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 RoninForge/roninforge-kotlin-compose --skill compose-validategit clone --depth 1 https://github.com/RoninForge/roninforge-kotlin-composeWrote 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/roninforge/roninforge-kotlin-compose/compose-validate)<a href="https://agentmods.dev/skills/roninforge/roninforge-kotlin-compose/compose-validate"><img src="https://agentmods.dev/badge/skills/roninforge/roninforge-kotlin-compose/compose-validate/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/roninforge/roninforge-kotlin-compose/compose-validate"><img src="https://agentmods.dev/badge/skills/roninforge/roninforge-kotlin-compose/compose-validate.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 | $0.00067 | $0.01358 |
| Opus 5.5 | $0.00027 | $0.00543 |
| Sonnet 5.5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
compose-validate 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 1mo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Compose / Kotlin Codebase
When to Use
When auditing AI-generated Android code, reviewing a migration to Compose, or preparing a codebase for shipping.
Instructions
Run each grep against the project root. Each hit is a candidate; review case by case.
View-system leak
# findViewById in a Compose-based module
grep -rn 'findViewById' --include='*.kt' .
# Activity using setContentView(R.layout
grep -rn 'setContentView(R\.layout' --include='*.kt' .
# Android Views imports leaking into Compose code
grep -rnE 'import android\.widget\.(TextView|Button|ImageView|EditText)' --include='*.kt' .
# XML layout files for new screens (audit each: is this in active use?)
find . -name '*.xml' -path '*/res/layout/*'
Material 2 leak
# Material 2 imports in a Material 3 project
grep -rnE 'import androidx\.compose\.material\.[A-Z]' --include='*.kt' .
# Material 2 dependency in build files
grep -rn 'androidx.compose.material:material' --include='*.gradle*' .
Coroutine misuse
grep -rn 'GlobalScope\.' --include='*.kt' .
grep -rnE 'runBlocking\s*\{' --include='*.kt' .
Null safety
# Force-unwrap operator (audit every match)
grep -rn '!!' --include='*.kt' .
!! has legitimate uses but they are rare. Most matches should be ?: / requireNotNull / scoped ?.let.
State / Compose hygiene
# LaunchedEffect with sentinel key
grep -rnE 'LaunchedEffect\(\s*(true|Unit)\s*\)' --include='*.kt' .
# Public MutableStateFlow (no leading _)
grep -rnE '(public\s+|^\s*)val\s+\w+\s*:\s*MutableStateFlow' --include='*.kt' .
grep -rnE '(public\s+|^\s*)val\s+\w+\s*=\s*MutableStateFlow' --include='*.kt' .
# LazyColumn / LazyRow without key
grep -rnE 'items\(\s*\w+\s*\)\s*\{' --include='*.kt' .
# collectAsState without WithLifecycle
grep -rn 'collectAsState(' --include='*.kt' . | grep -v 'WithLifecycle'
# Composables named lowercase
grep -rnE '@Composable\s*$' --include='*.kt' . -A 1 | grep -E 'fun\s+[a-z]'
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.
- 1mo ago First seen · 163 lines · 67 tokens per session scan A c365d6f8fd94
compose-validate is a skill published in the GitHub repository RoninForge/roninforge-kotlin-compose (1 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,358 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.
Other skills, from other repositories
compose-feature
Adds, changes, or reviews a screen, sheet, dialog, or destination slice (endpoint to repository to ViewModel to UI to navigation to DI to tests) in a Compose or CMP project. Use when adding a screen, building a new feature, adding a ViewModel or destination, wiring list/detail or a form screen, scaffolding a slice, or…
compose-platform
Owns platform splits for Compose Multiplatform apps: places declarations in commonMain, chooses expect/actual vs interface plus DI, wires host adapters and ports, and validates iOS/Swift interop, desktop and web targets, and platform lifecycle. Use when touching commonMain, expect, actual, iosMain, Swift, SKIE, Flow…
Appium Mobile Testing
Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.
Espresso Android Testing
Android UI testing with Espresso framework including view matchers, actions, assertions, idling resources, and RecyclerView testing patterns.
compose-architecture
Use when writing, changing or reviewing code that touches the house contract for Jetpack Compose and Compose Multiplatform apps: module graph, MVI/BaseViewModel, error tiers, state ownership, naming, Koin DI, Navigation 3 and coroutines. The compose skill is the entry point. Do NOT use for Gradle-only work…
compose-project
Owns project and build-level work for Compose and Compose Multiplatform apps: bootstrapping a new project, adopting the kit in an existing project, adding or extracting a module, convention plugins in build-logic, the version catalog, and CI plus agent hooks. Use when starting a Compose Multiplatform app, adding a…