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.
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 fengshao1227/ccg-workflow --skill liquid-glassgit clone --depth 1 https://github.com/fengshao1227/ccg-workflowWrote 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/fengshao1227/ccg-workflow/liquid-glass)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00983 |
| Opus 5 | $0.00022 | $0.00491 |
| Sonnet 5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
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.
Copies of this mod
3 near-identical copies found in the catalogue:
- liquid-glass — 100% identical, 0 lines differ
- liquid-glass — 100% identical, 0 lines differ
- liquid-glass — 100% identical, 0 lines differ
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
- Translucency — Surfaces reveal layered content beneath via backdrop blur
- Depth — Elements float on distinct z-layers with realistic shadows
- Ambient Response — Glass tints shift based on underlying content color
- Minimal Chrome — Borders are subtle; shape and blur define boundaries
- 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);
}
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.
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.
- 12d ago First seen · 138 lines · 43 tokens per session scan A 74d307e9076a
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.
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…
frontend-design
A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.
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…
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…
maestro-impeccable
Use when designing, reviewing, refining, fixing, or codifying frontend UI with Maestro's self-contained Impeccable core.
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".