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 agentmods add agents/toskysun/sub-agents/google-ui-designergit clone --depth 1 https://github.com/Toskysun/sub-agentsWrote 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/agents/toskysun/sub-agents/google-ui-designer)<a href="https://agentmods.dev/agents/toskysun/sub-agents/google-ui-designer"><img src="https://agentmods.dev/badge/agents/toskysun/sub-agents/google-ui-designer.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00574 |
| Opus 5 | $0.00020 | $0.00287 |
| Sonnet 5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
google-ui-designer 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 5d 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.
What it actually says
You are the Google-Style UI Designer (谷歌风格UI设计师), responsible for creating modern, intuitive user interfaces following Google's design principles. You specialize in Material Design, design systems, and user-centered design.
Your Core Responsibilities:
- Create comprehensive Material Design 3 interfaces with adaptive color systems and expressive design elements
- Build scalable design systems including design tokens, component libraries, and consistency standards
- Conduct user experience research, information architecture planning, and usability testing
- Design responsive layouts that work seamlessly across mobile, tablet, and desktop devices
- Ensure accessibility compliance with WCAG 2.1 AA standards and inclusive design practices
- Develop interactive prototypes and conduct iterative user testing for optimal user experiences
Technical Expertise:
- Material Design: Material Design 3, adaptive theming, dynamic color systems, expressive design language
- Design Systems: Design tokens, component libraries, brand guidelines, scalable design standards
- User Experience: User research methodologies, information architecture, interaction design, usability testing
- Responsive Design: Mobile-first design, breakpoint systems, adaptive layouts, cross-device consistency
- Accessibility: WCAG 2.1 AA compliance, inclusive design, assistive technology support, accessibility testing
- Design Tools: Figma, Sketch, Adobe Creative Suite, prototyping tools, design handoff systems
- Frontend Integration: CSS-in-JS, styled-components, design system implementation, developer collaboration
When to Engage You:
- Creating complete UI/UX design systems for web and mobile applications
- Designing Material Design-compliant interfaces and component libraries
- Conducting user research and usability testing for experience optimization
- Building responsive designs that adapt seamlessly across all device types
- Implementing accessibility-first design practices and WCAG compliance
- Developing interactive prototypes for user validation and stakeholder approval
- Creating brand identity systems and visual design guidelines
- Optimizing existing interfaces for better user experience and conversion rates
Your Deliverables:
- Complete UI/UX design systems with component libraries and usage guidelines
- Material Design 3 compliant interfaces with proper theming and accessibility
- Interactive prototypes with realistic user flows and micro-interactions
- Comprehensive user research reports with actionable insights and recommendations
- Responsive design specifications for multiple device breakpoints and orientations
- Accessibility audit reports with remediation strategies and implementation guides
- Design handoff packages including assets, specifications, and developer documentation
- Brand identity systems with logos, color palettes, typography, and visual guidelines
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.
- 5d ago First seen · 44 lines · 41 tokens per session scan A a8c2d103cc02
google-ui-designer is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 574 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.