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 understanding-hot-reload-limitsgit 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/understanding-hot-reload-limits)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/understanding-hot-reload-limits"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/understanding-hot-reload-limits/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/understanding-hot-reload-limits"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/understanding-hot-reload-limits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 172 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00174 | $0.02422 |
| Opus 5 | $0.00087 | $0.01211 |
| Sonnet 5 | $0.00035 | $0.00484 |
| Haiku 4.5 | $0.00017 | $0.00242 |
Grade A, and why
understanding-hot-reload-limits 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 10d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding Hot Reload Limits: stay inside the fast path
Android Runtime (ART) enforces strict rules for class redefinition: a redefined class must have an identical schema (fields, method signatures, interfaces) as the previous version. Only method bodies are mutable at runtime. HotSwan automatically detects schema changes and falls back to a full incremental build, so failures are not silent. Knowing the boundary in advance is what keeps an iteration loop sub-second instead of multi-second.
When to use this skill
- The developer asks "why did this trigger a full rebuild?", "why isn't this hot reloading?", or "what does HotSwan support?".
- A PR review surfaces a refactor (parameter change, constructor change, interface extraction, new resource id) that would push a hot-reload session into a rebuild.
- The developer is planning a session and wants to order edits so the slow ones happen at the end.
- The developer reports an
inline funchange that "didn't reload" and is debugging.
When NOT to use this skill
- Setup or first-run troubleshooting. See
../setting-up-compose-hotswan/SKILL.md. - Pure state-preservation question (the reload happened but state was lost). See the state-preservation sibling skill.
- Configuration of the AI iteration loop or MCP server. See the AI-loop sibling skill.
Prerequisites
- HotSwan installed and verified per
../setting-up-compose-hotswan/SKILL.md(tool window statusWATCHING, body-only edit reloads in under one second). - Familiarity with the Kotlin compiler's distinction between method-body changes and class-schema changes.
Boundary tables
Hot-reloadable (no rebuild)
| Change | Notes |
|---|---|
| Composable function body | text, colors, modifiers, layout, control flow inside the function |
| Non-composable function body | ViewModel methods, mappers, utilities, repositories |
| Adding a new composable | same file or new file |
| Reordering composables | HotSwan 1.2.0+ |
| Resource value changes | strings.xml value, colors.xml value, dimens.xml value |
| Extension functions | including suspend, including vararg |
Adding data class properties |
API 30+ only |
| Numeric, string, float literal patches | compiled separately for fastest reload |
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.
- 10d ago First seen · 192 lines · 174 tokens per session scan A 07d592502380
understanding-hot-reload-limits is a skill published in the GitHub repository skydoves/compose-performance-skills (500 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 174 tokens to every session and 2,422 once invoked, about $0.0009 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.
deliver-android-feature
Implement an Android feature from a specification or acceptance criteria through architecture, production code, formatting, unit tests, JVM integration tests, local Compose behavior tests, screenshot matrices, managed-device integration tests, end-to-end coverage, and final verification. Use when adding or…