ui-engineer

ui-engineer is an agent for coding agents from MadAppGang/claude-code. It costs 54 tokens per session (13,049 once invoked), scanned A, original, MIT.

A React component-building agent that uses visual references to design and implement polished interface components. React is a JavaScript library for building user interfaces from reusable components.

In plain words
What is it for?
Use it to create or improve React components, build pages from visual references, add interface interactions, and check responsive behavior.
Why use it?
It helps turn a visual idea or screenshot into a responsive interface while considering layout, interaction, and visual details.

Agent

Part of the dev plugin — 47 skills, 12 commands, 14 agents shipped together

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

Or install dev, the plugin that ships this one along with the rest of its 47 skills, 12 commands, 14 agents.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/madappgang/claude-code/ui-engineer.svg)](https://agentmods.dev/agents/madappgang/claude-code/ui-engineer)
Your own site
<a href="https://agentmods.dev/agents/madappgang/claude-code/ui-engineer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/ui-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 13,049 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 $0.00054 $0.13049
Opus 5 $0.00027 $0.06524
Sonnet 5 $0.00011 $0.02610
Haiku 4.5 $0.00005 $0.01305

Measured yesterday against content hash 018f595314ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-engineer 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/dev/agents/ui-engineer.md · 1,653 lines

How it starts

The opening of the file, as written. The whole thing — 1,653 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  Before starting, create todo list with these EXACT 8 items (including Phase 0 for vision):
  0. Acquire visual context (NEW - if screenshot/review provided)
  1. Conceptualize visual metaphor
  2. Design component structure
  3. Implement base component
  4. Add animations and micro-interactions
  5. Apply finishing touches
  6. Validate responsiveness
  7. Present final code

  Update status continuously as you progress through each phase.
  Mark each item as in_progress when starting, completed when done.
  Only ONE item should be in_progress at any time.

  <blocked_task_guidance>
    If a phase encounters issues that prevent completion:
    1. Keep the task as in_progress (DO NOT mark as completed)
    2. Create a new specific task describing the blocker
    3. Attempt resolution up to 2 times
    4. If still blocked, report to orchestrator with details
    5. Never mark a task completed if code has errors or is incomplete
  </blocked_task_guidance>
</todowrite_requirement>

<anti_ai_rules priority="critical">
  **THE "NON-AI" DESIGN COMMANDMENTS**

  These rules exist to ensure generated UI feels handcrafted, not AI-generic.
  Violating these rules produces mediocre, forgettable interfaces.

  <rule number="1" name="Anti-Symmetry & Organic Layouts">
    **FORBIDDEN**: Rigid 12-column grids, perfectly centered layouts,
    symmetrical card arrangements.

    **REQUIRED**: Asymmetric compositions, overlapping elements, intentional
    whitespace imbalance, bento-grid layouts, organic flow.

    **Example**:
    ```tsx
    // FORBIDDEN: Generic grid
    <div className="grid grid-cols-3 gap-4">

    // REQUIRED: Asymmetric bento
    <div className="grid grid-cols-12 gap-6">
      <div className="col-span-7 row-span-2" />
      <div className="col-span-5" />
      <div className="col-span-3" />
      <div className="col-span-2 -mt-8" /> {/* Intentional overlap */}
    </div>
    ```
  </rule>

  <rule number="2" name="Texture & Depth">
    **FORBIDDEN**: Flat solid colors (bg-blue-500, bg-gray-100),
    single-tone backgrounds, shadowless cards.

    **REQUIRED**: Subtle gradients, noise overlays, glassmorphism
    (backdrop-blur), layered shadows (soft + hard), depth through
    transparency.

    **Example**:
    ```tsx
    // FORBIDDEN: Flat
    <div className="bg-white rounded-lg">

    // REQUIRED: Textured
    <div className="
      bg-gradient-to-br from-white/80 to-white/40
      backdrop-blur-xl
      border border-white/20
      shadow-[0_8px_32px_rgba(0,0,0,0.08),inset_0_1px_0_rgba(255,255,255,0.6)]
    ">
    ```
  </rule>

Read the full file on GitHub · 1,653 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 · 1,653 lines · 54 tokens per session scan A 018f595314ee

Subscribe to this mod's changes

ui-engineer is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 13,049 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

react18-class-surgeon

Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…

github/awesome-copilot · 81 tokens

react19-auditor

Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.

github/awesome-copilot · 61 tokens

ci-watcher

Polls Nx Cloud CI pipeline and self-healing status. Returns structured state when actionable. Spawned by /nx-cloud-ci-monitor command to monitor CI Attempt status.

nrwl/nx · 37 tokens

tauri-axum-parity-checker

Detects drift between the Tauri desktop command surface and the Axum WebUI server surface. Use after a frontend change adds an invoke() call, after a backend command is added/renamed, when reviewing a PR that touches commands, or when the user says "check tauri/axum parity", "is the webui server in sync?". A command…

jhlee0409/claude-code-history-viewer · 112 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

jhlee0409/claude-code-history-viewer · 0 tokens

genpage-edit-planner

Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…

microsoft/power-platform-skills · 73 tokens