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 DanielJamesTronca/apple-liquid-glass-skill --skill apple-liquid-glassgit clone --depth 1 https://github.com/DanielJamesTronca/apple-liquid-glass-skillWrote 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/danieljamestronca/apple-liquid-glass-skill/apple-liquid-glass)<a href="https://agentmods.dev/skills/danieljamestronca/apple-liquid-glass-skill/apple-liquid-glass"><img src="https://agentmods.dev/badge/skills/danieljamestronca/apple-liquid-glass-skill/apple-liquid-glass/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/danieljamestronca/apple-liquid-glass-skill/apple-liquid-glass"><img src="https://agentmods.dev/badge/skills/danieljamestronca/apple-liquid-glass-skill/apple-liquid-glass.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 | $0.00105 | $0.01180 |
| Opus 5 | $0.00053 | $0.00590 |
| Sonnet 5 | $0.00021 | $0.00236 |
| Haiku 4.5 | $0.00011 | $0.00118 |
Grade A, and why
apple-liquid-glass scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Liquid Glass
Treat Liquid Glass as the functional layer for controls and navigation above content, not as decoration. Prefer system components and subtraction before writing custom glass.
Workflow
1. Inspect the target
Determine the active SDK, deployment targets, frameworks, and whether the app can be built or rendered before recommending code.
xcodebuild -version
python3 scripts/audit_liquid_glass.py <project-path> --json
rg --no-filename -o --glob '*.swift' '^import (SwiftUI|UIKit|AppKit|WidgetKit|CarPlay)$' \
<project-path> | sort | uniq -c
Honor DEVELOPER_DIR or another project-selected toolchain. Do not add OS 26
availability branches when every deployment target is 26 or newer. When the
project builds with an Xcode 27 beta SDK, load
references/migration-26-to-27.md and verify beta declarations against the
active SDK or current Apple documentation.
2. Decide whether glass belongs
Stop at the first disqualifying answer:
- Is this functional UI rather than content?
- Is there no system component that already provides the behavior?
- Does the element float above content that can move or change beneath it?
- Is it interactive, or otherwise essential functional chrome?
- Is glass clearer than a plain or standard-material treatment?
If any answer is no, do not add custom glass. Explain why and offer a concrete
system or standard-material alternative. For ambiguous design requests, load
references/design-decision-tree.md.
3. Route only to relevant guidance
| Target or task | Load |
|---|---|
| SwiftUI code | references/swiftui.md |
| UIKit code | references/uikit.md |
| AppKit code | references/appkit.md |
| Mixed-framework code | Each framework file actually used |
| Bars, navigation, sidebars, or search | references/navigation-bars-search.md |
| Sheets, menus, alerts, or popovers | references/presentations.md |
| WidgetKit | references/widgets.md |
| App icons, symbols, Icon Composer, or CarPlay icons | references/icons-and-symbols.md |
| Custom-control accessibility | references/accessibility.md |
| Hitches, profiling, snapshots, or visual testing | references/performance-and-testing.md |
| OS 26 to OS 27 beta migration | references/migration-26-to-27.md |
| Code review or “looks wrong” diagnosis | references/common-failures.md |
| Citation, conflict, or availability question | references/sources.md |
What ships with it
15 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 291 B
- references/accessibility.md 4.5 KB
- references/appkit.md 3.4 KB
- references/common-failures.md 4.7 KB
- references/design-decision-tree.md 5.3 KB
- references/icons-and-symbols.md 3.7 KB
- references/migration-26-to-27.md 6.8 KB
- references/navigation-bars-search.md 5.7 KB
- references/performance-and-testing.md 3.6 KB
- references/presentations.md 2.7 KB
- references/sources.md 3.2 KB
- references/swiftui.md 9.2 KB
- references/uikit.md 4.3 KB
- references/widgets.md 3.3 KB
- scripts/audit_liquid_glass.py 18 KB runs code
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.
- 11d ago First seen · 121 lines · 105 tokens per session scan A 2bb16695ed3a
apple-liquid-glass is a skill published in the GitHub repository DanielJamesTronca/apple-liquid-glass-skill (3 stars, last pushed 28d ago), licensed MIT. It adds 105 tokens to every session and 1,180 once invoked, about $0.0005 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
mobile-design-android
Use when the user asks to build Android screens, Jetpack Compose layouts, Material components, or any Android app UI. Also use when styling, redesigning, or beautifying any Android interface. Covers Material 3 Expressive for Android 16, spring motion, shape variety, and platform-native patterns.
mobile-design-ios
Use when the user asks to build iOS screens, SwiftUI views, UIKit layouts, mobile components, or any iOS app UI. Also use when styling, redesigning, or beautifying any iOS interface. Covers iOS 26 Liquid Glass design language, hierarchy, motion, and platform-native patterns.
liquid-glass
You are an expert in Apple's Liquid Glass design system introduced in iOS 26 at WWDC 2025. Help developers implement, migrate, and troubleshoot Liquid Glass UI in SwiftUI.
mobile-app
A design template for a single-screen iPhone 15 Pro app mockup, including the phone frame, status bar, app header, main content, and bottom navigation.
mobile-onboarding
A visual template showing three mobile-app onboarding screens side by side: a splash screen, a feature introduction, and sign-in.
iOS SwiftUI Accessibility
Enforces WCAG 2.2 accessible coding patterns when writing SwiftUI — labels, traits, Dynamic Type, contrast, touch targets, focus management, orientation, and more. Based on the ios-swiftui-accessibility-techniques project with 41 static analysis rules across 23 WCAG criteria.