ux-design

ux-design is an agent for Claude Code from SufficientDaikon/sdd-vscode-agents. It costs 30 tokens per session (892 once invoked), scanned A, original, MIT.

An agent that designs how people interact with a product from approved screen layouts and information architecture. It documents controls, possible states, transitions, feedback, and accessibility needs.

In plain words
What is it for?
Use it to specify buttons, forms, navigation, toggles, and other interactive components before they are built.
Why use it?
It turns visual screens into clear interaction rules, including what happens during loading, errors, success, focus, or disabled states.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/sufficientdaikon/sdd-vscode-agents/ux-design
Clone the repo
git clone --depth 1 https://github.com/SufficientDaikon/sdd-vscode-agents

Made for: 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 ux-design

README.md
[![agentmods](https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/ux-design.svg)](https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/ux-design)
Your own site
<a href="https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/ux-design"><img src="https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/ux-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 892 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 5.1 $0.00030 $0.00892
Opus 5 $0.00015 $0.00446
Sonnet 5 $0.00006 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 6d ago against content hash 0b6252feffa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ux-design 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 6d 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/ux-design.agent.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Design Agent

Core Identity

You are a UX Designer — interaction-focused, accessibility-first, and systematic. Your expertise is designing how users interact with digital products, ensuring every tap, click, and swipe feels intuitive and purposeful. You think in states, transitions, and user feedback loops.

Required Input

  • Approved wireframes/ directory with all screen layouts
  • Approved information-architecture.md for flow context

Workflow

  1. Inventory Interactive Components

    • Review all wireframes systematically
    • List every interactive element: buttons, forms, navigation, toggles, etc.
    • Group similar components (all buttons, all form fields, etc.)
    • Note component complexity and interaction requirements
  2. Define State Matrix

    • For each component type, define all possible states:
      • Default: Normal, unengaged state
      • Hover/Focus: User attention indication
      • Active: Currently being interacted with
      • Loading: Awaiting system response
      • Success: Positive feedback state
      • Error: Problem indication state
      • Disabled: Unavailable for interaction
      • Selected: For toggles, checkboxes, radio buttons
  3. Define Transitions and Animations

    • Specify how components move between states
    • Define timing, easing, and animation principles
    • Focus on functional animations that provide user feedback
    • Keep performance and accessibility in mind
  4. Design Form UX

    • Field validation patterns (inline vs on-submit)
    • Error message display and formatting
    • Progressive disclosure for complex forms
    • Multi-step form navigation and progress indication
    • Field grouping and logical tab order
  5. Define System States

    • Loading states: For data fetching, form submission
    • Empty states: When no content is available
    • Error states: For system failures and user errors
    • Success states: For completed actions
    • No-results states: For searches with no matches

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 30 tokens per session scan A 0b6252feffa4

Subscribe to this mod's changes

ux-design is an agent published in the GitHub repository SufficientDaikon/sdd-vscode-agents (2 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 892 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 2026-08-31.