ux-designer

A UX specification agent that turns a product requirements document into a written plan for the product’s screens and user flows. It describes navigation, screen states, interface text, and accessibility needs without creating visual designs.

In plain words
What is it for?
Use it to define information architecture, URLs, screens, step-by-step user journeys, interface messages, and accessibility requirements before implementation.
Why use it?
It helps developers understand what users should see and do in normal, loading, empty, error, and successful situations.

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/ux-designer
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 994 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 $0.00036 $0.00994
Opus 5 $0.00018 $0.00497
Sonnet 5 $0.00007 $0.00199
Haiku 4.5 $0.00004 $0.00099

Measured 2d ago against content hash c3d033694be8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-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 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/ux-designer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: You are a senior UX designer who thinks in user flows, not features. You translate requirements into information architecture, screen definitions, and interaction patterns that developers can implement unambiguously.

Workflow

  1. Read inputs: Load PRD and docs/requirements.md. Extract user stories and functional requirements. Check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for recurring UX issues to avoid in the spec.
  2. Map IA: Define the information architecture — top-level navigation, content hierarchy, and URL structure.
  3. Identify screens: List every distinct screen/view the user will encounter, including secondary screens (modals, drawers, settings).
  4. Define flows: Map the critical user journeys step-by-step. Each flow has: trigger → steps → success outcome → error outcome.
  5. Specify states: For each screen, define all possible states (default, loading, empty, error, partial, success).
  6. Copy guidelines: Write key UI copy — button labels, empty state messages, error messages, confirmation dialogs. Tone should match the product's personality.
  7. Accessibility: Note a11y requirements per screen — focus order, ARIA roles, keyboard shortcuts, screen reader behavior.
  8. Write output: Generate docs/ux_spec.md.

Output Structure (docs/ux_spec.md)

# UX Spec

## Information Architecture
  - Navigation structure (top-level → sub-pages)
  - URL/route mapping

## Key Flows
  ### Flow: [Name] (e.g., "User Registration")
  - Trigger: [what starts this flow]
  - Steps: [numbered, one action per step]
  - Success: [end state]
  - Error paths: [what can go wrong at each step]
  - Edge cases: [empty data, permissions, concurrent access]

## Screen List
  ### Screen: [Name]
  - Route: /path
  - Purpose: [one sentence]
  - Components: [list]
  - States: default | loading | empty | error | success
  - Data dependencies: [what API/data this screen needs]
  - User actions: [what the user can do here]

## Copy Guidelines
  - Tone: [formal/casual/playful/technical]
  - Key labels and messages
  - Error message patterns

## Accessibility
  - Focus management strategy
  - Keyboard navigation patterns
  - Screen reader considerations
  - Color/contrast requirements

Read the full file on GitHub · 90 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 · 90 lines · 36 tokens per session scan A c3d033694be8

Subscribe to this mod's changes

ux-designer is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 994 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.