agentmods.dev

mobile-architect

mobile-architect is a skill for Claude Code, Codex from m3taz-ahmed/ai-globals. It costs 50 tokens per session (2,464 once invoked), scanned A, original, MIT.

A guide for designing production cross-platform mobile apps with Flutter or React Native. It covers app structure, data storage, networking, testing, delivery pipelines, security, and monitoring.

In plain words
What is it for?
Use it to plan or bootstrap mobile apps, including offline support, state management, backend communication, automated delivery, testing, security, and observability.
Why use it?
It helps teams make consistent technical decisions across the two major cross-platform mobile ecosystems instead of solving architecture questions piecemeal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

not rated 5repo yesterday A scan 50 tokens original MIT

Good fit Use it to plan or bootstrap mobile apps, including offline support, state management, backend communication, automated delivery, testing, security, and observability.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/m3taz-ahmed/ai-globals/mobile-architect
View source ↗ m3taz-ahmed/ai-globals
Install

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.

Any agent
npx skills add m3taz-ahmed/ai-globals --skill mobile-architect
Clone the repo
git clone --depth 1 https://github.com/m3taz-ahmed/ai-globals

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mobile-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/mobile-architect/github.svg)](https://agentmods.dev/skills/m3taz-ahmed/ai-globals/mobile-architect)
Your own site
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/mobile-architect"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/mobile-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.

agentmods 80×15 button for mobile-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/mobile-architect"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/mobile-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02464
Opus 5 $0.00025 $0.01232
Sonnet 5 $0.00010 $0.00493
Haiku 4.5 $0.00005 $0.00246

Measured 9d ago against content hash c4ce94a216a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mobile-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 9d 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.

skills/mobile-architect/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[SKILL] mobile-architect [OBJ] Architect, bootstrap, and govern production-grade cross-platform mobile apps — Flutter and React Native/Expo — owning architecture, state, persistence, networking, testing, CI/CD, security, and observability across both ecosystems. [PERSONAS] MOBILE (primary), DEV (primary), ARCH (secondary), UX (secondary), QA (secondary). [SUB-SKILLS] flutter-architect (Flutter full-stack) -> flutter-design + flutter-developer; mobile-game-producer (games). Cross-ref frontend-frameworks-lord for RN.

[RULES]

  1. [CMD] Context7 IDs: Flutter /flutter/website; Dart /dart-lang/site-www; Riverpod /riverpod/riverpod; BLoC /felangel/bloc; Freezed /rrousselGit/freezed; Drift /simolus3/drift; Dio /cfug/dio; go_router /flutter/packages; Expo /expo/expo; React Native /facebook/react-native; TanStack Query /tanstack/query; Zustand /pmndrs/zustand; Zod /colinhacks/zod; Unistyles /jpudysz/react-native-unistyles; MMKV /mrousavy/react-native-mmkv; Sentry /getsentry/sentry-react-native; PostHog /PostHog/posthog-js; Maestro /mobile-dev-inc/maestro; Patrol /leanflutter/patrol; RevenueCat /RevenueCat/react-native-purchases.
  2. [REQ] [VER-01] Pin to lockfile exact versions. Flutter: read pubspec.lock -> load tech-stack/flutter.md (baseline Flutter 3.47 / Dart 3.13). RN: read package-lock.json -> load tech-stack/expo-sdk-56.md (baseline Expo SDK 56 / RN 0.86 / React 19.2). NEVER assume version.
  3. [REQ] Framework selection decision tree:
    • UI pixel-perfection across platforms + single codebase + non-hardware-dependent -> Flutter (Impeller, 60/120fps).
    • JS/TS team + fast MVP + easier hiring + web support -> React Native + Expo (New Architecture, JSI).
    • iOS-only + Apple Intelligence APIs + highest App Store approval -> Swift.
    • Android-only + deep hardware (BLE, camera2, Automotive) -> Kotlin + Jetpack Compose.
    • Share logic only (not UI) between iOS+Android -> Kotlin Multiplatform (KMP).
    • Web games/apps wrapped as native -> Capacitor.
  4. [REQ] Architecture (both platforms): Feature-first Clean Architecture. Layers: presentation -> domain -> data. Domain depends on nothing. Data depends on domain. Presentation depends on domain. No cross-feature imports. No business logic in UI. No backend SDK in domain/presentation (backend isolation).
  5. [REQ] State management:
    • Flutter: Riverpod 3.x with @riverpod code-gen (default) OR BLoC 9.x (enterprise/event-driven). NEVER Provider for new projects. NEVER setState for app-wide state.
    • RN: TanStack Query v5 (server state) + Zustand v5 (client state) + React Hook Form + Zod (forms). NEVER React Context for auth.
  6. [REQ] Offline-first: local DB as source of truth. Flutter: drift (SQL) + hive (KV). RN: WatermelonDB (SQL) + MMKV (KV). Sync: revision-based delta sync on reconnect; conflict resolution (LWW / field-level merge / server-wins). Background: workmanager (Flutter) / expo-background-fetch (RN). Connectivity: connectivity_plus (Flutter) / @react-native-community/netinfo (RN).
  7. [REQ] Navigation:
    • Flutter: go_router + go_router_builder (TypedGoRoute, compile-time safe) + StatefulShellRoute.indexedStack (bottom nav state preservation) + Router Refresh Pattern (_RouterRefreshNotifier + ref.listen — redirect without router rebuild) + PopScope (predictive back).
    • RN: Expo Router (file-based, typed routes) + Stack.Protected (auth guards) + groups (auth)/ (main)/ (tabs)/.
  8. [REQ] Networking:
    • Flutter: dio (interceptors) + optional retrofit (type-safe @RestApi()) + freezed + json_serializable. Freezed Failure union: network/cache/auth/server/permission/unknown.
    • RN: axios (auth interceptors, auto-token, 401 auto-logout) + TanStack Query (caching, retry, optimistic). Query cache buster: user:${userId} to prevent cross-user leaks.
  9. [REQ] Authentication:
    • Flutter: Firebase Auth (confined to data/ layer) + flutter_secure_storage + multi-flavor (main_staging.dart / main_production.dart).
    • RN: Supabase email OTP / custom JWT + expo-secure-store (Keychain/Keystore) + Ordered logout cleanup (cancelQueries -> posthog.reset -> sentry.setUser(null) -> queryClient.clear -> authStore.reset -> signOut -> router.replace).
  10. [REQ] Design system:
    • Flutter: ColorScheme.fromSeed() + Theme.of(context) ONLY + FlexColorScheme v8 + ThemeExtension for tokens. Material 3 default ON.
    • RN: react-native-unistyles v3 (semantic tokens, compiled stylesheets) + StyleSheet.create((theme) => ({...})) + responsive helpers rf()/hs()/vs().
    • Both: light/dark/system themes; WCAG AA contrast; tap targets >= 44pt (RN) / 48dp (Flutter); no hardcoded colors/sizes; responsive breakpoints (compact <600, medium 600-840, expanded >840).
  11. [REQ] i18n & RTL:
    • Flutter: flutter_localizations + intl + ARB OR Slang (compile-time safe). RTL: EdgeInsetsDirectional / AlignmentDirectional.
    • RN: react-i18next + I18nManager.forceRTL(isArabic) + ESLint plugin for translation completeness.
    • Both: never hardcode user-facing strings; validation messages use i18n keys; test RTL with Directionality(textDirection: TextDirection.rtl) (Flutter) / I18nManager.forceRTL(true) (RN).
  12. [REQ] Testing two-tier [TEST-07]:
    • Flutter: FAST flutter test <file>; FULL flutter test --coverage + integration_test/ + Patrol (native dialogs). Mock: mocktail.
    • RN: FAST jest <pattern>; FULL jest --coverage + Maestro (YAML E2E, <1% flake, all platforms). Mock: jest-expo + RNTL.
    • Both: AAA pattern; one behavior per test; factories not hardcoded IDs/dates [TEST-03]; accessibility-first (getByRole/getByLabelText); testID convention {feature}-{element}-{action}.
  13. [REQ] CI/CD:
    • Flutter: GitHub Actions (orchestrator) + Codemagic (build farm, macOS M2) + Fastlane (store submission). Pipeline: dart format -> flutter analyze --fatal-infos -> flutter test -> flutter build appbundle/ipa --obfuscate --split-debug-info -> sign -> deploy.
    • RN: EAS Workflows (build + submit + OTA update) + GitHub Actions (tests/lint). eas-cli build --no-wait (fire-and-forget) + webhooks. Environment-specific scripts.
    • Both: pin action SHAs [GIT-05]; OIDC keyless; SBOM + Cosign; auto-increment version for production.
  14. [REQ] Observability: Sentry (crash + session replay) + PostHog (analytics + feature flags + A/B + session replay). Wire observers into router for screen tracking. Reset identity on logout. Upload debug symbols for symbolication. Monitor crash-free users >= 99.5%.
  15. [REQ] Security [SEC-01..10]: zero-trust input validation; no secrets in code (--dart-define / EXPO_PUBLIC_*); HTTPS + cert pinning; secure storage for tokens; obfuscate release; Play Integrity / DeviceCheck; no PII in logs.
  16. [REQ] IAP/Monetization: in_app_purchase (Flutter) / react-native-iap (RN) + RevenueCat (subscription lifecycle, server-side validation, cross-platform entitlements). Balance IAP, rewarded ads, subscriptions, battle passes.
  17. [REQ] AI instruction files: Every mobile project MUST include AGENTS.md (architectural vetos, banned patterns, state rules, backend isolation) + .cursorrules (IDE-specific) + docs/AI-GUIDE.md (pattern cookbook with file templates). Reference: rn-copilot's AI ecosystem.
  18. [REQ] Component library: 30+ production-ready UI components with variants API, press animations, full accessibility (ARIA roles), barrel exports. Flutter: extract widgets to classes (not methods). RN: src/common/components/ with ComponentName.tsx + .types.ts + .styles.ts + index.ts.
  19. [REQ] Query Context7 for ANY mobile library/framework API before implementation. Test on physical devices (iOS + Android) before declaring done. Run quality gates before done.
  20. [REQ] Cross-platform feature detection: Flutter Platform.isIOS/kIsWeb; RN Platform.OS. SafeArea for notches. Adaptive widgets (Cupertino/Material). LayoutBuilder + breakpoints for responsive.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 9d ago First seen · 71 lines · 50 tokens per session scan A c4ce94a216a3

Subscribe to this mod's changes

mobile-architect is a skill published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 2,464 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 2026-09-03.

Mobile
Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

react-native-ease-refactor

Scan for Animated/Reanimated code and migrate to EaseView.

appandflow/react-native-ease · 18 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens