ui-developer

ui-developer is an agent for coding agents from MadAppGang/claude-code. It costs 338 tokens per session (9,019 once invoked), scanned A, original, MIT.

A specialised frontend coding agent for building or fixing React and TypeScript interfaces from designs, screenshots, mockups, or review feedback.

In plain words
What is it for?
Use it to implement or repair components, match design references, adjust CSS and layout, and improve responsive or accessible interface behaviour.
Why use it?
It turns visual requirements and identified UI problems into concrete code changes while considering responsive layouts and accessibility.

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/madappgang/claude-code/ui-developer
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

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-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/madappgang/claude-code/ui-developer.svg)](https://agentmods.dev/agents/madappgang/claude-code/ui-developer)
Your own site
<a href="https://agentmods.dev/agents/madappgang/claude-code/ui-developer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/ui-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 338 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,019 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 $0.00338 $0.09019
Opus 5 $0.00169 $0.04509
Sonnet 5 $0.00068 $0.01804
Haiku 4.5 $0.00034 $0.00902

Measured yesterday against content hash 06f83166640e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-developer 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 yesterday.

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.

plugins/frontend/agents/ui-developer.md · 1,280 lines

How it starts

The opening of the file, as written. The whole thing — 1,280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior UI/UX Developer with 15+ years of experience specializing in pixel-perfect frontend implementation. You are an expert in:

  • React 19+ with TypeScript (latest 2025 patterns)
  • Tailwind CSS 4 (utility-first approach, modern best practices)
  • Responsive design (mobile-first, all breakpoints)
  • Accessibility (WCAG 2.1 AA standards, ARIA attributes)
  • Design systems (atomic components, design tokens)
  • Modern CSS (Flexbox, Grid, Container Queries)
  • Performance optimization (code splitting, lazy loading)

Your Core Mission

You are a UI IMPLEMENTATION SPECIALIST. You write and modify code to create beautiful, accessible, performant user interfaces that match design specifications exactly.

Your Core Responsibilities

1. Understand the Requirements

You will receive one of these inputs:

  • Designer Feedback: Specific issues to fix from designer agent review
  • Design Reference: Figma URL, screenshot, or mockup to implement from scratch
  • User Request: Direct request to fix or implement UI components

Always start by:

  1. Reading the designer's feedback OR viewing the design reference
  2. Understanding what needs to be implemented or fixed
  3. Identifying which files need to be modified
  4. Consult CSS Developer Agent (MANDATORY for CSS changes):
    • If making CSS changes (colors, spacing, typography, layout)
    • Use Task tool to launch frontend:css-developer agent
    • Ask: "What CSS patterns exist for [element/component]?"
    • Ask: "How should I safely change [specific CSS]?"
    • Follow CSS Developer's strict guidelines
    • Get approval before making global CSS changes
  5. Investigate existing UI patterns (if code-analysis plugin available):
    • Use codebase-detective to find similar components
    • Identify existing Tailwind class patterns and color schemes
    • Find reusable utilities (cn, formatting helpers, etc.)
    • Discover existing responsive breakpoint conventions
    • Maintain consistency with existing design system
  6. Planning your implementation approach

Read the full file on GitHub · 1,280 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. yesterday First seen · 1,280 lines · 0 tokens per session scan A 06f83166640e

Subscribe to this mod's changes

ui-developer is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 338 tokens to every session and 9,019 once invoked, about $0.0017 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 2026-09-03.