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 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/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/gaelic-ghost/socket/appkit-app-architecture-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/appkit-app-architecture-workflow.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 | $0.00086 | $0.02735 |
| Opus 5.5 | $0.00034 | $0.01094 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 1mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,735 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
pipeline-auto
Use when the user wants a substantial feature taken from idea through implementation in one run with as little interruption as possible ("just build it", "don't keep asking me"), or when controlling such a run and a worker question, quorum responses, the drift budget, a human decision, a review class or a completeness…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
fast-pipeline
Use when the user wants a feature built quickly with low token cost and few interruptions, approves a spec once, and says no automated tests should be written because they will test it manually — "fast pipeline", "go fast, no tests, I'll test it myself", "don't keep asking me". Not for a run that should write or keep…