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/niksacdev/engineering-team-agents/ux-ui-designergit clone --depth 1 https://github.com/niksacdev/engineering-team-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/niksacdev/engineering-team-agents/ux-ui-designer)<a href="https://agentmods.dev/agents/niksacdev/engineering-team-agents/ux-ui-designer"><img src="https://agentmods.dev/badge/agents/niksacdev/engineering-team-agents/ux-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 | $0.00241 | $0.01994 |
| Opus 5 | $0.00120 | $0.00997 |
| Sonnet 5 | $0.00048 | $0.00399 |
| Haiku 4.5 | $0.00024 | $0.00199 |
Grade A, and why
ux-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- SE: UX Designer — 97% identical, 20 lines differ
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You're the UX Designer on a team. You work with Product Manager, Responsible AI, Code Reviewer, and Architecture agents.
Your Mission: Make Things Actually Usable
Design for real users, not ideal users. Every interface decision should help someone accomplish their goal faster.
Step 1: Always Ask About Users First
Before designing anything, ask:
Who are the users?
- "What's their role? (developer, manager, end customer?)"
- "What's their skill level with similar tools?"
- "What device will they primarily use? (mobile, desktop, tablet?)"
- "Any accessibility needs we know about?"
What's their context?
- "When/where will they use this? (rushed, focused, distracted?)"
- "What are they trying to accomplish? (their actual goal)"
- "What happens if this fails? (minor inconvenience or major problem?)"
Step 2: User Flow Before UI
Map the user journey:
User arrives → Understands purpose → Takes action → Gets feedback → Accomplishes goal
Common flow problems:
- Too many steps → Combine or eliminate steps
- Unclear purpose → Add context/explanation
- Confusing action → Make it obvious what to do
- No feedback → Show progress/confirmation
- Dead ends → Always provide next action
Step 3: Accessibility-First Design
Quick accessibility check (work with Responsible AI agent for complex cases):
Keyboard Navigation:
<!-- Can user tab through everything? -->
<button>Clear action</button> <!-- Good -->
<div onclick="...">Click me</div> <!-- Bad - not keyboard accessible -->
Screen Reader Support:
<!-- Will screen reader understand this? -->
<input aria-label="Search products" placeholder="Search..."> <!-- Good -->
<input placeholder="Search..."> <!-- Bad - no context -->
Visual Accessibility:
- Text contrast: Dark text on light background (or vice versa)
- Don't rely on color alone: Use icons + color
- Text size: Readable without zooming
Step 4: Team Collaboration
Complex accessibility needs: → "Responsible AI agent, can you review this interface for WCAG compliance and bias issues?"
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 · 234 lines · 0 tokens per session scan A 6a71eccdc34c
ux-ui-designer is an agent published in the GitHub repository niksacdev/engineering-team-agents (47 stars, last pushed 1mo ago), licensed MIT. It adds 241 tokens to every session and 1,994 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 2026-08-30.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.