Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/iammohdzaki/kmp-skillsnpx agentmods add skills/iammohdzaki/kmp-skills/kmp-mvi-setupWrote 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/skills/iammohdzaki/kmp-skills/kmp-mvi-setup)<a href="https://agentmods.dev/skills/iammohdzaki/kmp-skills/kmp-mvi-setup"><img src="https://agentmods.dev/badge/skills/iammohdzaki/kmp-skills/kmp-mvi-setup/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/skills/iammohdzaki/kmp-skills/kmp-mvi-setup"><img src="https://agentmods.dev/badge/skills/iammohdzaki/kmp-skills/kmp-mvi-setup.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 | $0.00060 | $0.04102 |
| Opus 5 | $0.00030 | $0.02051 |
| Sonnet 5 | $0.00012 | $0.00820 |
| Haiku 4.5 | $0.00006 | $0.00410 |
Grade A, and why
kmp-mvi-setup 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 12d 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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KMP + MVI Project Setup Skill
This skill guides you through creating a production-ready Kotlin Multiplatform (KMP) project using MVI (Model-View-Intent) architecture with Compose Multiplatform.
IMPORTANT: Before writing any code or project structure, you MUST ask the user all Pre-flight Questions below and wait for answers. Never assume defaults silently.
PREREQUISITE SKILLS: Read these skills first before generating any files:
kmp-versions— always fetch live compatible versions from official sourceskmp-project-structure— use the new multi-module layout (shared/+androidApp/)
Pre-flight Questions
Ask the user these questions in a single message before generating anything. Wait for all answers before reading any reference files or writing any code.
Before I scaffold your KMP project, I need a few details:
1. ℹ️ App name & package
What is your app name and base package?
e.g. App Name: "Task Manager", Package: "com.example.taskmanager"
2. 📱 Target platforms
- Android only
- Android + Desktop (JVM)
- Android + Desktop + iOS (requires macOS for iOS build)
3. 🔧 Dependency Injection
- Koin (recommended — KMP-native, simple DSL, no code gen)
- Manual DI (constructor injection, no library)
- Other — please specify
4. 🌐 Networking
Do you need HTTP API calls?
- Ktor (recommended — KMP-native, multiplatform engines)
- None (no networking needed)
- Other — please specify
5. 📦 Serialization
Do you need JSON or data encoding?
- kotlinx.serialization (recommended — works on all targets)
- None (no serialization needed)
- Other — please specify
6. 🖼️ Image loading
Do you need to load images from URLs?
- Coil 3 + Landscapist (recommended — KMP-ready, composable wrappers)
- Coil 3 standalone (ImageRequest API directly)
- None (skip for now)
- Other — please specify
7. 🦭 Navigation
Do you want type-safe navigation-compose scaffolded?
- Yes (recommended — @Serializable routes, NavHost, NavController via Effect)
- No (I’ll add it later)
8. 🗄️ Local Storage / Database
Do you need persistent local data storage?
- multiplatform-settings (small data: prefs, flags, settings — KMP-native)
- SQLDelight (recommended for structured data — full KMP: Android + iOS + Desktop)
- Room (structured data — Android/JVM only, no iOS)
- Both multiplatform-settings + SQLDelight (prefs + structured data)
- None (no local storage needed)
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/di-options.md 5.1 KB
- references/image-loading.md 6.4 KB
- references/mvi-patterns.md 15 KB
- references/navigation.md 5.5 KB
- references/network-ktor.md 7.7 KB
- references/serialization.md 6.0 KB
- references/storage-datastore.md 6.1 KB
- references/storage-room.md 7.2 KB
- references/storage-sqldelight.md 10 KB
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.
- 12d ago First seen · 430 lines · 60 tokens per session scan A ac92e014843b
kmp-mvi-setup is a skill published in the GitHub repository iammohdzaki/kmp-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 4,102 once invoked, about $0.0003 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 skills, from other repositories
neo-swift-ui
Use this skill when building, debugging, refactoring, or reviewing SwiftUI apps or views for iOS 16+ and related Apple platforms. Trigger for NavigationStack, Observation/state flow, view composition, previews, performance, accessibility, and SwiftUI architecture.
neo-swift
Use this skill when writing, reviewing, debugging, or modernizing Swift code for iOS, macOS, server-side Swift, or shared packages. Trigger for Swift 5+ language features, structured concurrency, memory safety, protocols/generics, SwiftUI integration, and performance-sensitive code.
swift-project-setup
Bootstraps a new Swift/SwiftUI/UIKit project with MVVM architecture, standard folder structure, testing targets, and CLAUDE.md configuration. Use when user says "create a new project", "setup a new app", "start a new iOS project", "scaffold a Swift project", "initialize an Xcode project", or "new SwiftUI app".
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
kotlin-patterns
Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.
swift-patterns
Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.