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 preserving-state-across-reloadsgit 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/preserving-state-across-reloads)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/preserving-state-across-reloads"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/preserving-state-across-reloads/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/preserving-state-across-reloads"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/preserving-state-across-reloads.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 | $0.00189 | $0.02627 |
| Opus 5 | $0.00095 | $0.01314 |
| Sonnet 5 | $0.00038 | $0.00525 |
| Haiku 4.5 | $0.00019 | $0.00263 |
Grade A, and why
preserving-state-across-reloads 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 11d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preserving State Across Reloads: keep edits inside HotSwan tier 1
Compose HotSwan applies every hot reload through three escalating tiers. Tier 1 (targeted recomposition) preserves the most: scroll position, navigation back stack, remember and rememberSaveable values, ViewModel state, lazy layout items, dialog and bottom sheet state. Tier 2 (composition reset) disposes and recreates compositions, dropping per-composable remember. Tier 3 (Activity.recreate()) restarts the Activity and only state held by ViewModel or SavedInstanceState survives.
The iteration loop is fastest and least surprising when every reload stays inside tier 1. This skill covers which edits trigger which tier, which state holders survive each tier, and how to hoist transient UI state when an edit must escalate.
When to use this skill
- The developer reports "scroll jumped to top after a hot reload", "lost dialog state", "lazy column re-fetched", or "tab selection reset to zero".
- The developer is about to refactor a composable and wants to know which recomposition scope the change touches.
- The HotSwan tool window status shows a tier 2 or tier 3 reload and the developer wants to understand why it escalated.
- The developer asks which state holders survive
Activity.recreate()versus a composition reset. - The user mentions "tier 1", "tier 2", "tier 3", "composition reset", "HotSwan state preservation", or "rememberSaveable across reload".
When NOT to use this skill
- The change was rejected as a schema violation entirely (added a parameter, changed a constructor, added a new resource ID) and HotSwan fell back to a full incremental build. See
../understanding-hot-reload-limits/SKILL.md. - HotSwan is not installed or the watcher is not running. See
../setting-up-compose-hotswan/SKILL.md. - The developer wants an AI agent to drive the loop autonomously. See
../iterating-with-ai-and-mcp/SKILL.md. - The recomposition itself is too wide independent of hot reload (a parent invalidating a whole subtree on every state tick). Diagnose with
../../recomposition/debugging-recompositions/SKILL.mdfirst.
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.
- 11d ago First seen · 193 lines · 189 tokens per session scan A be2f8009a07f
preserving-state-across-reloads is a skill published in the GitHub repository skydoves/compose-performance-skills (502 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 189 tokens to every session and 2,627 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-slot-api-pattern
Use when designing or reviewing a reusable Jetpack Compose component whose visual regions vary by caller, or when primitive content parameters and boolean shape flags are accumulating.
compose-state-deferred-reads
Use when Jetpack Compose code reads scroll, animation, gesture, or other frame-rate State in composition, passes changing values across composable boundaries, uses value-form layout/draw modifiers, or back-writes observable state from a later phase into one that's already run.
compose-state-hoisting
Use when deciding where Jetpack Compose UI element state or UI logic should live: local remember state, hoisted composable parameters, a plain state holder class, or a screen-level ViewModel/component.
collapsing-parallax-toolbar
Build a collapsing header from five siblings in one box — four sharing a single scroll state, one driven by a boolean instead — with artwork moved by a graphics layer at half the scroll rate, a title interpolated along a two-segment curve into the pinned bar, and a derived flip point that swaps the floating back…
empty-state-must-keep-its-navigation
Replace a populated header with an empty-state message without deleting the controls that header owned — re-supply them only in the branch that owned them, order the loading branch above the empty one, and stop reserving the artwork's height for a line of text. Use when a user reaches an empty period, filter or search…