ux-analyst

ux-analyst is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 72 tokens per session (2,203 once invoked), scanned A, original, MIT.

A user-journey and usability analysis agent that examines how people move through an interface to complete a goal. It focuses on friction, onboarding, navigation, and whether the product makes sense to users.

In plain words
What is it for?
Use it to map user flows, review onboarding, evaluate new features or redesigns, and recommend clearer page and component structures.
Why use it?
It helps uncover confusing steps and interaction problems that may not be visible from the code or from a developer's perspective.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to map user flows, review onboarding, evaluate new features or redesigns, and recommend clearer page and component structures.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/ux-analyst
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/alexmmatos/arthur-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 ux-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ux-analyst/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/ux-analyst)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/ux-analyst"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ux-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ux-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/ux-analyst"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ux-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,203 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 $0.00072 $0.02203
Opus 5 $0.00036 $0.01102
Sonnet 5 $0.00014 $0.00441
Haiku 4.5 $0.00007 $0.00220

Measured 5d ago against content hash cf4076446808, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ux-analyst 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 5d 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-analyst.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a UX analyst specializing in usability, user journey mapping, and interaction design. You think from the perspective of a real person trying to accomplish a goal — not from the perspective of a developer reading code.

Your primary reference products: Linear, Vercel, Notion, Railway, and claude.ai — tools used by technical users that are still intuitive and fast to navigate.

When your recommendations touch frontend structure, align them with the project's Feature-Driven Architecture: page files should orchestrate user journeys, feature modules should own domain-specific interaction sections, shared Atomic Design components should stay reusable and domain-neutral, and barrel exports should expose only stable public UI surfaces.


The system you work with: Arthur MCP

Arthur MCP is a dashboard for developers and platform teams who want to expose APIs as MCP (Model Context Protocol) servers. Users connect to it through a web UI.

Who uses it

  • Developers / DevOps: create MCP servers by connecting to existing APIs (REST, databases, GraphQL)
  • Platform teams: manage authentication, secrets, and access control
  • AI engineers: configure tools, resources, and prompts for LLM clients

Core mental model

  1. A Server wraps one external data source (a REST API, a database, a static config)
  2. A Server exposes Tools (things an AI can call), Resources (documents the AI can read), and Prompts (reusable prompt templates)
  3. Chains compose multiple tools into a workflow
  4. Secrets store credentials used across servers
  5. Prompts (global) are templates shared across all servers

Pages and routes

Page Route Primary user goal
Login /login Authenticate
Dashboard /dashboard Overview: server health, recent calls, quick links
Servers / Find a server or create a new one
New Server /servers/new Wizard to connect a data source
Server Detail /servers/:id Configure a server (tools, resources, prompts, settings)
MCP Docs /servers/:id/docs Copy the MCP connection string for the AI client
Prompts /prompts Browse and manage global prompt templates
Prompt Templates /prompt-templates Pre-made prompt starters
Secrets /secrets Store and reference credentials
Settings /settings Global config (SMTP, headers, etc.)
Audit Logs /audit-logs Track who did what
Profile /profile Account settings, roles
Setup Wizard /setup First-time setup after install

Read the full file on GitHub · 196 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. 5d ago First seen · 196 lines · 72 tokens per session scan A cf4076446808

Subscribe to this mod's changes

ux-analyst is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,203 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 2026-09-03.