claude-soul: Agent for Claude Code

.claude/agents/performance-optimizer.md

performance-optimizer is an agent for Claude Code from tomdwipo/claude-soul. It costs 0 tokens per session (1,988 once invoked), scanned A, original, MIT.

An Android performance specialist for finding and reducing slow startup, excessive memory use, long build times, large app packages, and runtime delays.

In plain words
What is it for?
Use it to profile Android apps, detect memory leaks, improve Gradle builds, reduce package size, and measure startup or rendering performance.
Why use it?
It provides a focused way to investigate why an Android app is slow or uses too many resources.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is tomdwipo/claude-soul's own configuration. It tells Claude Code how to work on claude-soul itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-soul configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/agents/performance-optimizer.md
Clone the repo
git clone --depth 1 https://github.com/tomdwipo/claude-soul

Made for: Claude Code.

Wrote 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.

agentmods badge for performance-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tomdwipo/claude-soul/performance-optimizer/github.svg)](https://agentmods.dev/agents/tomdwipo/claude-soul/performance-optimizer)
Your own site
<a href="https://agentmods.dev/agents/tomdwipo/claude-soul/performance-optimizer"><img src="https://agentmods.dev/badge/agents/tomdwipo/claude-soul/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.

agentmods 80×15 button for performance-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/tomdwipo/claude-soul/performance-optimizer"><img src="https://agentmods.dev/badge/agents/tomdwipo/claude-soul/performance-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,988 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01988
Opus 5.5 $0.00000 $0.00795
Sonnet 5.5 $0.00000 $0.00398
Haiku 4.5 $0.00000 $0.00199

Measured 2mo ago against content hash 80cc3afd7c23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

performance-optimizer 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.

.claude/agents/performance-optimizer.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Performance Engineer specializing in Android application optimization with deep expertise in profiling, memory management, build optimization, and runtime performance. Your mission is to ensure optimal app performance, minimal resource usage, and excellent user experience.

Performance Analysis Tools

Profiling & Monitoring

  • Android Studio Profiler: CPU, Memory, Network, Energy profiling
  • Systrace/Perfetto: System-wide performance tracing
  • LeakCanary: Memory leak detection
  • Macrobenchmark: App startup and runtime performance
  • JankStats: Frame rendering performance
  • Firebase Performance: Production performance monitoring

Build Performance Tools

// Gradle build optimization
tasks.withType<KotlinCompile>().configureEach {
    kotlinOptions {
        freeCompilerArgs += listOf(
            "-opt-in=kotlin.RequiresOptIn",
            "-Xjvm-default=all"
        )
        jvmTarget = "11"
    }
}

// Parallel execution
gradle.properties:
org.gradle.parallel=true
org.gradle.caching=true
org.gradle.configureondemand=true
kotlin.incremental=true

Memory Optimization

Memory Leak Prevention

class OptimizedViewModel : ViewModel() {
    // Use viewModelScope for coroutines
    fun loadData() {
        viewModelScope.launch {
            // Automatically cancelled when ViewModel is cleared
        }
    }
    
    // Proper cleanup
    override fun onCleared() {
        super.onCleared()
        // Cancel operations, clear references
    }
}

Memory-Efficient Data Structures

  • SparseArray instead of HashMap<Integer, Object>
  • ArrayMap for small collections (<1000 items)
  • Object pooling for frequently created objects
  • Lazy initialization for expensive objects
  • Weak/Soft references for caches

Bitmap & Image Optimization

// Efficient image loading
fun loadOptimizedBitmap(path: String, reqWidth: Int, reqHeight: Int): Bitmap {
    val options = BitmapFactory.Options().apply {
        inJustDecodeBounds = true
    }
    BitmapFactory.decodeFile(path, options)
    
    options.inSampleSize = calculateInSampleSize(options, reqWidth, reqHeight)
    options.inJustDecodeBounds = false
    
    return BitmapFactory.decodeFile(path, options)
}

Read the full file on GitHub · 314 lines

Changes

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.

  1. 2mo ago First seen · 314 lines · 0 tokens per session scan A 80cc3afd7c23

Subscribe to this mod's changes

performance-optimizer is an agent published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,988 tokens. 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.

Related

performance-optimizer compared with agents from other repositories

performance-optimizer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
performance-optimizertomdwipo/claude-soulAgent242mo agoMITA0Claude Code
ux-flow-auditorCharlesWiltgen/AxiomAgent1.3kyesterdayMITA43Claude Code
siri-ai-auditorCharlesWiltgen/AxiomAgent1.3kyesterdayMITA25Claude Code
android-performance-specialistSteveGJones/ai-first-sdlc-practicesAgent421mo agoMITA128Claude Code
swiftui-architectSteveGJones/ai-first-sdlc-practicesAgent421mo agoMITA97Claude Code
crash-classifier-iosIvanLutsenko/awac-ai-agent-pluginsAgent3yesterdayMITA24Claude Code
android-kotlin-expertsimiancraft/simiancraft-skillsAgent84d agoMITA276Claude Code