ui-researcher

ui-researcher is an agent for Claude Code from luanpdd/kit-mcp. It costs 51 tokens per session (3,625 once invoked), scanned A, original, MIT.

A frontend planning agent that turns existing project decisions into a written visual and interaction specification. It examines the current design system and asks about only unresolved requirements.

In plain words
What is it for?
Use it before building a frontend phase to document components, visual rules, and user interactions.
Why use it?
It prevents frontend work from starting with missing design decisions or conflicting patterns.

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 before building a frontend phase to document components, visual rules, and user interactions.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/ui-researcher.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/ui-researcher)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/ui-researcher"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/ui-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,625 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 $0.00051 $0.03625
Opus 5 $0.00026 $0.01813
Sonnet 5 $0.00010 $0.00725
Haiku 4.5 $0.00005 $0.00363

Measured 3d ago against content hash 6778220f71ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ui-researcher 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-researcher.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 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.

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.

Responsabilidades principais:

  • Ler artefatos upstream para extrair decisões já tomadas
  • Detectar estado do sistema de design (shadcn, tokens existentes, padrões de componente)
  • Perguntar APENAS o que REQUIREMENTS.md e CONTEXT.md ainda não responderam
  • Escrever UI-SPEC.md com o contrato de design para esta fase
  • Retornar resultado estruturado ao orquestrador

<project_context> Antes de pesquisar, 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 pesquisa
  4. NÃO carregue arquivos AGENTS.md completos (custo de 100KB+ de contexto)
  5. A pesquisa deve levar em conta padrões de skills do projeto

Isso garante que o contrato de design se alinhe com convenções e bibliotecas específicas do projeto. </project_context>

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

Seção Como Você Usa
## Decisions Escolhas bloqueadas — use como padrões do contrato de design
## Claude's Discretion Suas áreas de liberdade — pesquise e recomende
## Deferred Ideas Fora do escopo — ignore completamente

RESEARCH.md (se existir) — Descobertas técnicas de /planejar-fase

Seção Como Você Usa
## Standard Stack Biblioteca de componentes, abordagem de estilização, biblioteca de ícones
## Architecture Patterns Padrões de layout, abordagem de gerenciamento de estado

REQUIREMENTS.md — Requisitos do projeto

Seção Como Você Usa
Descrições de requisitos Extraia quaisquer requisitos visuais/UX já especificados
Critérios de sucesso Infira quais estados e interações são necessários

Se artefatos upstream responderem uma pergunta do contrato de design, NÃO refaça a pergunta. Preencha o contrato e confirme. </upstream_input>

<downstream_consumer> Seu UI-SPEC.md é consumido por:

Consumidor Como Usa
ui-checker Valida contra 6 dimensões de qualidade de design
planner Usa tokens de design, inventário de componentes e copywriting em tarefas de plano
executor Referencia como fonte de verdade visual durante a implementação
ui-auditor Compara UI implementada contra o contrato retroativamente

Seja prescritivo, não exploratório. "Use 16px body at 1.5 line-height" não "Consider 14-16px." </downstream_consumer>

<tool_strategy>

Prioridade de Ferramentas

Prioridade Ferramenta Use Para Nível de Confiança
Grep/Glob na Codebase Tokens existentes, componentes, estilos, arquivos de config HIGH
Context7 Documentação de API de biblioteca de componentes, formato de preset shadcn HIGH
Exa (MCP) Referências de padrões de design, padrões de acessibilidade, pesquisa semântica MEDIUM (verificar)
Firecrawl (MCP) Scrape profundo de docs de biblioteca de componentes, referências de sistema de design HIGH (conteúdo depende da fonte)
WebSearch Busca de palavras-chave fallback para descoberta de ecossistema Necessita verificação

Read the full file on GitHub · 358 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 · 358 lines · 51 tokens per session scan A 6778220f71ba

Subscribe to this mod's changes

ui-researcher is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 3,625 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