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 rules/sanjeed5/awesome-cursor-rules-mdc/android-sdkgit clone --depth 1 https://github.com/sanjeed5/awesome-cursor-rules-mdcWrote 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/rules/sanjeed5/awesome-cursor-rules-mdc/android-sdk)<a href="https://agentmods.dev/rules/sanjeed5/awesome-cursor-rules-mdc/android-sdk"><img src="https://agentmods.dev/badge/rules/sanjeed5/awesome-cursor-rules-mdc/android-sdk.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 | $0.03791 | $0.03791 |
| Opus 5 | $0.01895 | $0.01895 |
| Sonnet 5 | $0.00758 | $0.00758 |
| Haiku 4.5 | $0.00379 | $0.00379 |
Grade A, and why
android-sdk 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.
How it starts
The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
android-sdk Best Practices (Java)
This guide outlines the essential practices for building robust, performant, and maintainable Android applications using Java, adhering to modern standards and leveraging the AndroidX ecosystem.
1. Code Organization and Structure
1.1 Modular Architecture (MVVM) Adopt a clean, modular architecture, with MVVM (Model-View-ViewModel) as the standard. This promotes separation of concerns, testability, and scalability.
❌ BAD: Tight Coupling
// Activity directly fetching data and updating UI
public class UserProfileActivity extends AppCompatActivity {
private TextView userName;
// ... other UI elements
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_user_profile);
userName = findViewById(R.id.user_name);
// Direct network call on UI thread (or poorly managed background thread)
new Thread(() -> {
String name = fetchUserNameFromNetwork(); // Blocking call
runOnUiThread(() -> userName.setText(name));
}).start();
}
// ...
}
✅ GOOD: MVVM with Repository Pattern
// ui/UserProfileActivity.java
public class UserProfileActivity extends AppCompatActivity {
private UserProfileViewModel viewModel;
private TextView userName;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_user_profile);
userName = findViewById(R.id.user_name);
viewModel = new ViewModelProvider(this).get(UserProfileViewModel.class);
viewModel.getUserName().observe(this, name -> {
userName.setText(name);
});
}
}
// ui/UserProfileViewModel.java
public class UserProfileViewModel extends AndroidViewModel {
private UserRepository userRepository;
private MutableLiveData<String> userName = new MutableLiveData<>();
public UserProfileViewModel(@NonNull Application application) {
super(application);
this.userRepository = new UserRepository(application); // Injected via Hilt in real app
loadUserName();
}
public LiveData<String> getUserName() {
return userName;
}
private void loadUserName() {
// Use ExecutorService or RxJava for background work
Executors.newSingleThreadExecutor().execute(() -> {
String name = userRepository.fetchUserName();
userName.postValue(name); // Post value to main thread
});
}
}
// data/UserRepository.java
public class UserRepository {
// In a real app, this would interact with Room, Retrofit, etc.
public String fetchUserName() {
// Simulate network call
try { Thread.sleep(2000); } catch (InterruptedException e) {}
return "John Doe";
}
}
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 · 540 lines · 0 tokens per session scan A e1f3dc53c461
android-sdk is a cursor rule published in the GitHub repository sanjeed5/awesome-cursor-rules-mdc (3,571 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 3,791 tokens to every session, about $0.0190 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 cursor rules, from other repositories
workflow-level3
Defines the standard workflow for Level 3 (Intermediate Feature) tasks, guiding through comprehensive planning, targeted creative design, structured implementation, detailed reflection, and feature-specific archiving.
executing-red-team-engagement-planning
Red team engagement planning is the foundational phase that defines scope, objectives, rules of engagement (ROE), threat model selection, and operational timelines before any offensive testing begins.
solana-integration-constraints
Constraints and requirements for Solana integration with MetaMask Connect — wallet adapter config, CAIP-2 IDs, network support per platform, RPC routing, and platform limitations.
visual-and-observational-rules
Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen effects, and the overall simulation style.
018_DSPy_InputField_OutputField
DSPy 3.0.1 Field Definitions - Master InputField and OutputField for precise signature control.
python-cryptographic-failures
Detect and prevent cryptographic failures in Python applications as defined in OWASP Top 10:2021-A02.