What is mobile-development?

A software-development guide for iOS and Android apps, which must work with unreliable networks, limited batteries, platform rules, and app-store review. It emphasizes offline behavior, responsiveness, accessibility, and resource use.

Planning offline-capable features, keeping heavy work off the main screen thread, finding memory leaks, reducing battery use, analyzing app size, and preparing releases.

It addresses mobile problems that ordinary server or desktop practices can miss, such as blocked screens, crashes, battery drain, and poor behavior without a connection.

mobile-development — Skill for Claude Code and Codex by vignesh2027

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 vignesh2027/AI-AGENT-SKILLS --skill mobile-development

Clone the repo

git clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLS

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/mobile-development/github.svg)](https://agentmods.dev/skills/vignesh2027/ai-agent-skills/mobile-development)

Your own site

<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/mobile-development"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/mobile-development/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/mobile-development"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/mobile-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 520 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00520
Opus 5.5	$0.00009	$0.00208
Sonnet 5.5	$0.00004	$0.00104
Haiku 4.5	$0.00002	$0.00052

Measured 2mo ago against content hash d3ced4cda65f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mobile-development 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 2mo 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-development/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.

Overview

Mobile apps have unique constraints: unreliable networks, limited battery, strict platform guidelines, and app store review. This skill applies mobile-specific engineering discipline.

When to Use

Before implementing a new mobile feature
When an app is slow, crashes, or drains battery
Before submitting to the app store

Process

Step 1: Design for offline-first

Assume the network is unavailable. Design data flows that work offline and sync when connectivity returns. Use optimistic UI updates.

Step 2: Main thread discipline

No I/O on the main thread
No heavy computation on the main thread
Profile with Instruments (iOS) or Android Profiler for frame drops

Target: 60fps during all user interactions.

Step 3: Memory management

No strong reference cycles (iOS: use weak/unowned)
Instrument for memory leaks before release
Release large resources when the app backgrounds

Step 4: Battery efficiency

Minimize background work
Batch network requests
Use push over polling
Reduce GPS/sensor usage frequency when precision isn't needed

Step 5: App size

Analyze app size before each release
Use on-demand resources for large assets
Target: < 30MB download for initial install

Step 6: Crash rate

Integrate crash reporting from day one (Crashlytics, Sentry)
Fix crashes before shipping new features
Target: < 0.1% crash-free sessions

Step 7: Accessibility

Dynamic Type support (iOS) / font scaling (Android)
VoiceOver (iOS) / TalkBack (Android) tested
Touch targets ≥ 44pt × 44pt
Color contrast meets WCAG AA

Step 8: App store compliance

Review App Store / Play Store guidelines for relevant categories before implementing
Test on oldest supported OS version
Implement required privacy labels/permissions honestly

Verification Requirements

Offline state handled gracefully
No I/O or heavy computation on main thread
Profiled: 60fps during interactions
Crash reporting integrated
Accessibility tested with platform screen reader
App size within budget
Tested on oldest supported OS version

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.

2mo ago First seen · 71 lines · 22 tokens per session scan A d3ced4cda65f

Subscribe to this mod's changes

mobile-development is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 520 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Claude Code Mobile agent-skills ai-agents coding-agent cursor-ai developer-tools

mobile-development next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mobile-developmentvignesh2027/AI-AGENT-SKILLS	Skill	2	2mo ago	MIT	A	22	Claude Code, Codex
firebase-messagingevanca/flutter-ai-rules	Skill	668	2d ago	MIT	A	35	Claude Code
generate-images-with-firebase-aievanca/flutter-ai-rules	Skill	668	2d ago	MIT	A	84	Claude Code
firebase-app-checkevanca/flutter-ai-rules	Skill	668	2d ago	MIT	A	30	Claude Code
flutter-app-architectureevanca/flutter-ai-rules	Skill	668	2d ago	MIT	A	38	Claude Code
firebase-aievanca/flutter-ai-rules	Skill	668	2d ago	MIT	A	30	Claude Code
firebase-crashlyticsevanca/flutter-ai-rules	Skill	668	2d ago	MIT	A	34	Claude Code