 异步操作用 async/await（Swift Concurrency）
- 处理网络不可用的情况，给用户明确提示
分发方式
- App Store：需要沙箱、签名、审核
- Developer ID：签名 + 公证（Notarization），可直接分发
- 企业内部：可以用 .app 或 .dmg 直接分发（需关闭 Gatekeeper 或签名）
常见坑点
- macOS 权限系统比 iOS 复杂（辅助功能、屏幕录制、完全磁盘访问等）
- 菜单栏应用（MenuBarExtra）的生命周期与窗口应用不同
- 进程间通信用 XPC 或 DistributedNotificationCenter
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 · 50 lines · 44 tokens per session scan A de57ae4f6470
macOS应用 is a skill published in the GitHub repository nongjun/awesome-harness-engineering (2 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 470 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to macOS应用, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
swiftui-dev
Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.
axiom-concurrency
Use when writing ANY async code, actors, or threads in an Apple-platform app, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.
mobiai-kmp
Use when working on a Kotlin Multiplatform project — shared code, expect/actual declarations, platform-specific implementations, building and testing.
wax
Swift client guidance for Wax's public Memory, PhotoMemory, and VideoMemory APIs. Use only when writing or changing Swift app code that imports Wax. Do not use at session start. Do not use for MCP remember/recall/stats — those follow the live MCP server instructions. Do not use for waxmcp install or doctor (that is…
re-swift
A guide to examining compiled Swift programs, including their symbols, protocol data, closures, and links to Objective-C code. It covers Swift binaries on macOS and Linux with tools such as swift-demangle.