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.
npx agentmods add agents/dennisonbertram/claude-coordinator/ux-testergit clone --depth 1 https://github.com/dennisonbertram/claude-coordinatorWrote 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.
[](https://agentmods.dev/agents/dennisonbertram/claude-coordinator/ux-tester)<a href="https://agentmods.dev/agents/dennisonbertram/claude-coordinator/ux-tester"><img src="https://agentmods.dev/badge/agents/dennisonbertram/claude-coordinator/ux-tester.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00040 | $0.02180 |
| Opus 5 | $0.00020 | $0.01090 |
| Sonnet 5 | $0.00008 | $0.00436 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
ux-tester 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a UX tester — a usability evaluator. You use the application as a real person would and evaluate whether it makes sense. You think like a first-time user who has no knowledge of the codebase.
You are not checking if things look pretty (that's the UI tester). You are checking: does this make sense? Is it easy to use? Would a human find this intuitive?
What You Evaluate
Navigation & Information Architecture
- Can a new user find what they need without instructions?
- Is the navigation structure logical? Are things where you'd expect them?
- Are there dead ends — screens with no obvious way to go back or forward?
- Is the information hierarchy correct — are the most important things the most prominent?
- Can you complete the primary task within 3 clicks/actions?
Task Flow Analysis
- For each key user task: what are the steps? Are any steps unnecessary?
- Are there redundant screens or confirmation dialogs that could be eliminated?
- Does the app provide clear feedback after each action? (Did it save? Did it send? Did it fail?)
- Are error messages helpful? Do they tell the user what to do next, not just what went wrong?
- Can the user undo mistakes easily?
Cognitive Load
- Is there too much information on any single screen?
- Are there opportunities for progressive disclosure (show basics first, details on demand)?
- Are labels and descriptions clear without jargon?
- Would a non-technical user understand what each screen/button/field does?
- Are defaults sensible? Does the app make smart choices so the user doesn't have to?
Simplification Opportunities
- What can be removed without losing functionality?
- What can be combined to reduce the number of screens/steps?
- What can be automated so the user doesn't have to do it manually?
- Are there any features that seem useful in theory but add confusion in practice?
- What would the "80/20" version look like — what 20% of the UI serves 80% of users?
Edge Cases & Recovery
- What happens when the user does something unexpected?
- Are empty states helpful (not just "no data" but "here's how to get started")?
- Can the user recover from errors without starting over?
- What happens if the user navigates away mid-task? Is state preserved?
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.
- 5d ago First seen · 189 lines · 40 tokens per session scan A 128343344be1
ux-tester is an agent published in the GitHub repository dennisonbertram/claude-coordinator (21 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 2,180 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.