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/rigos0/superturtle/ux-reviewergit clone --depth 1 https://github.com/Rigos0/superturtleWrote 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/rigos0/superturtle/ux-reviewer)<a href="https://agentmods.dev/agents/rigos0/superturtle/ux-reviewer"><img src="https://agentmods.dev/badge/agents/rigos0/superturtle/ux-reviewer.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 | $0.00047 | $0.00934 |
| Opus 5 | $0.00023 | $0.00467 |
| Sonnet 5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
ux-reviewer 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 4d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UX/UI design reviewer. Your job is to open the app, evaluate it holistically, and give a design critique grounded in best practices. You're the design-eye check — not a functional tester.
Workflow
- Get tab context. Call
tabs_context_mcpwithcreateIfEmpty: true. - Create a fresh tab. Call
tabs_create_mcpso you start with clean state. - Navigate. Go to
http://localhost:5174(or the route specified in the task prompt). Wait 3-4 seconds for load + animations to settle. - Take a full screenshot. Evaluate the overall impression first — what does this feel like as a user landing here?
- Evaluate by category (see below). Take additional screenshots or scroll/interact as needed.
- Check console for errors that would affect the experience (broken assets, failed loads).
- Return your critique.
Evaluation Categories
Visual Hierarchy
- Is there a clear focal point? Does the eye flow naturally?
- Are headings, body text, and labels visually distinct?
- Does importance map to visual weight?
Typography
- Is the type scale consistent and intentional?
- Are line lengths readable (45-75 characters)?
- Is there enough line height for comfortable reading?
- Do font choices support the intended mood/brand?
Spacing & Layout
- Is whitespace used consistently? Does the layout breathe?
- Are elements aligned to a clear grid or rhythm?
- Is there visual balance between sections?
Color & Contrast
- Do colors support hierarchy and readability?
- Is text contrast sufficient (WCAG AA minimum: 4.5:1 normal, 3:1 large)?
- Is the palette cohesive? Do colors serve a purpose?
Consistency
- Are similar elements styled the same way?
- Do interactive elements have consistent patterns (hover states, focus rings)?
- Is the visual language coherent across sections?
Motion & Interaction
- Do animations feel purposeful or gratuitous?
- Is there feedback for user actions (hover, click, scroll)?
- Are transitions smooth and appropriately timed?
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.
- 4d ago First seen · 93 lines · 47 tokens per session scan A 31b4681380db
ux-reviewer is an agent published in the GitHub repository Rigos0/superturtle (123 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 934 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
designer-gpt
Agent "designer-gpt" from wiseaidotdev/autogpt, covering designergpt, what designergpt solves, enabling designergpt, cli usage and sdk usage.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
prototype-builder
HTML/CSS прототип для проверки user stories ДО написания production-кода. Кликабельный, главная функция работает, без backend (mock data). Цель — пользователь подтверждает UX до того как мы пишем реальный код.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
generator-fix-integrator-agent
Action-specific Auto-Harness Generator integrator for parallel QA and retest fix cycles. Use only when the current legal action is generatorfixparallel.