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/inboxpraveen/Minimize-Cursor-CostWrote 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/inboxpraveen/minimize-cursor-cost/mobile)<a href="https://agentmods.dev/rules/inboxpraveen/minimize-cursor-cost/mobile"><img src="https://agentmods.dev/badge/rules/inboxpraveen/minimize-cursor-cost/mobile/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/inboxpraveen/minimize-cursor-cost/mobile"><img src="https://agentmods.dev/badge/rules/inboxpraveen/minimize-cursor-cost/mobile.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 | $0.00000 | $0.00631 |
| Opus 5.5 | $0.00000 | $0.00252 |
| Sonnet 5.5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
mobile 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 2mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Rules
These apply when working on mobile-specific code. The TS/React rules still apply for React Native; this layers on top.
Universal mobile principles
- Don't add new native dependencies (CocoaPods, Gradle, Flutter packages) without flagging.
- Don't change minimum SDK / deployment target without asking.
- Don't add new permissions to Info.plist / AndroidManifest without flagging.
- Don't restructure the platform folder layout (
ios/,android/,lib/).
Swift / SwiftUI / UIKit
- Detect first: SwiftUI vs UIKit. Don't mix paradigms in a screen.
- Match existing concurrency style: Combine vs async/await vs callbacks. Don't switch.
- Don't add
@MainActor/@Observable/@StateObjectspeculatively. - Don't change
let↔varunless required. - Match existing dependency injection: protocol-oriented vs framework (Resolver, Swinject).
Kotlin Android
- Detect first: Jetpack Compose vs Views (XML). Don't mix in a screen.
- Match existing architecture: MVVM / MVI / Clean. Don't introduce a new layer.
- Match existing DI: Hilt / Koin / manual. Don't switch.
- Don't add coroutine scopes — match existing
viewModelScope/lifecycleScopeusage. - Don't add new lifecycle observers unless needed.
React Native
- Match existing navigation: React Navigation / Expo Router. Don't switch.
- Don't introduce a new state library — match existing.
- Match existing styling: StyleSheet / styled-components / NativeWind / Tamagui.
- Don't add platform-specific code (
Platform.OSchecks) unless the bug requires it. - Don't add new native modules unless asked.
Flutter
- Match existing state management: Provider / Riverpod / Bloc / GetX / setState. Don't switch.
- Don't restructure widget trees as a side-effect.
- Match existing folder structure (feature-first vs layer-first).
- Don't add
constconstructors retroactively unless asked. - Don't change
StatefulWidget↔StatelessWidgetunless required.
Output
- Show the smallest changeable unit: a single function, widget, or composable.
- Use
// ... rest of class/widget unchangedto skip. - Don't reprint generated files (
.g.dart, build outputs).
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.
- 2mo ago First seen · 56 lines · 0 tokens per session scan A e74aef9ca805
mobile is a cursor rule published in the GitHub repository inboxpraveen/Minimize-Cursor-Cost (10 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 631 tokens. 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
flutter
Flutter: Riverpod, widget extraction, Dart 3.
react-native
A set of rules for building mobile apps with TypeScript, React Native, Expo, and mobile interface components. React Native lets developers create native mobile apps with React, while Expo provides supporting tools.
23-app-startup
Application class, SplashScreen, StartupActivity + MainActivity split, and AndroidX Startup.
03-android-architecture
Clean Architecture layer rules.
29-screen-startup
StartupActivity funnel — StartupFragment init/routing, Startup screens, hand-off to MainActivity.
21-ads-billing
AdMob :gmaAds and in-app billing / premium patterns.