cursorrules

A collection of AI agent prompts, skills, and reusable workflows for Android, iOS, Flutter, React Native, Unity, and Unreal Engine development. Each agent defines the input and output format and includes a worked example for use in Cursor.

In plain words
What is it for?
Use it in Cursor Chat, with file references, or in Cursor Composer to apply agents such as code reviewers, crash analyzers, and performance tools to selected code.
Why use it?
It gives developers repeatable instructions for common mobile and game-development tasks instead of writing every prompt from scratch.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/salmanashraf/mobile-ai-agents/cursorrules
Clone the repo
git clone --depth 1 https://github.com/salmanashraf/mobile-ai-agents

Made for: Cursor.

Per session 1,304 This file is loaded in full into every session.
When invoked 1,304 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01304 $0.01304
Opus 5 $0.00652 $0.00652
Sonnet 5 $0.00261 $0.00261
Haiku 4.5 $0.00130 $0.00130

Measured 2d ago against content hash 4e14b70acbe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile Dev Skill Agents — Cursor Rules

This file is loaded automatically by Cursor AI for every session in this repo.

What This Repo Is

A toolkit of AI agents, skill prompts, and reusable workflows for Android, iOS, Flutter, React Native, Unity, and Unreal Engine developers. Every agent has a defined input format, output format, and a real worked example.


How to Use an Agent in Cursor

Option A — Cursor Chat (fastest)

In Cursor Chat, say: "Read agents/android/code-reviewer/agent.md and use it to review the file I paste below:" Then paste your code.

Option B — @file reference

In Cursor Chat: @agents/android/code-reviewer/agent.md Review this ViewModel for Clean Architecture issues: [paste code]

Option C — Cursor Composer (multi-file)

Open Composer (Cmd+I), then: "Apply the agent at agents/react-native/performance-optimizer/agent.md to every component in src/screens/ and list all findings."


Agent Index

Agent File Platform What It Does
Android Code Reviewer agents/android/code-reviewer/agent.md Android Kotlin/Compose: Clean Architecture, coroutines, anti-patterns
Android Crash Analyzer agents/android/crash-analyzer/agent.md Android Crash log → root cause, fix, test checklist
Android Compose Reviewer agents/android/compose-ui-reviewer/agent.md Android Compose-specific: recomposition, state hoisting, LazyColumn
Swift Code Reviewer agents/ios/swift-reviewer/agent.md iOS Swift/SwiftUI: memory safety, concurrency, idiomatic patterns
iOS Crash Analyzer agents/ios/crash-analyzer/agent.md iOS iOS crash/symbolicated reports → root cause + fix
Flutter Widget Generator agents/flutter/widget-generator/agent.md Flutter Plain English → production Dart widget
RN Performance Optimizer agents/react-native/performance-optimizer/agent.md React Native Re-renders, bridge calls, FlatList tuning
Unity Shader Generator agents/unity/shader-generator/agent.md Unity Visual description → HLSL/ShaderLab shader
Unreal Blueprint Advisor agents/unreal/blueprint-advisor/agent.md Unreal Blueprint review + C++ migration
Release Notes Generator agents/cross-platform/release-notes-generator/agent.md All git log → App Store / changelog / QA notes
CI/CD Pipeline Generator agents/cross-platform/ci-cd-generator/agent.md All GitHub Actions / Fastlane / Bitrise configs
Store Listing Writer agents/cross-platform/store-listing-writer/agent.md All ASO-optimized App Store + Play Store copy
Security Scanner agents/cross-platform/security-scanner/agent.md All OWASP Mobile Top 10 vulnerabilities
Accessibility Auditor agents/cross-platform/accessibility-auditor/agent.md All a11y audit: labels, touch targets, focus order

Read the full file on GitHub · 114 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. 2d ago First seen · 114 lines · 1,304 tokens per session scan A 4e14b70acbe7

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository salmanashraf/mobile-ai-agents (25 stars, last pushed 5d ago), licensed MIT. It adds 1,304 tokens to every session, about $0.0065 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.