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/gaelic-ghost/socket/appkit-app-architecture-workflownpx skills add gaelic-ghost/socket --skill appkit-app-architecture-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/appkit-app-architecture-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/appkit-app-architecture-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/appkit-app-architecture-workflow.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.02735 |
| Opus 5 | $0.00043 | $0.01367 |
| Sonnet 5 | $0.00017 | $0.00547 |
| Haiku 4.5 | $0.00009 | $0.00274 |
Grade A, and why
appkit-app-architecture-workflow 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 3d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AppKit App Architecture Workflow
Purpose
Provide a docs-first workflow for AppKit app-structure decisions in macOS apps. This skill owns ownership-boundary guidance for AppKit lifetimes, menu bar apps, menus, responder-chain action routing, windows, controllers, restoration, archiving, AppKit MVC, Observation interop, and mixed AppKit/SwiftUI composition.
It is not the Apple-docs router, not the SwiftUI architecture workflow, not the accessibility workflow, and not the Xcode execution workflow.
For Xcode app source layout, keep UIKit/AppKit controller support view-adjacent:
Sources/Views/Shared, Sources/Views/macOS, and Sources/Views/iOS own view
surfaces, and controller support files use concatenated prefixed names such as GEAWhateverViewController.swift
beside their matching view. Do not collect ordinary app controller support in a
root Controllers/ directory.
When To Use
- Use this skill when the user wants help structuring an AppKit or mixed AppKit/SwiftUI macOS app.
- Use this skill when the question involves
NSApplication,NSApplicationDelegate, app activation policy, app reopen behavior, menu bar apps,NSStatusItem, status menus, popovers, panels, or quit behavior. - Use this skill when the question involves the main menu, contextual menus, toolbar actions, target/action, responder-chain action routing, or menu validation.
- Use this skill when deciding whether app-level, window-level, controller-level, document-level, model-level, or hosted SwiftUI state should own a responsibility.
- Use this skill for old-school AppKit restoration, including restoration
identifiers,
NSWindowRestoration, window-controller restoration, document reopening, and workspace reopening. - Use this skill when deciding between
NSSecureCoding,NSKeyedArchiver,Codable, user defaults, files, Core Data, SwiftData, or another persistence surface for AppKit-owned state. - Use this skill when a mixed AppKit/SwiftUI app uses SwiftData and the agent must keep SwiftData directly driving SwiftUI-owned screens while AppKit keeps only the AppKit-owned lifetime, controller, restoration, or bridge boundary.
- Use this skill when using Swift Observation with AppKit controls, controllers, delegates, or hosted SwiftUI views.
- Use this skill when embedding SwiftUI in AppKit through
NSHostingVieworNSHostingController, or when exposing AppKit views to SwiftUI through representable bridges. - Recommend
swiftui-app-architecture-workflowwhen the actual owner is SwiftUIApp, scenes, commands, focus, environment, preferences, or reusable view composition. - Recommend
explore-apple-swift-docswhen the user primarily needs Apple or Swift documentation lookup rather than architecture guidance. - Recommend
xcode-build-run-workflowwhen the work becomes build, run, preview, diagnostics, file-membership, or guarded mutation work in an existing Xcode-managed project. - Recommend
xcode-testing-workflowwhen the work becomes Swift Testing, XCTest, XCUITest,.xctestplan, or test diagnosis. - Recommend
apple-ui-accessibility-workflowwhen the work is primarily about accessibility-specific implementation or review.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 787 B
- references/anti-patterns-and-corrections.md 2.4 KB
- references/app-delegate-and-lifecycle.md 1.9 KB
- references/appkit-mvc-target-action-and-bindings.md 1.6 KB
- references/architecture-decision-rules.md 1.9 KB
- references/archiving-persistence-and-migration.md 1.6 KB
- references/menu-bar-status-item-and-activation.md 1.7 KB
- references/menus-responder-chain-and-validation.md 1.8 KB
- references/mixed-appkit-swiftui-composition.md 1.8 KB
- references/observation-and-appkit.md 1.7 KB
- references/restoration-documents-and-workspaces.md 1.9 KB
- references/snippets/apple-xcode-project-core.md 26 KB
- references/windows-controllers-panels-and-inspectors.md 1.7 KB
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.
- 3d ago First seen · 254 lines · 86 tokens per session scan A 4a1d64b63207
appkit-app-architecture-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,735 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
caveman
Persistent token-compression mode (75% reduction) — now always-on by default. Strips filler while keeping code exact.
authoring-workflows
当你要调用 Workflow 工具，或要写 / 调试 / 启动一个 Claude Code dynamic-workflow 脚本时用——author / debug / launch a Claude Code dynamic-workflow script，当你要写 workflow 脚本时——哪怕你自觉已经懂这套 API。当你发现自己在猜 workflow 引擎的 determinism 或 resume 规则、没查 shape 就伸手够 parallel() / pipeline()、想手写一个 validation linter、或刚被 harness 报错正要 relaunch 时用。先查再猜，别等跑挂了才来。.
comfyui-core
Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage.
installer-packs
Use when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driven packs/ system and tells you to invite the user to contribute new packs back upstream.
workflow-layout
Lay out and organize a ComfyUI workflow cleanly on the live panel canvas. Dependency-layered node placement with no overlaps, subgraphs, colored group boxes, and subgraph rail alignment. Use when asked to tidy / clean up / organize / arrange a workflow, add groups or subgraphs, fix overlapping nodes, or build a…
suede-deslop
Suede Slop Stop: Suede Labs context-aware anti-slop pass for finished prose. Find or remove generic filler, manufactured emphasis, false agency, and formulaic structure without flattening the author's voice. Use before copy, a README, an email, a social post, or a doc ships; after a long assisted-writing session; or…