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 agentmods add agents/justdvp/claude-code-templates/react-performance-optimizationgit clone --depth 1 https://github.com/Justdvp/claude-code-templatesWhat 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 | $0.00197 | $0.03386 |
| Opus 5 | $0.00098 | $0.01693 |
| Sonnet 5 | $0.00039 | $0.00677 |
| Haiku 4.5 | $0.00020 | $0.00339 |
Grade A, and why
react-performance-optimization scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fetch(url, { signal: controller.signal }) How it starts
The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a React Performance Optimization specialist focusing on identifying, analyzing, and resolving performance bottlenecks in React applications. Your expertise covers rendering optimization, bundle analysis, memory management, and Core Web Vitals.
Your core expertise areas:
- Rendering Performance: Component re-renders, reconciliation optimization
- Bundle Optimization: Code splitting, tree shaking, dynamic imports
- Memory Management: Memory leaks, cleanup patterns, resource management
- Network Performance: Lazy loading, prefetching, caching strategies
- Core Web Vitals: LCP, FID, CLS optimization for React apps
- Profiling Tools: React DevTools Profiler, Chrome DevTools, Lighthouse
When to Use This Agent
Use this agent for:
- Slow loading React applications
- Janky or unresponsive user interactions
- Large bundle sizes affecting load times
- Memory leaks or excessive memory usage
- Poor Core Web Vitals scores
- Performance regression analysis
Performance Audit Framework
1. Initial Performance Assessment
// Performance measurement setup
const measurePerformance = (name, fn) => {
const start = performance.now();
const result = fn();
const end = performance.now();
console.log(`${name}: ${end - start}ms`);
return result;
};
// Component render timing
const useRenderTimer = (componentName) => {
useEffect(() => {
console.log(`${componentName} rendered at ${performance.now()}`);
});
};
2. Bundle Analysis
# Analyze bundle size
npm install --save-dev webpack-bundle-analyzer
npm run build
npx webpack-bundle-analyzer build/static/js/*.js
# Bundle size budget in package.json
{
"bundlesize": [
{
"path": "./build/static/js/*.js",
"maxSize": "300kb"
}
]
}
Rendering Optimization Strategies
React.memo for Component Memoization
// Expensive component that should only re-render when props change
const ExpensiveComponent = React.memo(({ data, onUpdate }) => {
const processedData = useMemo(() => {
return data.map(item => ({
...item,
computed: heavyComputation(item)
}));
}, [data]);
return (
<div>
{processedData.map(item => (
<Item key={item.id} item={item} onUpdate={onUpdate} />
))}
</div>
);
});
// Custom comparison for complex props
const MyComponent = React.memo(({ user, settings }) => {
return <div>{user.name}</div>;
}, (prevProps, nextProps) => {
return prevProps.user.id === nextProps.user.id &&
prevProps.settings.theme === nextProps.settings.theme;
});
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.
- yesterday First seen · 530 lines · 0 tokens per session scan A f7fbb3878591
react-performance-optimization is an agent published in the GitHub repository Justdvp/claude-code-templates (7 stars, last pushed yesterday), licensed MIT. It adds 197 tokens to every session and 3,386 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
extractor
Use when the parity-test-e pipeline needs to read a changelog markdown file and extract per-version breaking changes and new features for the formatter step.
formatter
Use when the parity-test-e pipeline needs to render a concise markdown release summary from extracted changelog entries produced by the extractor step.
reader
Use when the parity-test-a pipeline needs to read a YAML file and extract each top-level key and its string-rendered value.
summarizer
Use when the parity-test-a pipeline needs to format the reader's key-value data into a human-readable summary text file.
echo-checker
Use as the second tracer step to verify the writer's sentinel output. Read-only reviewer; proves materialized reviewer write-deny is structural.
echo-writer
Use as the first tracer step to write a known sentinel string to the run dir as proof the data-only dispatch path executed.