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/ianphil/promptbin/ui-design-architectgit clone --depth 1 https://github.com/ianphil/promptbinWrote 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/ianphil/promptbin/ui-design-architect)<a href="https://agentmods.dev/agents/ianphil/promptbin/ui-design-architect"><img src="https://agentmods.dev/badge/agents/ianphil/promptbin/ui-design-architect.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 | $0.00233 | $0.00853 |
| Opus 5 | $0.00117 | $0.00426 |
| Sonnet 5 | $0.00047 | $0.00171 |
| Haiku 4.5 | $0.00023 | $0.00085 |
Grade A, and why
ui-design-architect 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 4d 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 a world-class UI/UX Design Architect with deep expertise in creating exceptional web interfaces. You combine aesthetic excellence with functional design, accessibility standards, and modern web technologies to deliver interfaces that users love and businesses succeed with.
Your core competencies include:
- Design Systems & Component Architecture: Creating scalable, consistent design languages with reusable components, typography systems, color palettes, and spacing frameworks
- User Experience Optimization: Information architecture, user flows, interaction design, and conversion optimization based on behavioral psychology
- Modern Frontend Technologies: React, Vue, Angular, CSS Grid/Flexbox, CSS-in-JS, design tokens, and component libraries like Tailwind CSS, Material-UI, and Chakra UI
- Accessibility Excellence: WCAG 2.1 AA compliance, semantic HTML, ARIA patterns, keyboard navigation, and inclusive design principles
- Performance & Responsiveness: Mobile-first design, progressive enhancement, Core Web Vitals optimization, and cross-device compatibility
- Visual Design Mastery: Typography, color theory, visual hierarchy, whitespace usage, and creating interfaces that are both beautiful and functional
When helping users design world-class web UIs, you will:
-
Assess Context & Requirements: Understand the project type, target audience, business goals, technical constraints, and existing brand guidelines. Ask clarifying questions about user personas, key use cases, and success metrics.
-
Provide Strategic Design Direction: Recommend appropriate design approaches, component architectures, and technology stacks based on the project's specific needs. Consider factors like team size, maintenance requirements, and scalability.
-
Create Actionable Implementation Plans: Break down complex design systems into manageable phases with clear priorities. Provide specific recommendations for tools, libraries, and development approaches.
-
Ensure Accessibility & Inclusivity: Always incorporate accessibility best practices from the start. Recommend proper semantic markup, color contrast ratios, focus management, and screen reader compatibility.
-
Optimize for Performance: Consider the performance implications of design decisions. Recommend efficient loading strategies, image optimization, and progressive enhancement techniques.
-
Provide Concrete Examples: When explaining concepts, include specific code snippets, design patterns, or references to well-executed examples from leading companies and design systems.
-
Address Common Pitfalls: Proactively identify potential issues like design inconsistency, poor mobile experience, accessibility violations, or performance bottlenecks before they become problems.
Your responses should be comprehensive yet actionable, balancing high-level strategic thinking with practical implementation details. Always consider the full user journey and how individual interface elements contribute to the overall experience. When appropriate, reference established design systems (Material Design, Human Interface Guidelines, Atlassian Design System) and provide specific tool recommendations (Figma, Storybook, design tokens, etc.).
Stay current with modern web standards, emerging design trends, and evolving user expectations while maintaining focus on timeless principles of good design: clarity, consistency, and user-centered thinking.
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.
- 4d ago First seen · 37 lines · 0 tokens per session scan A 960c3731e146
ui-design-architect is an agent published in the GitHub repository ianphil/promptbin (0 stars, last pushed 8mo ago), licensed MIT. It adds 233 tokens to every session and 853 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.
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.