liquid-glass

liquid-glass is a skill for Claude Code from fengshao1227/ccg-workflow. It costs 43 tokens per session (983 once invoked), scanned A, original, MIT.

A set of CSS design tokens and component patterns for building Apple-inspired interfaces with translucent, layered surfaces. It covers light and dark themes, blur, shadows, rounded corners, and motion.

In plain words
What is it for?
Use it when styling cards and other interface components with translucent backgrounds, blur, layered depth, subtle borders, and physical-feeling transitions.
Why use it?
It gives you consistent values and patterns for a glass-style interface instead of making each effect from scratch. It also helps keep depth, color response, and animation coherent.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the ccg plugin — 58 skills, 12 commands, 7 agents shipped together

Good fit Use it when styling cards and other interface components with translucent backgrounds, blur, layered depth, subtle borders, and physical-feeling transitions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fengshao1227/ccg-workflow/liquid-glass
About the project

CCG is a command-line workflow engine that coordinates Claude, Codex, Gemini, and other models as specialized collaborators on coding tasks. It is used to analyze requests, choose a strategy, delegate work to model-specific roles, and combine their results. The catalogue entries provide the skills, commands, agents, and plugin that implement this workflow.

fengshao1227/ccg-workflow · 5,881 stars · on GitHub · ccg.fengshao1227.com

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 fengshao1227/ccg-workflow --skill liquid-glass
Clone the repo
git clone --depth 1 https://github.com/fengshao1227/ccg-workflow

Made for: Claude Code.

Or install ccg, the plugin that ships this one along with the rest of its 58 skills, 12 commands, 7 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.

agentmods badge for liquid-glass

README.md
[![agentmods](https://agentmods.dev/badge/skills/fengshao1227/ccg-workflow/liquid-glass/github.svg)](https://agentmods.dev/skills/fengshao1227/ccg-workflow/liquid-glass)
Your own site
<a href="https://agentmods.dev/skills/fengshao1227/ccg-workflow/liquid-glass"><img src="https://agentmods.dev/badge/skills/fengshao1227/ccg-workflow/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/fengshao1227/ccg-workflow/liquid-glass"><img src="https://agentmods.dev/badge/skills/fengshao1227/ccg-workflow/liquid-glass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 983 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00043 $0.00983
Opus 5 $0.00022 $0.00491
Sonnet 5 $0.00009 $0.00197
Haiku 4.5 $0.00004 $0.00098

Measured 12d ago against content hash 74d307e9076a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

templates/skills/domains/frontend-design/liquid-glass/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Liquid Glass Design System

Apple-inspired translucent glass UI with depth, refraction, and ambient light response.

Core Principles

  1. Translucency — Surfaces reveal layered content beneath via backdrop blur
  2. Depth — Elements float on distinct z-layers with realistic shadows
  3. Ambient Response — Glass tints shift based on underlying content color
  4. Minimal Chrome — Borders are subtle; shape and blur define boundaries
  5. Motion — Transitions feel physical: spring-based, with inertia

Usage

Import the token file in your CSS:

@import 'references/tokens.css';

CSS Tokens Reference

All tokens are defined in references/tokens.css. Key categories:

Category Prefix Example
Glass backgrounds --lg-bg-* --lg-bg-primary
Blur --lg-blur-* --lg-blur-md
Borders --lg-border-* --lg-border-color
Shadows --lg-shadow-* --lg-shadow-elevated
Radius --lg-radius-* --lg-radius-lg
Animation --lg-duration-* --lg-duration-normal

Component Patterns

Glass Card

.glass-card {
  background: var(--lg-bg-primary);
  backdrop-filter: blur(var(--lg-blur-md));
  -webkit-backdrop-filter: blur(var(--lg-blur-md));
  border: 1px solid var(--lg-border-color);
  border-radius: var(--lg-radius-lg);
  box-shadow: var(--lg-shadow-elevated);
  transition: transform var(--lg-duration-normal) var(--lg-easing-spring);
}

.glass-card:hover {
  transform: translateY(-2px);
  box-shadow: var(--lg-shadow-high);
}

Glass Toolbar

.glass-toolbar {
  background: var(--lg-bg-toolbar);
  backdrop-filter: blur(var(--lg-blur-lg)) saturate(var(--lg-saturate));
  -webkit-backdrop-filter: blur(var(--lg-blur-lg)) saturate(var(--lg-saturate));
  border-bottom: 1px solid var(--lg-border-subtle);
}

Glass Button

.glass-btn {
  background: var(--lg-bg-interactive);
  backdrop-filter: blur(var(--lg-blur-sm));
  border: 1px solid var(--lg-border-color);
  border-radius: var(--lg-radius-md);
  transition: all var(--lg-duration-fast) var(--lg-easing-spring);
}

.glass-btn:active {
  transform: scale(0.97);
  background: var(--lg-bg-pressed);
}

Read the full file on GitHub · 138 lines

Files

What ships with it

1 file 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 · 138 lines · 43 tokens per session scan A 74d307e9076a

Subscribe to this mod's changes

liquid-glass is a skill published in the GitHub repository fengshao1227/ccg-workflow (5,881 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 983 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

absolute-ui

Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…

maddhruv/absolute · 121 tokens

frontend-design

A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.

itmisx/deepx-code · 88 tokens

ac-tools-human-agentic-design

Generates interactive HTML prototypes optimized for dual human+agent interaction. Produces semantic, accessible designs with Tailwind + DaisyUI (Tier A) or React + shadcn/ui + Vite (Tier B). Triggers on keywords: prototype, design, UI prototype, landing page, dashboard, form design, human-agentic, had, mockup…

WaterplanAI/agentic-config · 81 tokens

ui-design-engineering

Design, implement, harden, and review production-grade user interfaces for web apps, dashboards, SaaS products, admin tools, forms, and responsive frontend components. Use when building or improving UI/UX, translating Figma or requirements into code, styling React/Vue/Svelte/HTML views, reviewing frontend quality…

ntaffzii/Skill-Agents · 115 tokens

maestro-impeccable

Use when designing, reviewing, refining, fixing, or codifying frontend UI with Maestro's self-contained Impeccable core.

catlog22/maestro-flow · 32 tokens

prototype

Build a throwaway prototype that answers one design question. Plain HTML/CSS/JS in the task's .aiwork/ folder by default, or UI variants inside the app (Nuxt/Vue, ...) on a prototype branch when they must sit against real layout and data. Use for "does this state model feel right" or "what should this look like".

lttr/claude-marketplace · 76 tokens