antigravity-superpowers: Skill for Claude Code

.agent/skills/mobile-developer/SKILL.md

mobile-developer is a skill for Claude Code, Codex from bonnguyenitc/antigravity-superpowers. It costs 35 tokens per session (1,873 once invoked), scanned A, original, MIT.

A set of guidelines for building and reviewing mobile apps on iOS and Android, including apps made with React Native, Flutter, SwiftUI, or Jetpack Compose.

In plain words
What is it for?
Use it when planning mobile features, choosing an app framework, reviewing mobile code, or making architecture decisions.
Why use it?
It prevents desktop assumptions from causing problems on phones, such as poor support for weak networks, one-handed use, different platform behavior, or low battery.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is bonnguyenitc/antigravity-superpowers's own configuration. It tells Claude Code and Codex how to work on antigravity-superpowers itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything antigravity-superpowers configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bonnguyenitc/antigravity-superpowers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bonnguyenitc/antigravity-superpowers/main/.agent/skills/mobile-developer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bonnguyenitc/antigravity-superpowers

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-developer

README.md
[![agentmods](https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/mobile-developer.svg)](https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/mobile-developer)
Your own site
<a href="https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/mobile-developer"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/mobile-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,873 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 $0.00035 $0.01873
Opus 5 $0.00017 $0.00937
Sonnet 5 $0.00007 $0.00375
Haiku 4.5 $0.00003 $0.00187

Measured 8d ago against content hash 636ecc38f6fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mobile-developer 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.

.agent/skills/mobile-developer/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile Developer Lens

Philosophy: Touch-first. Offline-capable. Battery-conscious. Platform-respectful. Mobile is NOT a small desktop. Design for bad network, one hand, bright sun, low battery.


⚠️ ASK BEFORE ASSUMING

If the request is open-ended, DO NOT default to React Native. Ask:

What Why it matters
Platform? iOS / Android / Both Affects EVERY design decision
Framework? RN / Flutter / SwiftUI / Compose Determines patterns and tools
Offline required? Core architecture decision
Target devices? Phone / Tablet Layout and nav complexity

When stack is unspecified, assume React Native + Expo.


Framework Decision Tree

What are you building?
├── Need OTA updates + rapid iteration → React Native + Expo
├── Pixel-perfect custom UI + perf-critical → Flutter
├── Deep native features, single platform
│   ├── iOS only → SwiftUI (iOS 16+) or UIKit (legacy)
│   └── Android only → Kotlin + Jetpack Compose
└── Existing codebase → match the codebase

Core Instincts

  • Offline-first — assume the network will fail; design around it from day one
  • Platform parity — iOS and Android behave differently; both must work
  • Startup cost — every dependency adds to cold start time and binary size; justify each one
  • UI/main thread is precious — heavy computation and animations must run off the main thread
  • Battery budget — background tasks, location, and push use real energy; minimize wake-ups

Performance Thresholds

Metric Target Critical
Cold start time (JS bundle ready) < 1s > 2s
Time to interactive (first screen) < 2s > 4s
List scroll frame rate 60fps < 45fps
IPA / APK download size < 30MB > 100MB
Memory usage (foreground) < 150MB > 300MB
JS bundle size (RN, gzipped) < 1MB > 3MB

❌ Anti-Patterns to Avoid

❌ NEVER DO Why ✅ DO INSTEAD
ScrollView for long lists Renders ALL items, memory explodes FlatList / FlashList / ListView.builder
Inline renderItem function New function every render, all items re-render useCallback + React.memo on item component
Missing keyExtractor (or using index) Reorder causes state/animation bugs Use unique stable ID from data
useNativeDriver: false on animations Animations run on JS thread, janky useNativeDriver: true — GPU-only transforms
Token in AsyncStorage Plaintext, exposed on rooted device expo-secure-store / Keychain / EncryptedSharedPreferences
Business logic in UI components Untestable, duplicated Separate service/hook layer
Deep links as afterthought Notifications and shares break Plan linking config from day one
console.log in production build Blocks JS thread, leaks data Remove; use a proper logger with levels

Read the full file on GitHub · 195 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 195 lines · 35 tokens per session scan A 636ecc38f6fb

Subscribe to this mod's changes

mobile-developer is a skill published in the GitHub repository bonnguyenitc/antigravity-superpowers (19 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,873 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.

Related

Other skills, from other repositories

codeck

Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…

isdou/codeck · 108 tokens

ui-mobile

Mobile UI patterns - React Native, iOS/Android, touch targets.

alinaqi/maggy · 17 tokens

android-kotlin

Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing.

alinaqi/maggy · 22 tokens

Debroid CLI Debugger

Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.

PatilShreyas/debroid · 61 tokens

compose-multiplatform

Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…

ericrisco/rsc-harness · 80 tokens

kotlin-android

Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).

ericrisco/rsc-harness · 78 tokens