Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sethdford/flowxnpx agentmods add rules/sethdford/flowx/performance-rulesWrote 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/rules/sethdford/flowx/performance-rules)<a href="https://agentmods.dev/rules/sethdford/flowx/performance-rules"><img src="https://agentmods.dev/badge/rules/sethdford/flowx/performance-rules/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/rules/sethdford/flowx/performance-rules"><img src="https://agentmods.dev/badge/rules/sethdford/flowx/performance-rules.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 | $0.00000 | $0.02572 |
| Opus 5.5 | $0.00000 | $0.01029 |
| Sonnet 5.5 | $0.00000 | $0.00514 |
| Haiku 4.5 | $0.00000 | $0.00257 |
Grade A, and why
performance-rules 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync, readFileSync } from 'fs'; How it starts
The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Rules: Stay 6x Faster Than Gemini CLI
🚨 PERFORMANCE KILLERS - NEVER DO THESE
Synchronous Operations (Gemini CLI Mistake)
// ❌ FORBIDDEN - Blocks event loop like Gemini CLI
import { execSync, readFileSync } from 'fs';
const result = execSync('command'); // Blocks everything
const content = readFileSync('file.txt'); // Blocks everything
// ✅ REQUIRED - Async operations
import { exec } from 'child_process';
import { readFile } from 'fs/promises';
const result = await exec('command');
const content = await readFile('file.txt');
Console Pollution (Gemini CLI Has 100+)
// ❌ FORBIDDEN - Slows down execution
console.log('debug info');
console.error('error details');
console.warn('warning message');
// ✅ REQUIRED - Use proper logging
import { logger } from '../utils/logger.js';
logger.debug('debug info');
logger.error('error details');
logger.warn('warning message');
Memory Leaks (Gemini CLI Pattern)
// ❌ FORBIDDEN - Memory leaks like Gemini CLI
let globalCache = new Map(); // Never cleaned up
setInterval(() => {}, 1000); // Never cleared
// ✅ REQUIRED - Proper cleanup
class CacheManager {
private cache = new Map();
private cleanupInterval: NodeJS.Timeout;
constructor() {
this.cleanupInterval = setInterval(() => this.cleanup(), 60000);
}
cleanup(): void {
this.cache.clear();
}
destroy(): void {
clearInterval(this.cleanupInterval);
this.cache.clear();
}
}
⚡ PERFORMANCE PATTERNS - ALWAYS USE THESE
1. Lazy Loading (Beat Gemini CLI Startup)
// ✅ REQUIRED - Lazy load heavy modules
async function getAIClient(): Promise<UnifiedClaudeClient> {
// Only import when needed
const { createUnifiedClient } = await import('../ai/unified-client.js');
return createUnifiedClient();
}
// ❌ WRONG - Heavy imports at startup like Gemini CLI
import { heavyModule } from './heavy-module.js'; // Slows startup
2. Efficient Data Structures
// ✅ REQUIRED - Use appropriate data structures
const userLookup = new Map<string, User>(); // O(1) lookup
const uniqueItems = new Set<string>(); // O(1) contains
// ❌ WRONG - Inefficient structures like Gemini CLI
const userLookup: User[] = []; // O(n) lookup
const uniqueItems: string[] = []; // O(n) contains check
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 · 394 lines · 0 tokens per session scan A 1f2742cf664e
performance-rules is a cursor rule published in the GitHub repository sethdford/flowx (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,572 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.