What is glass-expert?

A guide for building and checking Apple's Liquid Glass effect in SwiftUI, Apple's framework for user interfaces. Liquid Glass is a translucent surface that samples, blurs, refracts, and tints the content behind it.

Use it when implementing, debugging, reviewing, or visually verifying Liquid Glass in SwiftUI apps for macOS 26 or iOS 26.

It helps ensure the effect is actually visible, placed correctly, and readable instead of merely compiling or looking like a flat gray surface.

glass-expert — Skill for Claude Code and Codex by vosslab

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 vosslab/vosslab-skills --skill glass-expert

Clone the repo

git clone --depth 1 https://github.com/vosslab/vosslab-skills

Made for: Claude Code, Codex.

Or install vosslab-skills, the plugin that ships this one along with the rest of its 42 skills, 14 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vosslab/vosslab-skills/glass-expert/github.svg)](https://agentmods.dev/skills/vosslab/vosslab-skills/glass-expert)

Your own site

<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/glass-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/glass-expert/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/glass-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/glass-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,282 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.01282
Opus 5	$0.00030	$0.00641
Sonnet 5	$0.00012	$0.00256
Haiku 4.5	$0.00006	$0.00128

Measured 10d ago against content hash af335f562ef1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

glass-expert 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/capture_glass_evidence.sh, scripts/compare_captures.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/experts/glass-expert/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Liquid Glass Expert

Overview

Use this skill to get Liquid Glass demonstrably correct in SwiftUI apps on macOS 26+ (and iOS 26). Glass is a backdrop-sampling material: it blurs, refracts, and tints whatever renders behind it, adapts its own opacity to the backdrop, and guarantees no minimum text contrast. Most failures are silent -- the code compiles and a capture looks plausible while the effect is absent or illegible. This skill turns "add glass" into layered implementation plus visual evidence: a correct sampling path, colors that stay legible, and captures that prove the effect is live.

SwiftUI is the implementation layer; treat AppKit as a legacy escape hatch reached only when SwiftUI cannot yet express the behavior.

When to use

Implement custom glass (.glassEffect, GlassEffectContainer, morphing).
Debug glass that renders flat, gray, invisible, or unexpectedly opaque.
Prove with captures that glass is live before accepting work as done.
Decide which surfaces should be glass and which stay stable content.
Guarantee text contrast over glass across arbitrary backdrops.
Review or harden an existing app's glass adoption.

When not to use

Web glassmorphism (CSS backdrop-filter); this skill is SwiftUI-specific.
App-icon glass (Icon Composer layered icons); a different pipeline.
General SwiftUI layout or state questions with no glass involvement.

Workflow

Frame the project shape. When invoked on a target app, decide greenfield versus improve-existing and follow the matching workflow in references/project_workflow.md. Skip this step for a one-off question with no target repo.
Classify the task (placement, implementation, verification, debugging, or contrast) using references/task_selection.md.
For an observed problem ("glass looks flat", "text unreadable"), start at the symptom router references/topic_index.md.
Open the one matching reference from the routing table below.
Implement with the seed views in assets/ (see references/component_seeds.md) when the surface carries text or needs accessibility fallbacks.
Prove the result with the evidence protocol in references/testing_and_oracles.md, using the capture and comparison tools in scripts/. Ship only on visual evidence, never on compiling code.

Read the full file on GitHub · 100 lines

Files

What ships with it

18 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.

10d ago First seen · 100 lines · 59 tokens per session scan A af335f562ef1

Subscribe to this mod's changes

glass-expert is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 59 tokens to every session and 1,282 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 2026-08-31.

Design and UX Mobile

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…

android/skills · 91 tokens

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…

expo/skills · 201 tokens

glass-expert