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/macos-window-management-workflownpx skills add gaelic-ghost/socket --skill macos-window-management-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/macos-window-management-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/macos-window-management-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/macos-window-management-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 | $0.00054 | $0.00608 |
| Opus 5 | $0.00027 | $0.00304 |
| Sonnet 5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
macos-window-management-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 yesterday.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Window Management Workflow
Purpose
Own concrete macOS window behavior that sits below broad app architecture: scene selection, chrome, drag affordances, sizing, placement, restoration, utility windows, and validation. Keep application-wide ownership and AppKit controller architecture with swiftui-app-architecture-workflow and appkit-app-architecture-workflow.
Workflow
- Identify the window's job: main content, document, settings, inspector, utility, transient activity, or external display. Start from
WindowGroup,Window,Settings, orDocumentGroup; do not start by hiding the title bar. - Define the window's ownership and identity. Give independently openable windows stable scene values and user-facing titles so Window-menu, restoration, and focus behavior remain understandable.
- Choose the least-custom chrome. Prefer normal title bars and standard toolbars; use
windowToolbarStyle,toolbarBackgroundVisibility,toolbarVisibility, orwindowStyleonly to support the window's job. - If custom chrome removes a normal drag surface, add
WindowDragGestureonly in a region that does not steal content controls. UseallowsWindowActivationEvents(true)only when the window must activate and drag from the same gesture. - Treat placement, resizing, and zoom as behavioral contracts. Use scene-level placement APIs only when the content has a real ideal size or position; do not force a fixed geometry that fights user resizing or display changes.
- Respect state restoration by default. Disable restoration only for a truly transient, expensive, or unsafe-to-reconstruct window, and explain what opens instead on relaunch.
- Escalate to AppKit only for an actual AppKit-owned requirement such as
NSWindowbehavior, panels, responder-chain menus, or a controller lifecycle that SwiftUI cannot represent cleanly. - Validate on the oldest supported macOS plus the current target: launch, open another window, focus switching, resize/zoom, full screen, close/reopen, restoration, VoiceOver title, and Window-menu state.
What ships with it
3 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.
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.
- yesterday First seen · 35 lines · 54 tokens per session scan A 8ffffa00f40b
macos-window-management-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 54 tokens to every session and 608 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
create-diagram
Create architecture diagrams from a local codebase or system description. Use when the user asks to diagram a repo, map system architecture, show component relationships, create drill-down views, or explain a system visually with tld.
user-research
User research and insight synthesis for interviews, usability testing, personas, journey mapping, and actionable product/design recommendations. Use when planning studies, collecting evidence, synthesizing patterns, or converting findings into prioritized decisions.
frontend-patterns
Context enrichment for frontend UI development using shadcn/ui and Tailwind CSS. Use when building component libraries, implementing UI designs, theming, or working with accessible React components.
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
review
Visual Stack's primary tool. Build a UI wireframe and open it in an interactive review workspace where the user comments directly on the page, turning those comments into the next iteration — or point the same workspace at an app that is already running and review the real thing. Use when the user wants a wireframe…