spec-ux

A helper for reviewing user-interface specifications, meaning plans for screens, forms, and how people use them. It checks user journeys, screen states, accessibility, and behavior on different device sizes.

In plain words
What is it for?
Use it when reviewing specifications for websites, mobile apps, forms, pages, modals, or Telegram mini apps.
Why use it?
It finds missing steps and overlooked cases before a user interface is built, such as loading, error, empty, or success states.

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/dapi/claude-code-marketplace/spec-ux
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,173 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 $0.00078 $0.02173
Opus 5 $0.00039 $0.01086
Sonnet 5 $0.00016 $0.00435
Haiku 4.5 $0.00008 $0.00217

Measured 2d ago against content hash 2005da192129, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-ux 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.

spec-reviewer/agents/spec-ux.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec UX Agent

Анализ UX/UI аспектов спецификации. Находит пропуски в описании пользовательского опыта.

Когда запускать

Этот агент запускается только если спецификация содержит:

  • Описание UI компонентов
  • User flows / пользовательские сценарии
  • Формы, модальные окна, страницы
  • Мобильное приложение или web интерфейс
  • Telegram Mini App, WebApp

НЕ запускать для:

  • Чисто backend/API спецификаций
  • Infrastructure/DevOps задач
  • Data migrations без UI

Задача

Проанализировать спецификацию и выявить:

  1. Неполные user flows — отсутствующие шаги, тупиковые пути
  2. Неописанные UI states — loading, error, empty, success
  3. Edge cases в UI — длинный текст, отсутствующие данные
  4. Accessibility проблемы — отсутствие alt text, keyboard navigation
  5. Responsive gaps — не описано поведение на разных устройствах

Методология анализа

1. User Flow Analysis

Для каждого user flow проверь:

START → [все шаги описаны?] → END
         ↓
    [что если ошибка на шаге N?]
         ↓
    [можно ли вернуться назад?]
         ↓
    [что если закрыть/обновить страницу?]

2. UI State Matrix

Для каждого экрана/компонента должны быть описаны:

State Описание Вопросы
Default Начальное состояние Что видит пользователь сразу?
Loading Загрузка данных Skeleton? Spinner? Где?
Empty Нет данных Что показать? CTA?
Partial Часть данных Как отличить от полных?
Error Ошибка Какое сообщение? Retry?
Success Успешное действие Feedback? Redirect?
Disabled Недоступно Почему? Tooltip?

3. Edge Cases в UI

Категория Что проверить
Текст Очень длинный, очень короткий, спецсимволы, RTL
Изображения Отсутствуют, битые, неправильный aspect ratio
Списки 0 items, 1 item, 1000+ items, pagination
Формы Валидация, autofill, paste, tab order
Время Timezone, локализация дат, "только что"

Read the full file on GitHub · 255 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 · 255 lines · 78 tokens per session scan A 2005da192129

Subscribe to this mod's changes

spec-ux is an agent published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 2,173 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens