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/moclam1905/cocktailrecipes/project_overview_templategit clone --depth 1 https://github.com/moclam1905/CocktailRecipesWrote 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/moclam1905/cocktailrecipes/project_overview_template)<a href="https://agentmods.dev/rules/moclam1905/cocktailrecipes/project_overview_template"><img src="https://agentmods.dev/badge/rules/moclam1905/cocktailrecipes/project_overview_template.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 5.1 | $0.00013 | $0.04553 |
| Opus 5 | $0.00006 | $0.02277 |
| Sonnet 5 | $0.00003 | $0.00911 |
| Haiku 4.5 | $0.00001 | $0.00455 |
Grade A, and why
project_overview_template 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 5d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview Template
This project is a modern Android application built with Kotlin and Jetpack Compose, following a Clean Architecture approach. The architecture emphasizes separation of concerns, modular code organization, and use of Android best practices (MVVM, dependency injection with Hilt, etc.) to create a scalable and maintainable codebase.
Project Structure
The project is organized into multiple Gradle modules to enforce clear layering and feature separation:
ProjectName/
├── app/ - Android app module (application entry point, UI composition, navigation)
├── domain/ - Domain layer (business logic: use cases, domain models, repository interfaces)
├── data/ - Data layer (implementation of repositories, network services, database access)
├── core/ - Core utilities (common code such as UI theming, extensions, constants) *optional*
├── feature_login/ - Feature module: Login (UI screens and ViewModel for user authentication)
├── feature_dashboard/ - Feature module: Dashboard (UI and logic for the dashboard feature)
└── buildSrc/ - Build script module (Gradle Kotlin DSL for dependency versions and build logic)
Each feature of the app (e.g., login, dashboard, etc.) can be implemented in its own module (like feature_login, feature_dashboard above), which depends on the core, domain, and data modules. This modular structure improves encapsulation and build times, and makes it easier to scale the codebase.
Key Patterns & Concepts
-
Clean Architecture (Layered Architecture): The codebase is divided into layers (presentation, domain, data) to separate concerns:
-
Presentation layer (UI): Contains Android-specific code, Jetpack Compose UI, ViewModels. Depends on the domain layer.
-
Domain layer: Contains enterprise logic, use case classes, and domain models. This layer is independent of any Android framework or library.
-
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.
- 5d ago First seen · 282 lines · 4,553 tokens per session scan A fbd9751dd5a6
project_overview_template is a cursor rule published in the GitHub repository moclam1905/CocktailRecipes (1 stars, last pushed 1y ago), licensed MIT. It adds 13 tokens to every session and 4,553 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 2026-08-31.
Other cursor rules, from other repositories
ios-project-onboarding
Walks a new developer through one-time setup of an EXISTING configured iOS project from a blank macOS install — Xcode, Fastlane, SPM dependencies, code signing, simulator, and a smoke-test build. Assumes App Store Connect + Firebase + Fastlane are already configured upstream; user just needs local toolchain +…
compose-core
Modern Android development rules: Kotlin 2.x with K2, Jetpack Compose, Material 3, state hoisting + StateFlow + collectAsStateWithLifecycle, Hilt with hiltViewModel(), type-safe Navigation Compose, KSP, Version Catalogs, Compose Compiler as Kotlin plugin.
compose-architecture
Android architecture patterns: feature modularization, repository + data source pattern, sealed interfaces for UI state, ViewModel + StateFlow, Ktor / Retrofit + Kotlin Serialization, Room with Flow returns + KSP, coroutines structured concurrency.
android
Android 原生开发约定和最佳实践,包括 Kotlin、Jetpack Compose、架构模式等.
android_bak
该规则解释了 Android 原生开发的约定和最佳实践,包括 Kotlin、Java、Jetpack Compose 等。.
python
Cursor rule "python" from flyeric0212/cursor-rules, covering 角色, 目标, 编写代码时: and 解决问题时:.