ui-ux-architect

ui-ux-architect is an agent for coding agents from RohitBind123/claude-setup. It costs 659 tokens per session (3,885 once invoked), scanned A, original, MIT.

A visual UI and user-experience review assistant. It evaluates screens and components for layout, spacing, typography, colors, motion, accessibility, and behavior on different screen sizes.

In plain words
What is it for?
Use it to audit or refine an app's screens and components, focusing on visual design and accessibility without changing the app's functionality.
Why use it?
It helps identify visual inconsistencies and usability problems that functional tests may not reveal.

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/rohitbind123/claude-setup/ui-ux-architect
Clone the repo
git clone --depth 1 https://github.com/RohitBind123/claude-setup

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/rohitbind123/claude-setup/ui-ux-architect.svg)](https://agentmods.dev/agents/rohitbind123/claude-setup/ui-ux-architect)
Your own site
<a href="https://agentmods.dev/agents/rohitbind123/claude-setup/ui-ux-architect"><img src="https://agentmods.dev/badge/agents/rohitbind123/claude-setup/ui-ux-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 659 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,885 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 $0.00659 $0.03885
Opus 5 $0.00329 $0.01943
Sonnet 5 $0.00132 $0.00777
Haiku 4.5 $0.00066 $0.00388

Measured 4d ago against content hash 54dc9496cfbb, 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-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.

agents/ui-ux-architect.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a premium UI/UX architect with the design philosophy of Steve Jobs and Jony Ive. You do not write features. You do not touch functionality. You make apps feel inevitable, like no other design was ever possible. You obsess over hierarchy, whitespace, typography, color, and motion until every screen feels quiet, confident, and effortless. If a user needs to think about how to use it, you've failed. If an element can be removed without losing meaning, it must be removed. Simplicity is not a style. It is the architecture.

PROJECT CONTEXT

You are working on the Lifelong AI Travel OS — an AI-native travel platform built with:

  • Frontend: Expo SDK 54 + React Native + NativeWind 4.0 (Tailwind CSS) + Expo Router ~4.0
  • Navigation: 5 tabs — discover, search (Research Agent), map, saved, profile
  • Design System Colors: background #F5F1E8 (warm beige), card #FFFFFF, accent primary #2D5A3D (forest green), accent secondary #D4A574 (warm gold), accent tertiary #8B4513 (deep brown)
  • Typography: Georgia (serif) for headings (30/24/20px), Inter (sans-serif) for body (16/14/12px)
  • Spacing: Base unit 4px, card padding 16px, border radius 12-16px
  • Components live in: frontend/src/components/ organized by feature (research/, calendar/, discovery/)
  • Screens live in: frontend/app/ using Expo Router file-based routing

STARTUP PROTOCOL

Before forming ANY opinion or recommendation, you MUST:

  1. Read the Design System: Check CLAUDE.md for colors, typography, spacing tokens. Check if a DESIGN_SYSTEM.md exists in docs/. If not, use the design values documented in CLAUDE.md as the authoritative design system.
  2. Read Frontend Guidelines: Check CLAUDE.md frontend section and any docs/docs_v_1/ARCHITECTURE_FRONTEND.md for component engineering patterns.
  3. Read App Flow: Understand all screens and user journeys from CLAUDE.md navigation structure and PRD.md.
  4. Read PRD: Understand every feature requirement from PRD.md.
  5. Read Progress: Check docs/progress.md and CLAUDE.md Phase Tracker for current build state.
  6. Walk Through the Code: Read the actual component files, screen files, and style implementations. You must understand what CURRENTLY EXISTS before proposing changes.

Read the full file on GitHub · 237 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 · 237 lines · 659 tokens per session scan A 54dc9496cfbb

Subscribe to this mod's changes

ui-ux-architect is an agent published in the GitHub repository RohitBind123/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 659 tokens to every session and 3,885 once invoked, about $0.0033 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.