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 new-silvermoon/awesome-android-agent-skills --skill compose-performance-auditgit clone --depth 1 https://github.com/new-silvermoon/awesome-android-agent-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/new-silvermoon/awesome-android-agent-skills/compose-performance-audit)<a href="https://agentmods.dev/skills/new-silvermoon/awesome-android-agent-skills/compose-performance-audit"><img src="https://agentmods.dev/badge/skills/new-silvermoon/awesome-android-agent-skills/compose-performance-audit/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/new-silvermoon/awesome-android-agent-skills/compose-performance-audit"><img src="https://agentmods.dev/badge/skills/new-silvermoon/awesome-android-agent-skills/compose-performance-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00042 | $0.01570 |
| Opus 5.5 | $0.00017 | $0.00628 |
| Sonnet 5.5 | $0.00008 | $0.00314 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
compose-performance-audit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- compose-performance-audit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Performance Audit
Overview
Audit Jetpack Compose view performance end-to-end, from instrumentation and baselining to root-cause analysis and concrete remediation steps.
Workflow Decision Tree
- If the user provides code, start with "Code-First Review."
- If the user only describes symptoms, ask for minimal code/context, then do "Code-First Review."
- If code review is inconclusive, go to "Guide the User to Profile" and ask for Layout Inspector output or Perfetto traces.
1. Code-First Review
Collect:
- Target Composable code.
- Data flow: state, remember, derived state, ViewModel connections.
- Symptoms and reproduction steps.
Focus on:
- Recomposition storms from unstable parameters or broad state changes.
- Unstable keys in
LazyColumn/LazyRow(keychurn, missing keys). - Heavy work in composition (formatting, sorting, filtering, object allocation).
- Unnecessary recompositions (missing
remember, unstable classes, lambdas). - Large images without proper sizing or async loading.
- Layout thrash (deep nesting, intrinsic measurements,
SubcomposeLayoutmisuse).
Provide:
- Likely root causes with code references.
- Suggested fixes and refactors.
- If needed, a minimal repro or instrumentation suggestion.
2. Guide the User to Profile
Explain how to collect data:
- Use Layout Inspector in Android Studio to see recomposition counts.
- Enable Recomposition Highlights in Compose tooling.
- Use Perfetto or System Trace for frame timing analysis.
- Check Macrobenchmark results for startup/scroll metrics.
Ask for:
- Layout Inspector screenshot showing recomposition counts.
- Perfetto trace or System Trace export.
- Device/OS/build configuration (debug vs release).
Important: Ensure profiling is done on a release build with R8 enabled. Debug builds have significant overhead.
3. Analyze and Diagnose
Prioritize likely Compose culprits:
- Recomposition storms from unstable parameters or broad state changes.
- Unstable keys in lazy lists (
keychurn, index-based keys). - Heavy work in composition (formatting, sorting, object allocation).
- Missing
remembercausing recreations on every recomposition. - Large images without
Modifier.size()constraints. - Unnecessary state reads in wrong composition phases.
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 · 200 lines · 42 tokens per session scan A 499fb01cd910
compose-performance-audit is a skill published in the GitHub repository new-silvermoon/awesome-android-agent-skills (1,000 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,570 once invoked, about $0.0002 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 2026-08-30.
compose-performance-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compose-performance-auditnew-silvermoon/awesome-android-agent-skills | Skill | 1.0k | 3mo ago | Apache-2.0 | A | 42 | Claude Code, Codex |
| ios-fixgarrytan/gstack | Skill | 140k | yesterday | MIT | A | 15 | Claude Code |
| node-connectopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 39 | Claude Code, Codex |
| google-mobile-ads-validategoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 84 | Claude Code, Codex |
| jetpack-compose-performanceandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 41 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| swiftui-performance-auditsteipete/agent-scripts | Skill | 7.5k | 7d ago | MIT | A | 24 | Claude Code, Codex |