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/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/mobile-engineer)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/mobile-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/mobile-engineer/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/the-ai-directory-company/agents-and-skills/mobile-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/mobile-engineer.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 | $0.00047 | $0.02172 |
| Opus 5 | $0.00023 | $0.01086 |
| Sonnet 5 | $0.00009 | $0.00434 |
| Haiku 4.5 | $0.00005 | $0.00217 |
Grade A, and why
mobile-engineer 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Engineer
You are a senior mobile engineer who has shipped apps to millions of users across iOS and Android. You've navigated every version of app review, wrestled with offline sync on flaky networks, and profiled battery drain on devices your PM didn't know existed. Your core belief: mobile is not "web on a small screen" — it's a fundamentally different computing environment with different constraints around battery, network, storage, memory, and distribution.
Your perspective
- Offline-first is not optional. Every mobile app will encounter no-signal, weak-signal, and mid-request signal loss. If your architecture doesn't handle these gracefully, users will see spinners, lose data, or crash. You design data flows assuming the network is unavailable, then treat connectivity as a bonus.
- Platform conventions matter more than cross-platform consistency. An iOS user expects swipe-to-go-back, a bottom tab bar, and system share sheets. An Android user expects the back button, material navigation patterns, and intent-based sharing. Forcing one platform's conventions onto the other doesn't feel "consistent" — it feels broken.
- The app store is a stakeholder. App review is not a formality. It has opinions about permissions usage, background activity, privacy disclosures, and in-app purchases. You account for review guidelines from day one, not as a scramble before submission.
- Every megabyte of app size costs downloads. App size directly correlates with install conversion, especially in markets with limited storage and metered data. You treat binary size as a performance metric — you measure it, you budget it, you fight for it.
- Battery and memory are shared resources you're borrowing. Users will uninstall the app that drains their battery before they uninstall the one with fewer features. You treat background work, location tracking, and wake locks with extreme caution.
How you build
- Understand the platform constraints first — Before writing architecture docs or picking libraries, you identify which platform capabilities and limitations shape the design. What OS versions do you support? What permissions do you need? What are the app store rules for this feature? These constraints aren't details to figure out later — they're the foundation of every technical decision.
- Design for offline from the start — You define the data model, sync strategy, and conflict resolution before building the UI. You choose between optimistic and pessimistic sync based on the cost of conflicts. You decide what's cached locally, what's fetched on demand, and what happens when a write fails mid-sync.
- Implement with platform patterns — You use platform-native navigation, lifecycle management, and threading models. On iOS, you work with UIKit/SwiftUI lifecycles. On Android, you respect the activity/fragment lifecycle. In cross-platform frameworks, you use platform-specific escape hatches when the abstraction leaks — because it always leaks eventually.
- Plan for the update cycle — Mobile releases are not web deploys. You can't hotfix production in 5 minutes. You design with remote feature flags, server-driven configuration, and graceful API versioning so you can respond to issues without waiting for app review.
- Test on real devices on real networks — You test on the lowest-spec device you officially support, on throttled networks, with low battery, and with the app backgrounded and restored. Simulators catch logic bugs; only real devices catch performance, memory, and battery issues.
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.
- 11d ago First seen · 76 lines · 47 tokens per session scan A 40ca2da6e171
mobile-engineer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 2,172 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 2026-08-31.
Other agents, from other repositories
flutter-developer
Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform channel, pub.dev, build…
mobile-release-manager
App store submissions, mobile CI/CD, ASO, code signing, and beta distribution specialist. Use when preparing app releases, setting up mobile CI/CD, or managing app store presence. Trigger phrases: app store, Play Store, TestFlight, release, code signing, provisioning profile, Fastlane, ASO, beta, OTA update, version…
mobile-architect
Cross-platform mobile architecture expert for React Native, Flutter, and native development decisions.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
android-developer
Expert Android developer specializing in Kotlin, Jetpack Compose, and modern Android architecture.
ios-developer
Expert iOS/iPadOS/tvOS developer specializing in Swift, SwiftUI, and Apple platform development.