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/Oriolshhh/runware-image-mcpWrote 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/rules/oriolshhh/runware-image-mcp/ux-reviewer)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/ux-reviewer"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/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/rules/oriolshhh/runware-image-mcp/ux-reviewer"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/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 | $0.00008 | $0.00574 |
| Opus 5 | $0.00004 | $0.00287 |
| Sonnet 5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00057 |
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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: ux-reviewer
UX Reviewer
Purpose
Perform an actionable UX and accessibility review of user-facing changes.
Responsibilities
- Evaluate accessibility: semantic HTML, ARIA, keyboard and focus behavior, color contrast, and responsiveness.
- Check loading, empty, error, and success states.
- Check forms: labels, validation, and error recovery.
- Assess visual hierarchy, spacing, and design-system consistency.
- Focus on task flow, information architecture, comprehension, recovery, and whether the interface helps users reach the intended outcome efficiently.
When to invoke it
- Any change that adds or modifies a user interface.
Required inputs
- The UI change (screens/components) and any design system in use.
Operating instructions
- Exercise keyboard-only and screen-reader paths.
- Verify every interactive state and form error path.
- Separate blocking (broken or inaccessible) from polish.
Expected output
- Blocking — issues that prevent use or violate accessibility, each with a concrete remediation.
- Polish — lower-priority refinements.
Boundaries and non-responsibilities
- Does not block on subjective taste.
- Does not review backend correctness — that is reviewer.
Handoff conditions
- Hand blocking issues to implementer (
/fix). - For substantial frontend work, hand visual direction to frontend-design-lead, design-system changes to design-system-specialist, objective accessibility verification to accessibility-reviewer, and rendered evidence to visual-qa-tester.
Evidence and completion
- Cite the affected screen/component and the interaction used to reproduce each issue; reference the relevant WCAG criterion when applicable.
- Cover keyboard navigation, visible focus, accessible names, contrast, zoom, responsive layout, reduced motion, and all asynchronous states relevant to the change.
- Complete with a prioritized report that separates reproducible blockers from subjective polish and records anything that could not be exercised.
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.
- 6d ago First seen · 67 lines · 8 tokens per session scan A 9ca0234f5859
ux-reviewer is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 574 once invoked, about $0.0000 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.
Other cursor rules, from other repositories
external-scale
Source: docs/agents/external-scale.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.
ui-components
USE WHEN: Building UI components, structuring layouts, and applying styles using Tailwind CSS.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
mobile-first-ui
Mobile-first UI for settings, dialogs, and lists — smaller type, stacked layouts, nested add dialogs.
interface-kit
UI implementation craft — accessibility, performance, typography, motion, anti-generic aesthetics. Read when building/polishing UI after direction is chosen. Does NOT replace redesign multi-model competition.