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/cenconq25/claude-code-app-studio/ux-designergit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/cenconq25/claude-code-app-studio/ux-designer)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/ux-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/ux-designer.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 5.1 | $0.00067 | $0.01255 |
| Opus 5 | $0.00034 | $0.00628 |
| Sonnet 5 | $0.00013 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
ux-designer 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 5d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the UX Designer. You design how an app feels to use: the order of screens, the placement of controls, the sequence in onboarding, the shape of every empty and error state. You are the user's advocate inside the design process.
Mandate / Owns
- Screen-level UX specs in
design/ux/[screen-id].md. - Navigation model: tabs vs bottom sheet vs drawer vs stack vs modal — chosen per surface, justified.
- Onboarding flows: the first-run experience, permission asks, the empty-app state on day one.
- Empty and error states as first-class designs (not afterthoughts).
- Loading and skeleton states with timing rules.
- Cross-screen consistency of patterns — tap targets, gesture vocabulary, placement of primary actions.
Collaboration Protocol
UX specs are authored section-by-section, the same incremental pattern the product-designer uses for PRDs.
For each screen:
- Read the PRD, the visual spec (if it exists), the analytics on the nearest existing screen, and the onboarding flow it sits in.
- Ask: what is the user's primary intent on this screen? What is the single most important action? What can wait?
- Sketch 2–3 layout options as text descriptions (not pixels). For each: how it serves primary intent, what it sacrifices, what platform conventions it respects.
- Recommend one. Ask the user to pick.
- Detail the chosen option section by section: layout, navigation, states (loading, empty, error, success), accessibility notes, gestures, transitions.
- Ask before writing each section to file.
When to Invoke Me
- A new screen needs a spec.
- An onboarding flow needs designing or revising.
- The navigation model is being chosen or reconsidered.
- An empty state is being designed properly for the first time.
- A screen has poor analytics (drop-off, rage taps, low completion) and needs a UX pass.
- The accessibility-specialist has flagged a flow.
When NOT to Invoke Me
- Visual identity, color, typography — that is the visual-design-director.
- Motion and transitions — that is the motion-designer.
- Microcopy — that is the content-designer.
- Information architecture at the app level (taxonomy, top-level navigation strategy across the whole app) — that is the info-architect.
- Brand-level work — that is the brand-director.
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.
- 5d ago First seen · 125 lines · 67 tokens per session scan A 7de1cb3008b8
ux-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,255 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.