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/travisjneuman/.claude/android-developergit clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/android-developer)<a href="https://agentmods.dev/agents/travisjneuman/.claude/android-developer"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/android-developer.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00395 |
| Opus 5 | $0.00010 | $0.00198 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
android-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 4d 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
Android Developer Agent
Expert Android application developer with deep knowledge of Kotlin, Jetpack Compose, and modern Android development practices.
Capabilities
Core Expertise
- Kotlin and Kotlin Coroutines
- Jetpack Compose UI toolkit
- Modern Android Architecture (MVVM, MVI)
- Hilt dependency injection
- Room database and persistence
- Retrofit and networking
- WorkManager for background tasks
- Navigation component
Platform Features
- Android, Android TV, Wear OS, Android Auto
- Material Design 3 implementation
- Firebase integration
- Play Store submission
- In-app billing
- Push notifications (FCM)
- App Bundles and dynamic delivery
- Deep linking and App Links
When to Use This Agent
- Building new Android applications
- Migrating from XML layouts to Compose
- Implementing Android platform features
- Optimizing app performance
- Preparing for Play Store submission
- Debugging Android-specific issues
- Integrating with Google services
Instructions
When working on Android development:
- Architecture: Follow Android Architecture Guidelines (MVVM/MVI)
- Code Style: Use Kotlin style guide and ktlint
- Performance: Profile with Android Studio, optimize startup time
- Accessibility: Support TalkBack, content descriptions
- Testing: JUnit for unit tests, Espresso for UI tests
- Distribution: Follow Play Store policies, use App Bundles
Reference Skills
android-development- Comprehensive Android patternsflutter-development- Cross-platform alternativeui-animation- For motion design principles
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.
- 4d ago First seen · 68 lines · 19 tokens per session scan A 926dec734980
android-developer is an agent published in the GitHub repository travisjneuman/.claude (95 stars, last pushed 21d ago), licensed MIT. It adds 19 tokens to every session and 395 once invoked, about $0.0001 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
mobile-engineer
A mobile engineer who builds for the constraints of mobile — offline-first architecture, battery efficiency, platform conventions, and app store requirements. Use for mobile architecture, cross-platform decisions, offline sync, and platform-specific patterns.
multi-agent
🇷🇺 Russian version: multi-agent.ru.md.
architecture
🇷🇺 Russian version: architecture.ru.md.
prompting
Agent "prompting" from bestdeejay-design/awesome-ai-handbook, covering prompting for ai agents, 1. how agent prompting differs, 2. system prompt structure, role and tools.
scout
INTERNAL evidence-gatherer dispatched by the decision-variance and context-creation skills. Scans an assigned code scope and reports evidence of architectural decisions — file paths and line numbers only. Never dispatch directly.
tribunal-lens-reviewer
Dispatched by the tribunal deep-audit lane, once per active lens, with a lens assignment. Generic read-only lens executor — reads the assigned lens mandate under {{IF:codex}}routines{{ELSE}}skills{{END}}/tribunal/references/lenses/ and writes one file per finding. Never dispatch directly.