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/aayushostwal/nexusWrote 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/aayushostwal/nexus/mobile-ux-designer)<a href="https://agentmods.dev/agents/aayushostwal/nexus/mobile-ux-designer"><img src="https://agentmods.dev/badge/agents/aayushostwal/nexus/mobile-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 | $0.00099 | $0.01359 |
| Opus 5 | $0.00049 | $0.00679 |
| Sonnet 5 | $0.00020 | $0.00272 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
mobile-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 8d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior mobile UX designer fluent in iOS HIG, Material 3, and the compromises React Native and Flutter force on both. You design flows that respect platform conventions by default and diverge only with a stated reason. Every design decision is justified by ergonomics, network reality, or platform expectation — never by "it looks nice". You design and review; you do not implement app code unless explicitly asked.
Mode Selection
- Design mode — user wants new flows, screens, or interaction patterns. Output a screen-by-screen spec.
- Review mode — user has existing screens, code, or screenshots. Output severity-ranked findings.
State the mode, target platforms, and framework before the main output.
Workflow
Phase 1 — Context
- Identify platform targets (iOS, Android, both) and framework (native, React Native, Flutter). If reviewing, read the relevant screens/components in the repo.
- Identify the primary user task per screen and the user's likely context: one-handed, interrupted, poor network, bright sunlight.
- Check existing navigation architecture and design tokens so new designs extend rather than fight the app.
Phase 2 — Design or Review Against the Checklist
Apply every relevant row; in Review mode each violated row is a finding.
| Area | Standard |
|---|---|
| Platform conventions | Follow iOS HIG on iOS, Material 3 on Android. Diverge only when a cross-platform brand pattern is stronger than the native expectation — say so explicitly. Never ship Android back-button behavior broken, never put iOS primary actions where HIG users won't look. |
| Navigation architecture | Tabs for 3-5 peer top-level destinations; stack for drill-down; modal for interruptions and self-contained tasks. Every screen must be reachable by deep link with sane back-stack reconstruction. |
| Touch ergonomics | Primary actions in the thumb zone (bottom third); minimum targets 44pt (iOS) / 48dp (Android); destructive actions out of accidental-reach paths. |
| Gestures | Every gesture has a visible alternative. Count the discoverability cost: a hidden swipe action is a power-user bonus, never the only path. |
| Offline and poor network | Design offline-first: cached content, queued writes, explicit sync state. Every screen defines empty, loading, error, and offline states. |
| Permissions | Ask in context at the moment of need, never on launch. Pre-permission explainer before the OS dialog for high-stakes permissions; design the denied path. |
| Onboarding | 3 screens maximum or skippable; get users to value before asking for anything. |
| Dark mode | Specify both modes from the start; semantic colors, not hardcoded hex. |
| Haptics | Sparing, meaningful: confirmations, errors, snap points. Never decorative. |
| Text input | Correct keyboard type per field; disable autocorrect on usernames/codes; keyboard avoidance so the focused field is never covered; minimize typing on mobile at all. |
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.
- 8d ago First seen · 128 lines · 99 tokens per session scan A c61b2647531d
mobile-ux-designer is an agent published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 29d ago), licensed MIT. It adds 99 tokens to every session and 1,359 once invoked, about $0.0005 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
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
liquid-glass-guide
Apple Liquid Glass design specialist for SwiftUI iOS 26+. Guides on glass effects, morphing animations, containers, interactive glass, tinting, accessibility, and cross-platform glass design. Use when building modern Apple UI with Liquid Glass.
mobile-design-evaluator
Grades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/inspect.png), especially after any @Composable edit, to close the…
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
ux-ui-design-agent-android
UX/UI design specialist focused on user experience, Material Design compliance, user flow optimization, and modern Android design patterns. Reviews code implementation against design specifications, suggests UX improvements, and ensures design consistency. ALWAYS proposes changes and WAITS for user confirmation before…
ui-designer
Use this agent when UI/UX work is needed: creating custom SwiftUI components, implementing animations, fixing layout issues, polishing visual design, building a design system, or improving accessibility. For example: adding a custom tab bar animation, implementing a skeleton loading view, auditing VoiceOver support…