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.
npx skills add ujffdi/mavericks-mvi-skills --skill mavericks-mvigit clone --depth 1 https://github.com/ujffdi/mavericks-mvi-skillsWrote 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/ujffdi/mavericks-mvi-skills/mavericks-mvi)<a href="https://agentmods.dev/skills/ujffdi/mavericks-mvi-skills/mavericks-mvi"><img src="https://agentmods.dev/badge/skills/ujffdi/mavericks-mvi-skills/mavericks-mvi/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/ujffdi/mavericks-mvi-skills/mavericks-mvi"><img src="https://agentmods.dev/badge/skills/ujffdi/mavericks-mvi-skills/mavericks-mvi.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 | $0.00083 | $0.01052 |
| Opus 5 | $0.00042 | $0.00526 |
| Sonnet 5 | $0.00017 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
mavericks-mvi 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mavericks MVI Guide
Mavericks screens are rendered from immutable state. Keep state data-only, reducers pure, and side effects in ViewModel methods or UI consumers.
Quick Reference
| Task | Use |
|---|---|
| Define screen state | data class XxxState(...) : MavericksState |
| Create Hilt VM | @AssistedInject + @Assisted initialState + Factory + hiltMavericksViewModelFactory() |
| Register VM | @Binds @IntoMap @ViewModelKey in the owning ViewModelModule |
| One-shot request | suspend { repo.call() }.execute { copy(request = it) } |
| Long-lived Flow to normal state | flow.setOnEach { value -> copy(value = value) } |
| Refresh without UI flicker | .execute(retainValue = State::request) { ... } |
| Compose VM | mavericksViewModel() or mavericksViewModel(argsFactory = { args }) |
| Compose state | vm.collectAsStateWithLifecycle(State::prop) |
| Fragment VM | by fragmentViewModel() / activityViewModel() / parentFragmentViewModel() |
| Fragment state | vm.onEach(State::prop) { ... } |
| Fragment one-shot | vm.onEach(State::effect, deliveryMode = uniqueOnly()) { ... } |
| Read current state in VM | withState { state -> ... } or suspend awaitState() |
Core Rules
- State must be immutable, public, data-only, and reducer-safe.
- Hilt Mavericks VMs must use
@AssistedInject,@Assisted initialState,@AssistedFactory, andhiltMavericksViewModelFactory(). - Every Hilt Mavericks VM must be bound with
@Binds @IntoMap @ViewModelKey. - Use
executefor finite async work represented byAsync<T>. - Use
setOnEachfor long-lived Flows that map directly to ordinary State fields. - Use Mavericks lifecycle-aware Compose collection:
com.airbnb.mvrx.compose.collectAsStateWithLifecycle. DeliveryModeis only forMavericksViewsubscriptions, not ViewModelonEachand not Compose.- Effects are a project pattern on top of State; nullable single effects are not queues.
Read Only What You Need
- State fields, immutability, args, and
@PersistState: references/state.md - ViewModel template,
execute,setOnEach,setState,withState: references/viewmodel-execute.md - Hilt component and map binding: references/hilt.md
- Compose, Fragment,
MavericksView,DeliveryMode, scopes: references/observing-ui.md - Nullable effects, effect queues, consumption rules: references/effects.md
Async<T>states and rendering patterns: references/async.md- Mavericks ViewModel testing: references/testing.md
What ships with it
7 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.
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 · 66 lines · 83 tokens per session scan A 287cd7e6800e
mavericks-mvi is a skill published in the GitHub repository ujffdi/mavericks-mvi-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 1,052 once invoked, about $0.0004 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
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kmp-lsp
Kotlin/Java/Swift LSP server for code navigation in Android and iOS codebases. Use when navigating Kotlin, Java, or Swift source files: finding class definitions, listing symbols, jumping to implementations, finding all usages, checking type signatures, or switching workspace between projects. Triggers for: "find this…
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
kotlin-expert
Expert-level Kotlin development, Android, coroutines, and multiplatform. Use when the user mentions Android, coroutines, multiplatform, or JVM, or when the task involves Kotlin Fundamentals, Android Development, Kotlin Multiplatform, or Kotlin Style.