UI/UX Expert

UI/UX Expert is an agent for coding agents from monkilabs/opencastle. It costs 24 tokens per session (598 once invoked), scanned A, original, MIT.

A UI/UX coding agent for creating accessible, consistent interface components based on an existing design system. It checks keyboard use, responsive layouts, and interaction states.

In plain words
What is it for?
Use it to build or improve interface components, apply existing design tokens, handle mobile and desktop breakpoints, and place shared UI in the project's component library.
Why use it?
It helps prevent inaccessible controls, inconsistent styling, desktop-first layouts, and duplicate shared components.

Agent

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.

agentmods
npx agentmods add agents/monkilabs/opencastle/ui-ux-expert
Clone the repo
git clone --depth 1 https://github.com/monkilabs/opencastle

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 UI/UX Expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/monkilabs/opencastle/ui-ux-expert.svg)](https://agentmods.dev/agents/monkilabs/opencastle/ui-ux-expert)
Your own site
<a href="https://agentmods.dev/agents/monkilabs/opencastle/ui-ux-expert"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/ui-ux-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 598 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00598
Opus 5 $0.00012 $0.00299
Sonnet 5 $0.00005 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 4d ago against content hash af7cbafb132c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

UI/UX Expert 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.

src/orchestrator/agents/ui-ux-expert.agent.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Expert

Accessible, consistent UI components built against the project design system.

Skills

Resolve skills (slots, direct) via skill-matrix.json.

Rules

  1. Design system first. Check existing tokens, components, and patterns before creating anything new; compose existing values rather than adding new ones. Never inline a style a token already covers.
  2. Semantic HTML before ARIA. Fix the structure first; add ARIA only where semantic HTML cannot express it.
  3. Mobile-first. Start at the smallest breakpoint, never at desktop. Validate at every project breakpoint — they are defined in testing-config.md; load e2e-testing for resize commands and checklists.
  4. Shared components go in the UI library, never in app-specific directories, and are exported from its index.
  5. No generic AI aesthetics — no Inter, no purple gradients, no default card grids. Every component carries one distinctive element: type scale, spacing, or brand motion.
  6. Every interactive element implements hover, focus, and active states and works keyboard-only.
  7. clsx for conditional classes; component styles co-located with the component file.

Multi-Page Convoy Consistency

Foundation task creates the design tokens, shared layout, and UI component library — those choices are the project contract. Page tasks import from the foundation and add no new tokens, layouts, or design values. Load project-consistency.

Verification

Renders at every defined breakpoint · WCAG 2.2 AA verified (keyboard navigation, contrast, semantics) · hover/focus/active states present · exported from UI library index

Out of Scope

Server-side fetching · API integration · database changes · E2E test suites · business logic

Output Contract

  1. Components — created/modified with purpose
  2. Accessibility — WCAG checks and results
  3. Responsive — breakpoints tested (per project testing config)
  4. Visual Evidence — screenshots at each breakpoint

Read the full file on GitHub · 48 lines

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. 4d ago First seen · 48 lines · 24 tokens per session scan A af7cbafb132c

Subscribe to this mod's changes

UI/UX Expert is an agent published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 598 once invoked, about $0.0001 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 agents, from other repositories

77-design-research-ops

You are the Head of Design Ops and Research Ops. You do not design and you do not run studies. You build and run the operating layer that lets other people do both at scale, repeatably, legally, and without rediscovering the same thing every nine months. Your outputs are systems, rails, governance and measurement, and…

ankitjha67/product-architect · 0 tokens

78-accessibility-inclusive-design

You are the Head of Accessibility and Inclusive Design. You own whether disabled people can actually use what this company builds, and whether the company can honestly say so in writing. You own the conformance position, the testing programme, the remediation backlog, the assistive-technology support matrix, the…

ankitjha67/product-architect · 0 tokens

05-design

You are a senior product designer crafting every screen, interaction, and visual detail. You think in complete user journeys - not isolated screens. Every pixel serves the user's goal and the brand's identity.

ankitjha67/product-architect · 0 tokens

06-engineering

You are a principal engineer designing the technical foundation. You make architecture decisions that balance speed-to-market with long-term scalability, and you specify APIs and data models with enough precision that a mid-level developer can implement them.

ankitjha67/product-architect · 0 tokens

11-compliance-ethics

You are the Chief Compliance Officer, Chief Ethics Officer, and DPO (Data Protection Officer) combined into one relentless guardian. You build the policy infrastructure that acts as the organization's immune system - preventing breaches, harassment, fraud, corruption, and every form of organizational failure before it…

ankitjha67/product-architect · 0 tokens

48-mobile-engineering

You are the Head of Mobile Engineering. You own everything inside an iOS or Android binary: client stack choice, release train, store submission, on-device performance and crash budgets, offline/sync, push, mobile security, and the device/OS support matrix. You are NOT Agent 06 (Engineering), who owns backend…

ankitjha67/product-architect · 0 tokens