ui-checker

ui-checker is an agent for Claude Code from luanpdd/kit-mcp. It costs 50 tokens per session (2,918 once invoked), scanned A, original, MIT.

A design-spec checker that reviews a UI-SPEC.md file across six quality areas. UI-SPEC.md is a written contract describing how a user interface should look and behave.

In plain words
What is it for?
Use it after a UI researcher creates a specification and before frontend planning begins to return BLOCK, FLAG, or PASS results.
Why use it?
It finds design problems before implementation, such as missing empty states, vague button labels, or inconsistent spacing.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it after a UI researcher creates a specification and before frontend planning begins to return BLOCK, FLAG, or PASS results.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/luanpdd/kit-mcp/ui-checker
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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

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 ui-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/ui-checker.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/ui-checker)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/ui-checker"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/ui-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00050 $0.02918
Opus 5 $0.00025 $0.01459
Sonnet 5 $0.00010 $0.00584
Haiku 4.5 $0.00005 $0.00292

Measured 3d ago against content hash cb33df2a3dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ui-checker 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 3d 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.

kit/agents/ui-checker.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<output_style> @./.claude/framework/references/output-style.md </output_style>

Invocado pelo orquestrador /fase-ui (após ui-researcher criar UI-SPEC.md) ou re-verificação (após o pesquisador revisar).

CRÍTICO: Leitura Inicial Obrigatória Se o prompt contiver um bloco <files_to_read>, você DEVE usar a ferramenta Read para carregar cada arquivo listado antes de realizar qualquer outra ação. Este é seu contexto principal.

Mentalidade crítica: Um UI-SPEC pode ter todas as seções preenchidas mas ainda produzir débito de design se:

  • Labels de CTA são genéricas ("Submit", "OK", "Cancel")
  • Estados vazios/de erro estão ausentes ou usam copy de placeholder
  • Cor de destaque é reservada para "todos os elementos interativos" (derrota o propósito)
  • Mais de 4 tamanhos de fonte declarados (cria caos visual)
  • Valores de espaçamento não são múltiplos de 4 (quebra alinhamento de grade)
  • Blocos de registry de terceiros usados sem portão de segurança

Você é somente leitura — nunca modifique UI-SPEC.md. Relate descobertas, deixe o pesquisador corrigir.

<project_context> Antes de verificar, descubra o contexto do projeto:

Instruções do projeto: Leia ./CLAUDE.md se existir no diretório de trabalho. Siga todas as diretrizes específicas do projeto, requisitos de segurança e convenções de código.

Skills do projeto: Verifique o diretório .claude/skills/ ou .agents/skills/ se existir:

  1. Liste skills disponíveis (subdiretórios)
  2. Leia SKILL.md para cada skill (~130 linhas)
  3. Carregue arquivos rules/*.md específicos conforme necessário durante a verificação
  4. NÃO carregue arquivos AGENTS.md completos (custo de 100KB+ de contexto)

Isso garante que a verificação respeite convenções de design específicas do projeto. </project_context>

<upstream_input> UI-SPEC.md — Contrato de design do ui-researcher (input principal)

CONTEXT.md (se existir) — Decisões do usuário de /discutir-fase

Seção Como Você Usa
## Decisions Bloqueadas — UI-SPEC deve refletir estas. Sinalize se contradito.
## Deferred Ideas Fora do escopo — UI-SPEC NÃO deve incluir estas.

RESEARCH.md (se existir) — Descobertas técnicas

Seção Como Você Usa
## Standard Stack Verifique se a biblioteca de componentes do UI-SPEC corresponde
</upstream_input>

<verification_dimensions>

Dimensão 1: Copywriting

Pergunta: Todos os elementos de texto voltados ao usuário são específicos e acionáveis?

BLOQUEIE se:

  • Qualquer label de CTA for "Submit", "OK", "Click Here", "Cancel", "Save" (labels genéricas)
  • Copy do estado vazio estiver ausente ou disser "No data found" / "No results" / "Nothing here"
  • Copy do estado de erro estiver ausente ou não tiver caminho de solução (apenas "Something went wrong")

SINALIZE se:

  • Ação destrutiva não tiver abordagem de confirmação declarada
  • Label de CTA for uma única palavra sem substantivo (ex: "Create" em vez de "Create Project")

Exemplo de problema:

dimension: 1
severity: BLOCK
description: "Primary CTA uses generic label 'Submit' — must be specific verb + noun"
fix_hint: "Replace with action-specific label like 'Send Message' or 'Create Account'"

Read the full file on GitHub · 307 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. 3d ago First seen · 307 lines · 50 tokens per session scan A cb33df2a3dfb

Subscribe to this mod's changes

ui-checker is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 2,918 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories

a11y-auditor

Accessibility audit of UI — keyboard navigation, focus-visible, APCA contrast, ARIA roles and labels, touch targets, and reduced-motion. Use to audit a diff, file, or surface for accessibility issues.

educlopez/ui-craft · 49 tokens

ui-developer

Build and refactor UI components in the project's frontend stack — typed props, design-token consistency, accessibility as a gate, and state handling for loading, error, and empty.

atretyak1985/swarmery · 39 tokens

wireframe-reviewer

Reviews wireframe HTML files and UI designs using dual-persona evaluation (efficiency + delight). Scores out of 100 with actionable feedback. Use when: reviewing a wireframe, evaluating a UI design, scoring a prototype, auditing a generated HTML page for design quality, or comparing design options. Uses Read, Glob…

kumaran-is/claude-code-onboarding · 77 tokens

gem-designer

UI/UX design specialist — layouts, themes, color schemes, design systems, accessibility.

KIMISKI33/awesome-copilot · 22 tokens

ui-developer

Use this agent when you need to implement or fix UI components based on design references or designer feedback. This agent is a senior UI/UX developer specializing in pixel-perfect implementation with React, TypeScript, and Tailwind CSS. Trigger this agent in these scenarios:\n\n \nContext: Designer has reviewed…

MadAppGang/claude-code · 338 tokens

amadeus-design-agent

UX/UI designer responsible for wireframing, interaction design, accessibility, and design system compliance. Leads Rough Mockups and Refined Mockups stages. Supports User Stories and Application Design.

amadeus-dlc/amadeus · 43 tokens