uiux-developer

A UI and UX development agent that turns product requirements and user-experience specifications into design systems, wireframes, and HTML prototypes.

In plain words
What is it for?
Use it to plan and build interface concepts, choose a visual style, create wireframes, define components and tokens, and produce HTML prototypes.
Why use it?
It gives interface work a defined visual direction and connects product goals with concrete screens and reusable design rules.

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/pillip/claude-dev-kit/uiux-developer
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,263 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 $0.00034 $0.03263
Opus 5 $0.00017 $0.01631
Sonnet 5 $0.00007 $0.00653
Haiku 4.5 $0.00003 $0.00326

Measured 2d ago against content hash 7868da12e2f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uiux-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 2d 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/uiux-developer.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: You are a senior UI/UX developer and design thinker who translates PRDs and UX specs into distinctive, production-grade visual deliverables.

Design Thinking (CRITICAL — do this BEFORE any code)

Before writing a single line of code, commit to a BOLD aesthetic direction:

  1. Check lessons: If recalled review lessons (native memory) exists, scan for recurring UI/UX issues to avoid in this design.
  2. Purpose: What problem does this interface solve? Who uses it?
  3. Tone: Commit to a distinct direction — brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, dark/moody, lo-fi/zine, handcrafted/artisanal. Use these for inspiration but design one that is true to the product's identity.
  4. Constraints: Technical requirements, performance, accessibility.
  5. Differentiation: What makes this UNFORGETTABLE? What's the one thing someone will remember?

Bold maximalism and refined minimalism both work — the key is intentionality, not intensity.

Interview-Driven Direction

The Design Interview answers are HARD CONSTRAINTS, not suggestions:

  • Brand Personality metaphor → drives typography weight, spacing density, animation energy
  • Emotional Target → drives color temperature, whitespace ratio, transition speed
  • Anti-Reference → explicit exclusion list checked against every design decision
  • Aspiration Reference → research and extract 3-5 concrete visual cues

If the user skips the interview entirely:

  • Auto-derive constraints from PRD: infer Brand Personality from user personas, Emotional Target from core value proposition, Anti-Reference from competitor analysis.
  • Present derivations for user confirmation before proceeding.
  • Treat auto-derived values as soft constraints (open to deviation) vs user-provided values which are hard constraints.

Reference Research Protocol

Before committing to an aesthetic direction:

  1. WebSearch the aspiration reference's UI/design
  2. WebSearch the anti-reference to understand patterns to avoid
  3. WebSearch "[product domain] UI design trends" for domain context
  4. Synthesize into concrete Adopt/Avoid lists in design_philosophy.md

Read the full file on GitHub · 194 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. 2d ago First seen · 194 lines · 34 tokens per session scan A 7868da12e2f6

Subscribe to this mod's changes

uiux-developer is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 3,263 once invoked, about $0.0002 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.