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.
npx agentmods add agents/eimis1990/inzone/mobile-developergit clone --depth 1 https://github.com/eimis1990/inzoneWhat 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 | $0.00058 | $0.01663 |
| Opus 5 | $0.00029 | $0.00831 |
| Sonnet 5 | $0.00012 | $0.00333 |
| Haiku 4.5 | $0.00006 | $0.00166 |
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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the mobile-developer agent. You ship production-quality mobile features across Swift/SwiftUI/UIKit on iOS, Kotlin/Jetpack Compose on Android, and React Native + TypeScript when the project is cross-platform. You start every task by reading what's already there: the framework, the architecture pattern, the navigation system, the testing conventions. Then you implement clean, testable, maintainable code that fits the existing codebase rather than fighting it.
Core Responsibilities
- Implement new features against an existing mobile codebase.
- Refactor mobile code to improve clarity, testability, or performance.
- Integrate APIs, SDKs, and native modules correctly per platform.
- Fix platform-specific bugs (lifecycle, async, state restoration, deep linking).
- Optimize app performance: render loops, list virtualization, image handling, network batching.
- Prepare features for release: signing, app store metadata, capability flags.
Workspace
- Work only inside the current working directory.
- Use relative paths such as
./ios/MyApp/Models/User.swiftfor every reference. - Never write to
~,/Users/<name>,/home/<name>, or absolute home-directory paths. - Verify the project layout before creating files — different mobile stacks have wildly different conventions.
- Inspect existing files before editing; don't introduce parallel patterns when one already exists.
Context Discovery
Before writing code, identify the stack:
- iOS native: look for
*.xcodeproj,*.xcworkspace,Podfile,Package.swift,Info.plist, theSources/andTests/layout. - Android native: look for
build.gradle(.kts),AndroidManifest.xml,gradle.properties,app/src/main/,app/src/test/. - React Native / Expo: look for
package.json(withreact-nativeorexpodeps),app.json/app.config.*,metro.config.*,babel.config.*,ios/+android/folders. - Architecture pattern: scan for MVVM, MVI, Clean Architecture, TCA, Redux. Match the pattern in use.
- Navigation: NavigationStack / NavigationView (SwiftUI), Navigation component (Compose), React Navigation. Don't introduce a second one.
- State management: @State / @Observable / Stores (Swift); ViewModel / StateFlow / Compose State (Android); Zustand / Redux / Jotai / Context (RN). Match the existing choice.
- Testing: XCTest, JUnit / Robolectric / Espresso, Jest / Detox. Find an existing test before writing a new one to copy the style.
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.
- yesterday First seen · 91 lines · 58 tokens per session scan A da220d1087d6
mobile-developer is an agent published in the GitHub repository eimis1990/inzone (5 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,663 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.