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 raintree-technology/hig-doctor --skill hig-components-dialogsgit clone --depth 1 https://github.com/raintree-technology/hig-doctorWrote 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/raintree-technology/hig-doctor/hig-components-dialogs)<a href="https://agentmods.dev/skills/raintree-technology/hig-doctor/hig-components-dialogs"><img src="https://agentmods.dev/badge/skills/raintree-technology/hig-doctor/hig-components-dialogs/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/raintree-technology/hig-doctor/hig-components-dialogs"><img src="https://agentmods.dev/badge/skills/raintree-technology/hig-doctor/hig-components-dialogs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00136 | $0.00924 |
| Opus 5 | $0.00068 | $0.00462 |
| Sonnet 5 | $0.00027 | $0.00185 |
| Haiku 4.5 | $0.00014 | $0.00092 |
Grade A, and why
hig-components-dialogs 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hig-components-dialogs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple HIG: Presentation Components
Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.
Key Principles
-
Alerts: sparingly, for critical situations. Errors needing attention, destructive action confirmations, or information requiring acknowledgment. They interrupt flow and demand a response.
-
Sheets: focused tasks that maintain context. Slides in from the edge (or attaches to a window on macOS). Use for creating items, editing settings, multi-step forms.
-
Popovers: non-modal on iPad and Mac. Appear next to the trigger element, dismissed by tapping outside. For additional information, options, or controls without taking over the screen.
-
Action sheets: choosing among actions. Present when picking from multiple actions, especially if one is destructive. iPhone: slide up from bottom. iPad: appear as popovers.
-
Minimize interruptions. Before reaching for a modal, consider inline presentation or making the action undoable instead.
-
Concise, actionable alert text. Short descriptive title. Brief message body if needed. Button labels should be specific verbs ("Delete", "Save"), not "OK".
-
Mark destructive actions clearly. Destructive button style (red text). Place destructive buttons where users are less likely to tap reflexively.
-
Provide a cancel option for alerts and action sheets with multiple actions. On action sheets, cancel appears at the bottom, separated.
-
Digit entry: focused and accessible. Appropriately sized input fields, automatic advancement between digits, support for paste and autofill.
-
Adapt presentation to platform. The same interaction may use different components on iPhone, iPad, Mac, and visionOS.
Reference Index
| Reference | Topic | Key content |
|---|---|---|
| alerts.md | Alerts | Button ordering, title/message text, confirmation, destructive actions |
| action-sheets.md | Action sheets | Multiple actions, cancel option, destructive handling |
| popovers.md | Popovers | Non-modal, dismiss on tap outside, iPad/Mac |
| sheets.md | Sheets | Modal task, context preservation |
| digit-entry-views.md | Digit entry | PIN input, autofill, auto-advance |
What ships with it
5 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.
- 12d ago First seen · 77 lines · 136 tokens per session scan A 53c53ae1b403
hig-components-dialogs is a skill published in the GitHub repository raintree-technology/hig-doctor (126 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 924 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
emil-design-skills
Use when collection of 8 design engineering skills by Emil Kowalski (Vercel, Linear) — animation standards, UI craft, Apple design principles, library selection, and prototyping. Based on years of production experience. Use when the user asks about UI polish, animation decisions, or wants to audit/improve interface…
apple-design
Complete Apple Human Interface Guidelines (HIG) and Apple Design System standard. Use when designing, building, or auditing UI/UX for iOS, iPadOS, macOS, watchOS, visionOS, or Apple-styled web and mobile applications.
apple-bento-grid
Create Apple-inspired bento grid presentation cards for showcasing project stats, timelines, and achievements. Generates self-contained HTML files with zero-gap grids, stat cards, pill tags, bar charts, and dark quote cards — optimized for screenshot export. Supports both light (Apple signature #f5f5f7) and dark…
apple-hig-check
Audit code or design against Apple Human Interface Guidelines.
svvarm
Opinionated design director for frontend interfaces. Use for ANY frontend design task: building UIs, reviewing designs, fixing typography, improving layouts, checking for AI slop, or making interfaces production-ready. Understands natural language — just describe what you need. One command, zero AI slop.
macos-design
Design, critique, or scaffold native macOS applications using current HIG, Liquid Glass, menu/toolbar conventions, safe areas, accessibility, and SwiftUI/AppKit patterns. Use when the user invokes /macos-design or names this skill for macOS app design, UI review, native UI generation, or notch-style / Dynamic Island…