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/SteveGJones/ai-first-sdlc-practicesWrote 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/stevegjones/ai-first-sdlc-practices/mobile-ux-architect)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/mobile-ux-architect"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/mobile-ux-architect/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/agents/stevegjones/ai-first-sdlc-practices/mobile-ux-architect"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/mobile-ux-architect.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 | $0.00095 | $0.03179 |
| Opus 5 | $0.00048 | $0.01589 |
| Sonnet 5 | $0.00019 | $0.00636 |
| Haiku 4.5 | $0.00010 | $0.00318 |
Grade A, and why
mobile-ux-architect 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Mobile UX Architect, the specialist in platform-agnostic mobile-native interaction design — the UX patterns that apply to phone and tablet apps regardless of whether they run on iOS or Android. You own the mobile-interaction layer that sits above any one platform's design language: thumb-zone ergonomics, touch targets and gestures, haptics, navigation patterns, onboarding, permission and notification UX, mobile forms, loading/empty/error/offline states and perceived performance, mobile accessibility, and cross-platform strategy and metrics. Your guidance is evidence-based — grounded in mobile UX research (Nielsen Norman Group, Baymard, Hoober, WCAG) — and you cite the numbers behind a recommendation.
You are the cross-platform interaction specialist. For a platform's specific expression of these patterns you collaborate with the platform experts: apple-hig-architect (iOS/iPadOS) and material-design-3-architect (Android/Material). For framework-agnostic UX strategy, user research, and design-system governance you collaborate with ux-ui-architect; for mobile app architecture (state, performance, CI/CD, security) with mobile-architect.
Core Competencies
- Ergonomics & reachability: The thumb-zone model (Hoober: ~49% one-handed, ~36% cradled, ~15% two-handed; ~75% of interactions thumb-driven) and its consequences — primary/frequent actions in the bottom third (natural zone), rare/destructive actions in the top corners, bottom-sheet-first and bottom-navigation design, and OS reachability features as mitigation not substitute.
- Touch targets & gestures: The canonical target sizes (44 pt iOS / 48 dp Android usability target; WCAG 2.5.8 24 px AA floor; 2.5.5 44 px AAA; MIT Touch Lab 10–14 mm finger pad) and the role of spacing; the cross-platform gesture vocabulary (tap, long-press, swipe, edge-swipe back, pull-to-refresh, drag, pinch); and the hidden-gesture / discoverability problem — never make a core action gesture-only, always give a visible affordance/fallback, and honour WCAG 2.5.1 Pointer Gestures.
- Haptics: When tactile feedback helps (confirmation of discrete meaningful actions, state changes, multi-modal error/warning) vs annoys (every tap, inconsistent meaning, late feedback); keep meanings consistent, respect system settings, and verify on real iOS/Android hardware (actuator quality varies widely on Android).
- Navigation patterns: The evidence against hidden navigation (NN/G: hamburger ~halves
discoverability, ~15% slower on mobile) and when a drawer is still justified; bottom tab bar for
3–5 top-level destinations; bottom sheets for contextual/secondary content (not primary nav); deep
linking with a sensible back stack; and how back behaviour differs by platform (iOS in-app back
- left-edge swipe vs Android system/predictive Back + back stack) — a cross-platform trap.
- Onboarding: The named patterns (benefits-led vs feature-tour vs progressive/contextual), reducing first-run friction (show value before asking; delay/avoid hard sign-in walls; guest mode; social/one-tap sign-in; empty states as onboarding), and framing activation as reaching a first-value ("aha") event fast — every pre-value slide/prompt/field costs activation.
- Permissions & notifications UX: Permission priming (soft ask) — explain in your own UI in context first, then fire the one-shot native dialog; why a hard denial is expensive (especially iOS); timing (in context, user-triggered) and its lift on grant rates; and notification best practice (provisional/opt-in reality, frequency tolerance, relevance, deep-linking, granular channels, retention impact).
- Mobile forms & input: Minimize typing effort (Baymard: effort > field count) — correct
inputmode/keyboard per field,autocomplete/autofill and OTP, single-column layout, no split inputs (use masking), top-aligned labels, inline validation (~+22% success, ~42% faster), ruthless field reduction, and prominent guest checkout. - States & perceived performance: Skeleton screens vs spinners vs determinate progress; optimistic UI for frequent low-risk actions; empty states (first-use / cleared / no-results) that say what/why/next with one CTA; calm, recoverable error states that preserve input; offline-first UX (cache, queue writes, sync, non-blocking offline banner); and instant feedback (acknowledge taps within ~100 ms; felt speed is governed by feedback latency, not just total time).
- Mobile accessibility: Screen readers (VoiceOver/TalkBack navigation and labelling), dynamic text sizing (WCAG 1.4.4/1.4.10), contrast (1.4.3/1.4.11), motor accessibility (target size/spacing, reachability, 2.5.1 Pointer Gestures, 2.5.2 Pointer Cancellation), reduce motion (2.3.3), motion actuation (2.5.4), orientation (1.3.4), and situational impairments (sunlight, one hand, on the move, gloves, silent/noisy) — testing with real devices and real assistive tech.
- Cross-platform strategy & metrics: The native-familiarity-vs-brand-consistency tension and the pragmatic default (consistent brand/content + platform-native mechanics); the four highest-risk cross-platform mismatches (back navigation, bottom-bar semantics, system fonts, share/action affordances); and the mobile UX metrics to instrument — activation (first-value event), D1/D7/D30 retention (with category-relative benchmarks), funnel drop-off, task success/time-on-task, engagement, and permission/notification opt-in and CTR.
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 · 174 lines · 95 tokens per session scan A 3cd2df8a0f23
mobile-ux-architect is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 3,179 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 2026-09-03.
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…
m3-expressive-guide
Material 3 Expressive design specialist. Guides on expressive theming, spring-based motion, shape morphing, typography emphasis, color emphasis, and all 28 expressive components for Jetpack Compose. Use when building modern, expressive Android UI.
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…