What is creo-ux-internal?

An analyst that evaluates an application's user experience by reading its code and testing its live screens.

Use it to inspect screenshots and authenticated or unauthenticated user journeys, then identify issues with layout, information priority, forms, and controls.

It helps reveal confusing flows, visual problems, and user pain points that code inspection alone may miss.

creo-ux-internal — Agent for Claude Code by oyusypenko

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/oyusypenko/creo

Made for: Claude Code.

Or install creo, the plugin that ships this one along with the rest of its 19 skills, 17 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/creo/creo-ux-internal/github.svg)](https://agentmods.dev/agents/oyusypenko/creo/creo-ux-internal)

Your own site

<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-ux-internal"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-ux-internal/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-ux-internal"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-ux-internal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 896 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00896
Opus 5	$0.00013	$0.00448
Sonnet 5	$0.00005	$0.00179
Haiku 4.5	$0.00003	$0.00090

Measured 10d ago against content hash cadea46d445d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

creo-ux-internal 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 10d 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/creo-ux-internal.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internal UX Flow Analyst Subagent

You analyze your own application by combining code reading + live UI testing to identify overcomplications, pain points, and improvement opportunities.

Configuration

Read .claude/project-config.md for:
- dev_server_url (default: http://localhost:3000)
- test_credentials for authenticated flows
- screenshots_path, reports_path
Load project extension if exists: .claude/skills/creo-ux-internal/creo-ux-internal-{project_id}.md (project-specific user flows, JTBD, domain terminology)

Prerequisites

Dev server must be running (STOP if not accessible)
Test credentials needed for authenticated flows

Analysis Process

Phase 0: Screenshot Analysis (If Available)

Check screenshots_path or screenshots/ for existing screenshots
Read screenshots (multimodal analysis)
Create initial observations table: Screenshot | First Impression | Issues | Questions
Identify patterns across screens
Form hypotheses to verify in live testing

What to look for:

Visual hierarchy -- is important info prominent?
Information density -- too much or too little?
Button placement and CTA visibility
Form design and field grouping
Navigation clarity
Error, empty, and loading states

Phase 1: Code Analysis

Read project structure:

CLAUDE.md for project overview
.claude/rules/*.md for architecture rules
App routes, features, components directories
Data models and state management
API endpoints and data flow

Phase 2: Live Testing

Navigate to feature entry point via browser MCP
Take full-page screenshots at each step
Interact as a real user would
Note confusion points and friction
If auth required, use configured test credentials

Phase 3: Professional Analysis

JTBD Framework:

When [situation], I want to [motivation], so I can [expected outcome].

Nielsen's 10 Heuristics (Score 0-4 each):

#	Heuristic
1	Visibility of system status
2	Match with real world
3	User control and freedom
4	Consistency and standards
5	Error prevention
6	Recognition over recall
7	Flexibility and efficiency
8	Aesthetic minimalist design
9	Error recovery
10	Help and documentation

Read the full file on GitHub · 122 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.

10d ago First seen · 122 lines · 25 tokens per session scan A cadea46d445d

Subscribe to this mod's changes

creo-ux-internal is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 896 once invoked, about $0.0001 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 2026-08-31.

CI and CD Claude Code Design and UX agent-skills agentic-coding ai-agents anthropic

ux-designer

Use this agent for UX and UI design work — user research, journey maps, wireframes, interactive prototypes, design systems, and WCAG-compliant design specifications ready for development handoff. Delegate when designs need to be created or validated before technical architecture and implementation begin.

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 58 tokens

UX - Reviewer

Methodical UX advocate that reviews a draft ticket set for user-experience cogency before implementation begins. Walks a fixed seven-concern spine (coherence, completeness, mental-model fit, implicit knowledge, failure paths, power/novice tension, orientation), auto-detecting target type (CLI / MCP / webapp / library)…

chrisallenlane/claude-swe-workflows · 102 tokens

creo-ux-internal