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 5.5 | $0.00033 | $0.00421 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo 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 5mo ago), licensed MIT. It adds 83 tokens to every session and 1,052 once invoked, about $0.0003 per session on Opus 5.5. 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.
mavericks-mvi compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mavericks-mviujffdi/mavericks-mvi-skills | Skill | 3 | 5mo ago | MIT | A | 83 | Claude Code, Codex |
| compose-animationschrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 64 | Claude Code |
| compose-focus-navigationchrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 41 | Claude Code |
| kotlin-androidericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 78 | Claude Code, Codex |
| compose-multiplatformericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 80 | Claude Code, Codex |
| kmp-lspHessesian/kmp-lsp | Skill | 207 | 2d ago | MIT | A | 114 | Claude Code, Codex |
| kotlin-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 55 | Claude Code |