agentmods.dev

liquid-glass

liquid-glass is a skill for Claude Code from YordiLorenzo/liquid-glass-skills. It costs 243 tokens per session (1,389 once invoked), scanned A, original, MIT.

A set of practical rules for using Apple’s Liquid Glass interface material in SwiftUI, UIKit, and AppKit apps on newer iOS and macOS versions.

In plain words
What is it for?
Use it when building, reviewing, or updating toolbars, controls, sheets, tab bars, and custom glass effects for iOS or macOS.
Why use it?
It helps prevent incorrect availability checks and poor design choices when adding translucent glass surfaces. It also separates verified guidance from version-specific workarounds that may need rechecking.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the liquid-glass plugin — 3 skills shipped together

not rated 4repo 1mo ago A scan 243 tokens original MIT

Good fit Use it when building, reviewing, or updating toolbars, controls, sheets, tab bars, and custom glass effects for iOS or macOS.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yordilorenzo/liquid-glass-skills/liquid-glass
View source ↗ YordiLorenzo/liquid-glass-skills
Install

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.

Any agent
npx skills add YordiLorenzo/liquid-glass-skills --skill liquid-glass
Clone the repo
git clone --depth 1 https://github.com/YordiLorenzo/liquid-glass-skills

Made for: Claude Code.

Or install liquid-glass, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for liquid-glass

README.md
[![agentmods](https://agentmods.dev/badge/skills/yordilorenzo/liquid-glass-skills/liquid-glass/github.svg)](https://agentmods.dev/skills/yordilorenzo/liquid-glass-skills/liquid-glass)
Your own site
<a href="https://agentmods.dev/skills/yordilorenzo/liquid-glass-skills/liquid-glass"><img src="https://agentmods.dev/badge/skills/yordilorenzo/liquid-glass-skills/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.

agentmods 80×15 button for liquid-glass

Your own site · 80×15
<a href="https://agentmods.dev/skills/yordilorenzo/liquid-glass-skills/liquid-glass"><img src="https://agentmods.dev/badge/skills/yordilorenzo/liquid-glass-skills/liquid-glass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 243 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00243 $0.01389
Opus 5 $0.00121 $0.00694
Sonnet 5 $0.00049 $0.00278
Haiku 4.5 $0.00024 $0.00139

Measured 12d ago against content hash cf184b7c9f3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 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.

liquid-glass/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Liquid Glass — the material

Composed 2026-08 and verified against developer.apple.com and SDK interfaces. Every rule carries an availability floor and a confidence tag: [verified] (checked against Apple docs/SDK this composition), [apple] (Apple doc, unverified), [multi] (corroborated by multiple independent accounts), [single] (one account — verify before relying), [version-pinned] (bug workaround tied to OS versions; recheck on updates).

Operating rules

  1. ALWAYS read references/availability-and-sdk27.md before generating or reviewing glass code. It corrects availability errors present in most published material, including Apple's.
  2. Load other references on demand via the router below — one topic, one file.
  3. Glass belongs on the functional layer (controls, chrome) floating above the content layer. When asked to add glass to content (lists, media, text), first ask whether it should be glass at all.
  4. Prefer standard components (toolbars, search, sheets, tab bars) that adopt glass automatically; custom glassEffect surfaces are for distinctive elements only.
  5. Never present simulator rendering or exact screenshot pixels as evidence a glass change is correct — see references/known-bugs-and-testing.md.
  6. Animation of glass (morphing, transitions, reduce-motion gating, performance) is owned by the companion liquid-glass-motion skill, installed alongside this one. Read its references when the task involves motion; do not improvise glass animation from here.

Workflows

  • Review existing glass → references/review-checklist.md (diff-checkable items + known-bad API table). Also flag where glass should NOT be used.
  • Adopt / migrate an app → references/fallback-and-migration.md (deletion-first audit, 5 phases), then per-surface references.
  • Implement from scratch → references/material-and-variants.md + references/containers-and-sampling.md, then the platform file for your framework.

Hard rules (the short list)

Read the full file on GitHub · 98 lines

Files

What ships with it

11 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.

Changes

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.

  1. 12d ago First seen · 98 lines · 243 tokens per session scan A cf184b7c9f3a

Subscribe to this mod's changes

liquid-glass is a skill published in the GitHub repository YordiLorenzo/liquid-glass-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 243 tokens to every session and 1,389 once invoked, about $0.0012 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.

Claude CodeDesign and UXMobileagent-skillsappkitclaude-skillsios26ios27
Related

Other skills, from other repositories

appllama-app-design-skill

Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG…

Appllama/appllama-skills · 184 tokens

app-icon-studio

Apple app icons: create, generate, evaluate, export, install, or debug iOS AppIcon.appiconset and macOS .icns assets for small-size clarity.

Xopoko/build-swift-apps · 40 tokens

macos-window-architect

Use SwiftUI scene/window modifiers first; switch to macos-appkit-bridge only when SwiftUI cannot express the behavior.

Xopoko/build-swift-apps · 46 tokens

ios-liquid-glass-designer

Implement, refactor, or review iOS 26+ SwiftUI Liquid Glass with native glassEffect, GlassEffectContainer, button styles, availability gates, and non-glass fallbacks.

Xopoko/build-swift-apps · 47 tokens

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.

datit309/supergraph · 48 tokens

ios-swiftui-architect

Use for iOS SwiftUI UI structure and component choices. Read the nearest local example before introducing a new pattern.

Xopoko/build-swift-apps · 43 tokens