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.
git clone --depth 1 https://github.com/moasq/ios-dev-agentWrote 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/moasq/ios-dev-agent/scope)<a href="https://agentmods.dev/rules/moasq/ios-dev-agent/scope"><img src="https://agentmods.dev/badge/rules/moasq/ios-dev-agent/scope/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/moasq/ios-dev-agent/scope"><img src="https://agentmods.dev/badge/rules/moasq/ios-dev-agent/scope.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00491 | $0.00491 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
scope 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Rules — Build the Minimum Functional App
Golden Rule: Small and Working > Big and Broken
A small app that works perfectly is ALWAYS better than a big app with broken features. Your goal is to impress the user with a polished, functional experience — not to overwhelm them with stub screens.
Screen Limits
- Default to 1–2 screens maximum unless the user explicitly asks for more.
- Pick only the MOST CRITICAL features that make the app functional.
- If the user mentions specific features, build those and ONLY those.
Examples
| User says | Build | Do NOT build |
|---|---|---|
| "notes app" | list + editor (2 screens) | folders, tags, search, sharing, trash, settings |
| "music app" | library list + now playing (2 screens) | browse, radio, search, social, lyrics |
| "TikTok clone" | scrollable video feed (1 screen) | discover, create, inbox, profile, comments |
| "weather app" | current weather + forecast (1 screen) | hourly breakdown, maps, alerts, settings |
| "todo app" | task list with add/complete (1 screen) | categories, due dates, recurring, sharing |
| "chat app" | conversation list + chat (2 screens) | contacts, settings, profile, media gallery |
Quality Over Quantity
- Every screen MUST be fully functional — real navigation, real data flow, real interactions.
- Do NOT create stub/placeholder views that show "Coming soon" or "TODO".
- Do NOT create empty tab views just to fill a TabBar.
- Prefer fewer polished screens over many incomplete screens.
- Build EXACTLY what the user asked for, nothing more. User intent is king.
Feature Scoping
- When the user asks for an "app clone" (e.g., "TikTok clone", "Spotify clone"), build the ONE defining feature that makes that app recognizable, not every feature the real app has.
- The defining feature of TikTok is the vertical video feed. The defining feature of Spotify is the music library + player. The defining feature of Instagram is the photo feed.
- Additional features can be added later via edit requests — that's what the edit flow is for.
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 · 43 lines · 491 tokens per session scan A 1eed15ed2a81
scope is a cursor rule published in the GitHub repository moasq/ios-dev-agent (4 stars, last pushed 3mo ago), licensed MIT. It adds 491 tokens to every session, about $0.0025 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 2026-09-03.
Other cursor rules, from other repositories
nativescript
NativeScript best practices and patterns for mobile applications.
performance-optimization
// Use weak/unowned references appropriately class ViewController: UIViewController { private var timer: Timer?
webkit-browser
Cursor rule "webkit-browser" from duckduckgo/apple-browsers, covering webkit & browser development guidelines, webview configuration, basic webview setup, user scripts management and tab management.
maestro-device-selection
Maestro tests can run on either iPhone or iPad simulators based on tags in the test YAML files. This allows you to test iPad-specific UI layouts and features while maintaining a single test suite.
cursorrules
Kortix is a React Native + Expo app built with TypeScript, NativeWind (Tailwind CSS), and a custom design system.
gradle
Enforce modern Gradle build practices for Java and Android projects, focusing on Kotlin DSL, modularity, version catalogs, and performance optimizations.