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 skydoves/compose-performance-skills --skill setting-up-compose-hotswangit clone --depth 1 https://github.com/skydoves/compose-performance-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/skydoves/compose-performance-skills/setting-up-compose-hotswan)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/setting-up-compose-hotswan"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/setting-up-compose-hotswan/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/skydoves/compose-performance-skills/setting-up-compose-hotswan"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/setting-up-compose-hotswan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00161 | $0.02872 |
| Opus 5 | $0.00081 | $0.01436 |
| Sonnet 5 | $0.00032 | $0.00574 |
| Haiku 4.5 | $0.00016 | $0.00287 |
Grade A, and why
setting-up-compose-hotswan 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 9d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting Up Compose HotSwan: zero to sub-second reload on a real device
Compose HotSwan is a JetBrains IDE plugin plus a Gradle compiler plugin that swaps changed Kotlin classes into a running Compose app on a real device or emulator in under one second, preserving navigation, scroll, and remember state. This skill installs both pieces, wires the canonical Gradle DSL with debugOnly = true, and verifies the first save-to-reload round-trip. Sibling skills cover what does and does not hot-reload (../understanding-hot-reload-limits/SKILL.md), state preservation across reloads, and the AI-driven iteration loop.
Versions verified at the time of authoring. Confirm against the current release notes for newer minors.
When to use this skill
- The developer mentions HotSwan, hot reload, instant UI update, "save and see", "no rebuild", live edit, or fast Compose iteration on device.
- The developer has the HotSwan JetBrains Marketplace plugin installed and asks how to apply the Gradle compiler plugin.
- A team is onboarding a new project to HotSwan and wants the canonical
libs.versions.toml+ root build + app build wiring. - The developer just installed the IDE plugin and the tool window status is stuck before
WATCHING.
When NOT to use this skill
- The question is about JetBrains' own Live Edit or Apply Changes features. HotSwan and those are separate products with different boundaries; do not conflate.
- The question is about Compose Preview rendering inside the IDE. HotSwan targets the running app on a real device or emulator, not preview canvases.
- The question is about which changes hot-reload vs force a rebuild. See
../understanding-hot-reload-limits/SKILL.md. - The question is about preserving complex state across reloads. See the state-preservation sibling skill (out of scope here).
Prerequisites
- Android Studio 2024.3+ or IntelliJ IDEA 2024.3+.
- Kotlin 2.0+ with the
org.jetbrains.kotlin.plugin.composeGradle plugin already applied on the Compose modules. - Gradle 8+.
- A real device or emulator with USB debugging enabled and visible to
adb devices. - The HotSwan IDE plugin installed from JetBrains Marketplace (https://plugins.jetbrains.com/plugin/30551-compose-hotswan/).
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.
- 9d ago First seen · 257 lines · 161 tokens per session scan A 25777e4b9a2a
setting-up-compose-hotswan is a skill published in the GitHub repository skydoves/compose-performance-skills (499 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 161 tokens to every session and 2,872 once invoked, about $0.0008 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.
Other skills, from other repositories
claude-android-ninja
Build and migrate Android apps with Kotlin, Jetpack Compose, MVVM, Hilt, Room 3 (KSP, SQLiteDriver, Flow/suspend DAOs), Navigation3, and multi-module Gradle. Use for new projects or modules, Compose screens and ViewModels, Room 3 and RemoteMediator, API 37 / targetSdk migration, Play Integrity client wiring…
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.
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).
compose-side-effects
Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection.
kotlin-multiplatform-expect-actual
Use when designing Kotlin Multiplatform expect/actual or interface boundaries for platform services, native SDKs, source sets, Compose Multiplatform UI, permissions, files, settings, sensors, or platform interop.