break_down_rule

break_down_rule is a cursor rule for Cursor from moclam1905/CocktailRecipes. It costs 20 tokens per session (1,148 once invoked), scanned A, original, MIT.

A task-breakdown rule for turning an Android feature design document into a detailed checklist. It targets Android apps built with Kotlin, a programming language, and Jetpack Compose, Android’s modern UI toolkit.

In plain words
What is it for?
Breaking down UI, logic, data, dependencies, error handling, testing, documentation, and open questions into implementation tasks.
Why use it?
It turns a broad design into smaller actions that developers can complete and track. It also makes dependencies and task order clearer.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Breaking down UI, logic, data, dependencies, error handling, testing, documentation, and open questions into implementation tasks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/moclam1905/cocktailrecipes/break_down_rule
Install

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.

Clone the repo
git clone --depth 1 https://github.com/moclam1905/CocktailRecipes

Made for: Cursor.

Wrote 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.

agentmods badge for break_down_rule

README.md
[![agentmods](https://agentmods.dev/badge/rules/moclam1905/cocktailrecipes/break_down_rule.svg)](https://agentmods.dev/rules/moclam1905/cocktailrecipes/break_down_rule)
Your own site
<a href="https://agentmods.dev/rules/moclam1905/cocktailrecipes/break_down_rule"><img src="https://agentmods.dev/badge/rules/moclam1905/cocktailrecipes/break_down_rule.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.01148
Opus 5 $0.00010 $0.00574
Sonnet 5 $0.00004 $0.00230
Haiku 4.5 $0.00002 $0.00115

Measured 7d ago against content hash d75675ba7958, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

break_down_rule 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 7d 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.

.cursor/rules/android-kotlin-compose-rules/break_down_rule.mdc · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Breakdown Rule

You are an expert project manager and Android software architect. Given a technical design document for a feature, your task is to break it down into a comprehensive, actionable checklist of smaller tasks. This checklist will guide developers and track progress.

Input

You will receive a Markdown document representing the technical design of an Android app feature or component. This design document typically includes sections like Overview, Purpose, Design (detailing UI, logic, data changes), Dependencies, Error Handling, and Open Questions.

Output

Produce a Markdown checklist that breaks down the implementation into discrete tasks.

Guidelines

  1. Granularity: Each task should be small enough to be completed within a few hours to a day. Avoid overly broad tasks; prefer more granular ones that clearly state a single objective.

  2. Actionable: Write tasks as concrete actions using strong verbs (e.g., "Create...", "Implement...", "Add...", "Update...", "Refactor...", "Test...", "Document...").

  3. Dependencies: Note any dependencies or order. If Task B relies on completion of Task A, indicate that (through ordering or an explicit note).

  4. Completeness: Cover all elements of the design:

    • Database or storage changes (e.g., Room entity or migration updates).

    • API integrations or modifications (e.g., calling new REST endpoints via Retrofit).

    • UI changes (Compose UI screens, components, navigation adjustments).

    • Business logic and domain layer implementation (ViewModels, use cases).

    • Unit tests for new logic.

    • UI tests or integration tests (if applicable).

    • Documentation updates (update README or design docs if needed).

    • Address any open questions or edge cases highlighted in the design.

  5. Clarity: Use clear, concise descriptions. Avoid ambiguous terms or internal jargon.

  6. Checklist Format: Use Markdown checklist syntax for tasks:

    - [ ] Task 1: Short description of task 1.
    - [ ] Task 2: Short description of task 2 (depends on Task 1).
    

Read the full file on GitHub · 109 lines

Changes

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.

  1. 7d ago First seen · 109 lines · 1,148 tokens per session scan A d75675ba7958

Subscribe to this mod's changes

break_down_rule is a cursor rule published in the GitHub repository moclam1905/CocktailRecipes (1 stars, last pushed 1y ago), licensed MIT. It adds 20 tokens to every session and 1,148 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.

Related

Other cursor rules, from other repositories

android-project

Core behavior rules for AI agents working on this Android project.

JoDaBaRo/agentic-mobile-rules · 8,084 tokens

ios-project-bootstrap

Walks a developer through bootstrapping a BRAND-NEW iOS project for agentic CLI delivery — Apple Developer Program enrollment, App Store Connect listing, provisioning profiles, Fastlane setup from scratch, Firebase App Distribution, TestFlight + App Store first upload. Use when the user says they're starting a new iOS…

JoDaBaRo/agentic-mobile-rules · 108 tokens

android-project-bootstrap

Walks a developer through bootstrapping a BRAND-NEW Android project for agentic CLI delivery — creating the Firebase project, registering the Android app, setting up App Distribution, creating the Google Play Console listing, wiring API access, and installing the Gradle plugins. Use when the user says they're starting…

JoDaBaRo/agentic-mobile-rules · 106 tokens

android-project-onboarding

Walks a new developer through one-time setup of an EXISTING configured Android project from a blank macOS install — JDK, Android SDK, AVD, scrcpy, shell env vars, credential files, and a smoke-test build. Assumes Firebase project + Play Console listing already exist; user just needs to acquire credentials. Use when…

JoDaBaRo/agentic-mobile-rules · 161 tokens

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 +…

JoDaBaRo/agentic-mobile-rules · 182 tokens

ios-project

Core behavior rules for AI agents working on this iOS project.

JoDaBaRo/agentic-mobile-rules · 4,506 tokens