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/rm2thaddeus/Pixel_DetectiveWrote 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/rm2thaddeus/pixel_detective/ux-workflow-patterns)<a href="https://agentmods.dev/rules/rm2thaddeus/pixel_detective/ux-workflow-patterns"><img src="https://agentmods.dev/badge/rules/rm2thaddeus/pixel_detective/ux-workflow-patterns/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/rm2thaddeus/pixel_detective/ux-workflow-patterns"><img src="https://agentmods.dev/badge/rules/rm2thaddeus/pixel_detective/ux-workflow-patterns.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 | $0.00000 | $0.04616 |
| Opus 5.5 | $0.00000 | $0.01846 |
| Sonnet 5.5 | $0.00000 | $0.00923 |
| Haiku 4.5 | $0.00000 | $0.00462 |
Grade A, and why
ux-workflow-patterns 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 1mo 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 — 678 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Workflow Patterns
🎯 USER EXPERIENCE PATTERNS (From Sprint 10 UX Lessons)
Based on critical UX discoveries, user feedback, and workflow improvements implemented during Sprint 10.
🚨 CRITICAL UX FLAW DISCOVERED & FIXED
The "Add Images" Workflow Disaster
// ❌ CRITICAL UX FLAW: Browser security violation
function AddImagesModal() {
const [directoryPath, setDirectoryPath] = useState('')
return (
<Modal>
<ModalBody>
<Text>Enter the directory path containing your images:</Text>
<Input
placeholder="C:\Users\username\Pictures\..."
value={directoryPath}
onChange={(e) => setDirectoryPath(e.target.value)}
/>
<Button onClick={() => processDirectory(directoryPath)}>
Process Directory
</Button>
</ModalBody>
</Modal>
)
}
Why this was a disaster:
- Security Violation: Browsers cannot access local file system paths
- 100% Failure Rate: This workflow would fail for every user
- Confusing UX: Users don't understand why it doesn't work
- Backend Mismatch: Backend expects server paths, not client paths
✅ SOLUTION: Proper File Upload Workflow
// ✅ CORRECT: Browser-compatible file upload
function AddImagesModal() {
const [selectedFiles, setSelectedFiles] = useState<FileList | null>(null)
const fileInputRef = useRef<HTMLInputElement>(null)
const handleFolderSelect = (event: React.ChangeEvent<HTMLInputElement>) => {
if (event.target.files) {
setSelectedFiles(event.target.files)
}
}
const handleUpload = async () => {
if (!selectedFiles) return
const formData = new FormData()
Array.from(selectedFiles).forEach(file => {
formData.append('files', file)
})
const response = await api.post('/api/v1/ingest/upload', formData, {
headers: { 'Content-Type': 'multipart/form-data' }
})
// Navigate to job tracking
router.push(`/logs/${response.data.job_id}`)
}
return (
<Modal>
<ModalBody>
<VStack spacing={4}>
<Text>Select a folder containing your images:</Text>
<Box
p={6}
border="2px dashed"
borderColor="gray.300"
borderRadius="md"
cursor="pointer"
onClick={() => fileInputRef.current?.click()}
_hover={{ bg: 'gray.50' }}
>
<VStack>
<Icon as={FiUploadCloud} boxSize={12} color="gray.500" />
<Text fontWeight="medium">Click to select a folder</Text>
<Text fontSize="sm" color="gray.500">
Files will be uploaded to the server for processing
</Text>
</VStack>
</Box>
<Input
type="file"
ref={fileInputRef}
onChange={handleFolderSelect}
style={{ display: 'none' }}
{...{ webkitdirectory: 'true', mozdirectory: 'true' }}
/>
{selectedFiles && (
<Alert status="success">
<AlertIcon />
<Text>{selectedFiles.length} files selected</Text>
</Alert>
)}
</VStack>
</ModalBody>
<ModalFooter>
<Button
colorScheme="blue"
onClick={handleUpload}
isDisabled={!selectedFiles}
>
Upload and Process
</Button>
</ModalFooter>
</Modal>
)
}
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.
- 1mo ago First seen · 678 lines · 0 tokens per session scan A 9ca576383514
ux-workflow-patterns is a cursor rule published in the GitHub repository rm2thaddeus/Pixel_Detective (21 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,616 tokens. 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 cursor rules, from other repositories
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…
prototype-previewer
Build interactive prototype reviewers with synced review notes and Figma capture pages.
figma-performance
Handling large documents efficiently in the Plugin API.
ant-design
A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.