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-patternsgit 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-patterns)<a href="https://agentmods.dev/skills/raintree-technology/hig-doctor/hig-patterns"><img src="https://agentmods.dev/badge/skills/raintree-technology/hig-doctor/hig-patterns/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-patterns"><img src="https://agentmods.dev/badge/skills/raintree-technology/hig-doctor/hig-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 29 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 78 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00205 | $0.01697 |
| Opus 5 | $0.00102 | $0.00848 |
| Sonnet 5 | $0.00041 | $0.00339 |
| Haiku 4.5 | $0.00020 | $0.00170 |
Grade A, and why
hig-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 10d 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-patterns — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple HIG: Interaction Patterns
Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.
Key Principles
-
Minimize modality. Use modality only when it is critical to get attention, a task must be completed or abandoned, or saving changes is essential. Prefer non-modal alternatives.
-
Provide clear feedback. Every action should produce visible, audible, or haptic response. Activity indicators for indeterminate waits, progress bars for determinate, haptics for physical confirmation.
-
Support undo over confirmation dialogs. Destructive actions should be reversible when possible. Undo is almost always better than "Are you sure?"
-
Launch quickly. Display a launch screen that transitions seamlessly into the first screen. No splash screens with logos. Restore previous state.
-
Defer sign-in. Let users explore before requiring account creation. Support Sign in with Apple and passkeys.
-
Keep onboarding brief. Three screens max. Let users skip. Teach through progressive disclosure and contextual hints.
-
Use progressive disclosure. Show essentials first, let users drill into details. Don't overwhelm with every option on one screen.
-
Respect user attention. Consolidate notifications, minimize interruptions, give users control over alerts. Never use notifications for marketing.
Reference Index
| Reference | Topic | Key content |
|---|---|---|
| charting-data.md | Charting Data | Data visualization patterns, accessible charts, interactive elements |
| collaboration-and-sharing.md | Collaboration & Sharing | Share sheets, activity views, collaborative editing, SharePlay |
| drag-and-drop.md | Drag and Drop | Drag sources, drop targets, spring loading, multi-item drag, visual feedback |
| entering-data.md | Entering Data | Text fields, pickers, steppers, input validation, keyboard types, autofill |
| feedback.md | Feedback | Alerts, action sheets, haptic patterns, sound feedback, visual indicators |
| file-management.md | File Management | Document browser, file providers, iCloud integration, document lifecycle |
| going-full-screen.md | Going Full Screen | Full-screen transitions, immersive content, exiting full screen |
| launching.md | Launching | Launch screens, state restoration, cold vs warm launch |
| live-viewing-apps.md | Live Viewing Apps | Live content display, real-time updates, Live Activities, Dynamic Island |
| loading.md | Loading | Activity indicators, progress views, skeleton screens, lazy loading, placeholders |
| managing-accounts.md | Managing Accounts | Sign in with Apple, passkeys, account creation, credential autofill, account deletion |
| managing-notifications.md | Managing Notifications | Permission requests, grouping, actionable notifications, provisional delivery |
| modality.md | Modality | Sheets, alerts, popovers, full-screen modals, when to use each |
| multitasking.md | Multitasking | iPad Split View, Slide Over, Stage Manager, responsive layout, size class transitions |
| offering-help.md | Offering Help | Contextual tips, onboarding hints, help menus, support links |
| onboarding.md | Onboarding | Welcome screens, feature highlights, progressive onboarding, skip options |
| playing-audio.md | Playing Audio | Audio sessions, background audio, Now Playing, audio routing, interruptions |
| playing-haptics.md | Playing Haptics | Core Haptics, UIFeedbackGenerator, haptic patterns, custom haptics |
| playing-video.md | Playing Video | Video player controls, picture-in-picture, AirPlay, full-screen video |
| printing.md | Printing | Print dialogs, page setup, AirPrint integration |
| ratings-and-reviews.md | Ratings & Reviews | SKStoreReviewController, timing, frequency limits, in-app feedback |
| searching.md | Searching | Search bars, suggestions, scoped search, results display, recents |
| settings.md | Settings | In-app vs Settings app, preference organization, toggles, defaults |
| undo-and-redo.md | Undo and Redo | Shake to undo, undo/redo stack, multi-level undo |
| workouts.md | Workouts | Workout sessions, live metrics, Always On display, summaries, HealthKit |
What ships with it
25 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.
- references/charting-data.md 1.8 KB
- references/collaboration-and-sharing.md 1.5 KB
- references/drag-and-drop.md 3.5 KB
- references/entering-data.md 1.6 KB
- references/feedback.md 1.5 KB
- references/file-management.md 3.0 KB
- references/going-full-screen.md 1.8 KB
- references/launching.md 1.5 KB
- references/live-viewing-apps.md 2.6 KB
- references/loading.md 1.3 KB
- references/managing-accounts.md 2.5 KB
- references/managing-notifications.md 2.2 KB
- references/modality.md 1.6 KB
- references/multitasking.md 1.5 KB
- references/offering-help.md 1.8 KB
- references/onboarding.md 1.7 KB
- references/playing-audio.md 2.1 KB
- references/playing-haptics.md 3.4 KB
- references/playing-video.md 3.8 KB
- references/printing.md 1.4 KB
- references/ratings-and-reviews.md 1.1 KB
- references/searching.md 1.5 KB
- references/settings.md 1.9 KB
- references/undo-and-redo.md 1.3 KB
- references/workouts.md 1.3 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.
- 10d ago First seen · 105 lines · 205 tokens per session scan A 279de9ec0514
hig-patterns is a skill published in the GitHub repository raintree-technology/hig-doctor (125 stars, last pushed 5d ago), licensed MIT. It adds 205 tokens to every session and 1,697 once invoked, about $0.0010 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
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-design-foundations
Use when choosing colors, typography, or layout/spacing for an Apple-style interface — semantic & dynamic system colors, Display P3 wide gamut, dark mode, the San Francisco type family, Dynamic Type, the 8-point grid, safe areas, and bento layouts. Part of the apple-design family. Keywords: apple color, semantic…
apple-design-os
Use when designing app UI for Apple operating systems — iOS/iPadOS surfaces (sheets, detents, tab bars, large titles, widgets, lock screen, Dynamic Island), macOS (windows, traffic lights, sidebars, menus, vibrancy), visionOS spatial design, watchOS (complications, Digital Crown), or the standard UIKit/SwiftUI…
apple-design-materials
Use when implementing translucent glass surfaces, vibrancy/blur materials, the 2025 Liquid Glass language, app icons (the continuous-corner squircle), or SF Symbols. Part of the apple-design family. Keywords: liquid glass, vibrancy, blur, backdrop-filter, frosted glass, translucency, material, ultraThinMaterial…
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an…
expo-design-system
Framework (OSS). Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when…