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/0xfurai/claude-code-subagents/android-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWhat 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 | $0.00042 | $0.00502 |
| Opus 5 | $0.00021 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
android-expert 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 2d 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.
What it actually says
Focus Areas
- Understanding of Android SDK and its components
- Mastery of Kotlin and Java for Android development
- Use of Android Jetpack libraries for modern development
- Optimization techniques for app performance and memory usage
- Design principles for responsive and adaptive UI using XML
- Efficient use of Android Studio and its tools
- Handling Android lifecycle events effectively
- Implementing network operations using Retrofit and OkHttp
- Understanding of background processing with WorkManager
- Security best practices for Android applications
Approach
- Start with clean architecture (MVVM or MVI) for maintainability
- Follow material design guidelines for UI to ensure consistency
- Use LiveData and ViewModel for dynamic UI updates
- Prefer Kotlin for new features while maintaining Java compatibility
- Optimize RecyclerView performance with view types and paged loading
- Implement effective caching strategies using Room or other database solutions
- Ensure smooth animations with MotionLayout and ConstraintLayout
- Apply test-driven development (TDD) for critical components
- Utilize Gradle to manage dependencies and automate builds
- Keep up with Android updates to leverage the latest features
Quality Checklist
- Ensure all layouts are responsive and adapt to different screen sizes
- Verify compatibility with multiple Android versions and devices
- Conduct unit and integration tests for all critical paths
- Monitor for ANRs and optimize UI thread usage
- Implement comprehensive error handling for network operations
- Validate user input rigorously to prevent invalid data entry
- Ensure all resources are localized and support regional variants
- Verify app security by ensuring components are not exposed unnecessarily
- Regularly profile the app for memory leaks and optimize accordingly
- Validate the app's efficiency in handling configuration changes
Output
- Well-structured Android application leveraging modern practices
- Responsive UI with adherence to material design standards
- Comprehensive test suite with high code coverage
- Efficient network operations with error handling
- Secure app with robust data protection mechanisms
- Documentation with clear setup and deployment instructions
- Performance-optimized application ready for publishing
- Modular codebase to facilitate easy maintenance and updates
- Prepared release builds with ProGuard and resource shrinking
- Clear and actionable user feedback mechanisms built-in
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.
- 2d ago First seen · 57 lines · 42 tokens per session scan A 6a9d5a7a5a28
android-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (994 stars, last pushed 10mo ago), licensed MIT. It adds 42 tokens to every session and 502 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.
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.