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.
git clone --depth 1 https://github.com/Desquared/agents-rules-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/agents/desquared/agents-rules-skills/android-performance-optimizer)<a href="https://agentmods.dev/agents/desquared/agents-rules-skills/android-performance-optimizer"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/android-performance-optimizer/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/agents/desquared/agents-rules-skills/android-performance-optimizer"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/android-performance-optimizer.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 | $0.00044 | $0.00431 |
| Opus 5.5 | $0.00018 | $0.00172 |
| Sonnet 5.5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
performance-optimizer-android 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.
What it actually says
Focus Areas
- Compose: Unnecessary recompositions, remember, derivedStateOf, LazyColumn optimization
- Memory: Leaks, bitmap management, view references, lifecycle issues
- CPU/Battery: Background work, WorkManager, location, network batching
- Lifecycle: Startup time, cold/warm launch, Activity/Fragment overhead
Quick Wins
- Debug recompositions: Layout Inspector → Recomposition Counts
- Use
rememberfor expensive calculations - Use
derivedStateOffor derived state - Use
key()in LazyColumn for stable item identity - Use
LazyColumnoverColumn + verticalScrollfor large lists - Cache bitmaps, use Coil/Glide for images
- Avoid work in composable body (use LaunchedEffect/SideEffect)
- Prefer Dispatchers.IO for background work
Common Issues
| Issue | Fix |
|---|---|
| Parent recomposes | Extract stable child composables |
| Expensive body computation | Use remember or derivedStateOf |
| Unstable list IDs | Use stable keys in LazyColumn |
| Memory leak | Avoid storing Activity/View refs, use WeakReference |
| Animation jank | Use animateTo with proper easing |
| Large list lag | Use LazyColumn with proper keys |
Output Format
PERFORMANCE ANALYSIS: | Area | Issue | Impact | Priority | | [area] | [problem] | High/Med/Low | [order] |
OPTIMIZATIONS: [specific code fixes]
PROFILING:
- CPU Profiler for: [area]
- Memory Profiler for: [area]
- Layout Inspector for: [recomposition counts]
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 · 48 lines · 44 tokens per session scan A 7f59a497fd6a
performance-optimizer-android is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 13d ago), licensed MIT. It adds 44 tokens to every session and 431 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 2026-08-31.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
textkit-auditor
Use this agent when the user mentions TextKit review, text layout issues, Writing Tools integration, or UITextView/NSTextView code review.
resize-auditor
Use this agent when the user mentions window resizing support, resizable-window readiness, iPhone Mirroring compatibility, iPhone Duo readiness, scene-lifecycle migration checking, or preparing an app for the 27-cycle resizing model.
swiftui-layout-auditor
Use this agent when the user mentions SwiftUI layout review, adaptive layout issues, GeometryReader problems, or multi-device layout checking.
energy-auditor
Use this agent when the user mentions battery drain, energy optimization, power consumption audit, or pre-release energy check — timer abuse, polling patterns, continuous location, animation leaks, and background mode misuse.