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/recomposesh/recompose/macos-patternsnpx skills add recomposesh/recompose --skill macos-patternsgit clone --depth 1 https://github.com/recomposesh/recomposeWhat 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 | $0.00159 | $0.04346 |
| Opus 5 | $0.00079 | $0.02173 |
| Sonnet 5 | $0.00032 | $0.00869 |
| Haiku 4.5 | $0.00016 | $0.00435 |
Grade A, and why
macos-patterns 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.
This is a copy
100% identical to macos-patterns — 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.
How it starts
The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native macOS Patterns for Web Developers
This is a reference guide for the macOS-specific patterns that have no web equivalent. When building a native macOS app, these are the things that trip up everyone coming from web development. The AI should consult this before generating macOS code to avoid confidently producing patterns that don't work.
Menu Bar Apps
There are two approaches. Use MenuBarExtra for simple menus, NSStatusItem for full control.
SwiftUI MenuBarExtra (simple)
@main
struct MyApp: App {
var body: some Scene {
MenuBarExtra("MyApp", image: "MenuBarIcon") {
MenuBarView()
}
}
}
This creates a menu-bar-only app. The menu content is a standard SwiftUI view. For a popover-style menu bar app (richer UI than a plain menu), use the .window style:
MenuBarExtra("MyApp", image: "MenuBarIcon") {
PopoverContentView()
}
.menuBarExtraStyle(.window)
AppKit NSStatusItem (full control)
For custom menus, dynamic icons, or complex interactions:
let statusItem = NSStatusBar.system.statusItem(withLength: NSStatusItem.squareLength)
if let button = statusItem.button {
let icon = NSImage(named: "MenuBarIcon")!
icon.size = NSSize(width: 18, height: 18)
icon.isTemplate = true // CRITICAL: adapts to dark/light mode automatically
button.image = icon
}
let menu = NSMenu()
menu.addItem(NSMenuItem(title: "Settings...", action: #selector(openSettings), keyEquivalent: ","))
statusItem.menu = menu
isTemplate = true is essential. Without it, your icon will be invisible in light mode or look wrong in dark mode.
NSPopover for Rich Menu Bar Content
For a popover attached to the menu bar icon (like Bartender, iStatMenus):
let popover = NSPopover()
popover.contentSize = NSSize(width: 300, height: 400)
popover.behavior = .transient // auto-closes when clicking outside
popover.contentViewController = NSHostingController(rootView: MyPopoverView())
// Show from the status item button:
if let button = statusItem.button {
popover.show(relativeTo: button.bounds, of: button, preferredEdge: .minY)
}
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 · 591 lines · 159 tokens per session scan A b1dd249b315a
macos-patterns is a skill published in the GitHub repository recomposesh/recompose (25 stars, last pushed 5d ago), licensed MIT. It adds 159 tokens to every session and 4,346 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to macos-patterns, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.