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 skills add parhamb/design-skills --skill ux-utilitygit clone --depth 1 https://github.com/parhamb/design-skillsWrote 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/skills/parhamb/design-skills/ux-utility)<a href="https://agentmods.dev/skills/parhamb/design-skills/ux-utility"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-utility/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/skills/parhamb/design-skills/ux-utility"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-utility.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 | $0.00045 | $0.00720 |
| Opus 5 | $0.00023 | $0.00360 |
| Sonnet 5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
ux-utility 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utility Features
Utility features are what keep power users loyal. They reduce repetitive work and let users shape the app around their own habits and preferences.
Checklist
| Item | Guidance |
|---|---|
| Favorites and bookmarks | Save icon visible on content cards. Saved list is easy to find from the main navigation. |
| Share feature | Uses the native share sheet. Never a custom share UI. Includes a shareable URL. |
| In-app browser | External links may open in an in-app browser, but always with a visible "Open in browser" action. Respect the user's default browser for external destinations — never trap users in the in-app view. |
| Personalization | User can choose interests, layout, or notification frequency, starting at onboarding. |
| Clipboard integration | Copied URLs are detected on app launch and offered to the user as a quick action — using privacy-safe detection APIs (see pattern below). |
Patterns
Share sheet: Pre-populate the share text with a useful message, not a bare URL. Include UTM parameters for tracking. Support sharing images, text, and URLs through the same entry point.
Favorites architecture: Save to local storage first, then sync to the server. Never fail silently. Show a fill animation on save as confirmation. Empty state for the saved list should invite the first save action. Optionally allow organizing saved items into folders for power users.
Personalization strategies: Start with an explicit onboarding step where users select their interests. Refine over time with behavioral signals (views, time spent, taps). Always show a "Why am I seeing this?" explanation so recommendations feel trustworthy rather than arbitrary.
Clipboard detection: Show a subtle, non-intrusive banner when a link is detected on the clipboard: "We noticed a link — open it in [App]?" Dismiss automatically after a few seconds if the user ignores it. Never open the link automatically.
Platform constraints: on iOS 16+, reading the clipboard directly triggers a
system paste permission prompt — use UIPasteboard.detectPatterns to check
whether a URL is present without reading the contents and without triggering
the prompt. Android 12+ shows a system toast whenever an app reads the
clipboard, so read it only at the moment of use, never speculatively.
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 · 74 lines · 45 tokens per session scan A c2ccf5302fbb
ux-utility is a skill published in the GitHub repository parhamb/design-skills (21 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 720 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 skills, from other repositories
Art
Static visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Nano Banana Pro (default), Nano Banana, and Flux. USE WHEN art, illustration, diagram, flowchart, infographic, header image, blog social thumbnail, visualize, generate image, mermaid, architecture…
Webdesign
Design and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through…
ApertureOscillation
3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis — to surface design tensions, scope recommendations, and coherence assessments invisible at any single zoom level. USE WHEN aperture oscillation, oscillate scope, zoom in and out, tactical vs…
Tldraw
Read, create, and edit tldraw .tldr canvas files deterministically — sketch hand-drawn-register diagrams (boxes, arrows, sticky notes, frames, text) directly into a canvas file the user opens in any tldraw surface, and read a rough canvas back as structured data to organize it. USE WHEN tldraw, .tldr file, whiteboard…
learn
Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask in any language to research, study, deep-dive, compile sources, synthesize unfamiliar material, or turn a source bundle into a coherent reference. Not for quick lookups…
dashboard
Update the agent's Control Center. Use when the user says "update my Control Center", "update my dashboard", "redesign my home", or "/dashboard".