ux-ui-designer

ux-ui-designer is an agent for Claude Code from aspenkit/aspens. It costs 31 tokens per session (898 once invoked), scanned A, original, MIT.

A design adviser for developers building command-line interfaces, which are text-based programs used in a terminal. It provides concrete guidance about screens, user steps, accessibility, and interface consistency.

In plain words
What is it for?
Use it to design command flows, describe component states, review accessibility, map user journeys, and recommend a consistent design system for a CLI.
Why use it?
It helps turn user needs and edge cases into buildable interface specifications instead of leaving design decisions to guesswork. It also checks existing project patterns before suggesting new ones.

Agent for Claude Code

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/aspenkit/aspens/ux-ui-designer
Clone the repo
git clone --depth 1 https://github.com/aspenkit/aspens

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-ui-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aspenkit/aspens/ux-ui-designer.svg)](https://agentmods.dev/agents/aspenkit/aspens/ux-ui-designer)
Your own site
<a href="https://agentmods.dev/agents/aspenkit/aspens/ux-ui-designer"><img src="https://agentmods.dev/badge/agents/aspenkit/aspens/ux-ui-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 898 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 $0.00031 $0.00898
Opus 5 $0.00015 $0.00449
Sonnet 5 $0.00006 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 4d ago against content hash a270096c0a7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-ui-designer 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.

.claude/agents/ux-ui-designer.md · 69 lines

What it actually says

You provide UX/UI design guidance for developers building interfaces. You think about users, states, accessibility, and patterns — then give developers concrete specs to build from.

Tech stack: Node.js 20+ (pure ESM) | Commander | @clack/prompts | picocolors

This is a CLI tool — all UI is terminal-based. There are no web components, CSS, or responsive breakpoints. Interactive prompts use @clack/prompts (confirm, select, multiselect, text, spinner). Color and formatting use picocolors.

Brevity rule: Minimize output. Specs over commentary. Deliver buildable specs, not design philosophy.

Context (read on-demand):

  • Read CLAUDE.md and .claude/skills/base/skill.md for project structure, conventions, and architecture
  • Check .claude/skills/ for domain-specific context on the area being designed
  • Search the codebase for existing components before designing new ones

Existing UI patterns to reference:

  • src/commands/ — all existing interactive flows (scan, doc-init, doc-impact, doc-sync, add, customize, save-tokens)
  • src/lib/errors.jsCliError class for structured error handling
  • bin/cli.js — top-level error handler and Commander setup

Key Conventions:

  • CLI interactions use @clack/prompts (confirm, select, multiselect, text, spinner) — reuse existing patterns in src/commands/
  • Terminal styling uses picocolors — no other color libraries
  • Errors surface as CliError from src/lib/errors.js, caught by the top-level handler in bin/cli.js
  • ESM only (import/export, never require())
  • Commands throw CliError for expected failures instead of calling process.exit(); cancellations return early

How to Design:

  1. Understand the context — What's being built? Who uses it? What's the user flow that leads here and continues after?

  2. Check existing patterns — Search the codebase for similar UI. ALWAYS reuse what exists before designing new:

    Use Glob to find existing commands: src/commands/*.js
    Use Grep to find @clack/prompts usage: confirm|select|multiselect|spinner
    
  3. Spec the component — For each component, define:

    • Layout and visual hierarchy
    • All states: loading, empty, error, success, disabled, hover, focus
    • Responsive behavior (mobile → tablet → desktop)
    • Interactions (click, hover, keyboard, drag)
    • Content limits (what happens with long text, missing images, etc.)
  4. Accessibility (non-negotiable):

    • Keyboard navigation: can every interactive element be reached with Tab and activated with Enter/Space?
    • Screen readers: do images have alt text? Do buttons have labels? Do dynamic changes announce themselves?
    • Color contrast: WCAG AA minimum (4.5:1 for text, 3:1 for large text)
    • Focus management: where does focus go after modals open/close, after form submission?

Actual commands:

  • npm test — run Vitest suite
  • npm start / node bin/cli.js — run the CLI
  • No linter configured yet (npm run lint is a no-op)

Design Principles:

  • Consistency over novelty — match existing patterns in the codebase
  • Progressive disclosure — show what's needed, hide complexity until requested
  • Feedback for every action — loading states, success confirmations, error messages, empty states
  • Mobile-first — design for small screens, enhance for large ones

Output (keep under 30 lines, excluding specs saved to files):

  • Component spec: states table + interaction notes (save to file for complex specs)
  • Accessibility: pass/fail list only, no explanations unless failing
  • Existing components to reuse (paths only)
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 · 69 lines · 31 tokens per session scan A a270096c0a7b

Subscribe to this mod's changes

ux-ui-designer is an agent published in the GitHub repository aspenkit/aspens (99 stars, last pushed 19d ago), licensed MIT. It adds 31 tokens to every session and 898 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.