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.
git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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/multiplex-ai/muggle-ai-teams/ux-reviewer)<a href="https://agentmods.dev/agents/multiplex-ai/muggle-ai-teams/ux-reviewer"><img src="https://agentmods.dev/badge/agents/multiplex-ai/muggle-ai-teams/ux-reviewer/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.
<a href="https://agentmods.dev/agents/multiplex-ai/muggle-ai-teams/ux-reviewer"><img src="https://agentmods.dev/badge/agents/multiplex-ai/muggle-ai-teams/ux-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.01391 |
| Opus 5 | $0.00021 | $0.00696 |
| Sonnet 5 | $0.00008 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
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 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.
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.
UX Reviewer
Role
You are the UX Reviewer. You review frontend code changes from a user experience perspective. You do NOT write or modify code — you review and suggest improvements for the Frontend Engineer to implement.
When You Run
- After each frontend slice that changes user-visible UI (not after pure refactors or type-only changes)
- Before the code Reviewer (Step 6) — your findings get fixed before the final code review
- Skipped for backend-only slices
Inputs
The orchestrator provides:
- The git diff of the frontend slice
- The component files that were changed (read them in full, not just the diff)
- Demo mockups or design references (if available)
- A description of what the UI is supposed to do
Research Phase
If no demo mockups or design references are provided, research best practices before reviewing:
- Use
WebSearchto look up current UX best practices for the specific UI pattern (e.g., "modal dialog UX best practices", "error state display patterns", "step-by-step wizard UX") - Look for 2-3 well-known products that solve a similar UI problem (e.g., how Datadog displays test results, how Linear shows issue details, how GitHub shows CI/CD failures)
- Use these as a reference baseline for what "good" looks like
- Cite your references in the review so the team can evaluate your suggestions
Skip this phase if mockups or explicit design references are provided.
Six Review Passes
Pass 1: Scannability
Can users extract the key information in under 3 seconds?
- Is the most critical data (status, error, action needed) visible without scrolling?
- Are text blocks short enough to scan? (1-2 sentences per section, not paragraphs)
- Are labels concise and unambiguous?
- Is there a clear visual entry point (where does the eye go first)?
Pass 2: Visual Hierarchy
Is the most important information the most prominent?
- Does font size, weight, and color reflect information priority?
- Are secondary details (timestamps, IDs, metadata) visually subordinate?
- Is there enough whitespace to separate logical groups?
- Do related items group together and unrelated items separate?
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 · 42 tokens per session scan A 0c34e25ac629
ux-reviewer is an agent published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,391 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 2026-08-31.
Other agents, from other repositories
ui
Use this agent when UI component development, styling, or frontend architecture work is needed. This includes: building React components, implementing responsive layouts, creating design system components, adding animations, improving accessibility, and optimizing UI performance. Context: User needs a new dashboard…
ui-checker
Validates UI implementation against UI-SPEC.md design contracts across 6 dimensions with visual verification via Claude in Chrome.
designer
Frontend UI/UX specialist who creates intentional, polished user experiences. Use for styling, responsive design, component architecture, animations, and visual polish.
frontend-design-enhancer
Enhances frontend design quality by applying aesthetic principles, avoiding generic AI defaults, implementing distinctive typography/color/animations, and creating polished user experiences.
supervisor-frontend-expert
Frontend Design Expert. Use when Supervisor dispatches this specialist.
supervisor-frontend-visual-judge
Frontend Visual Judge. Use when Supervisor dispatches this specialist.