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 rules/srajangpt1/agent-rule-sync/conventionsgit clone --depth 1 https://github.com/Srajangpt1/agent-rule-syncWhat 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 | $0.01446 | $0.01446 |
| Opus 5 | $0.00723 | $0.00723 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
conventions 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
-
Error Handling: Always check for errors using instanceof Error before accessing error properties. Use instanceof Error before accessing .message. Return error objects with success: false and error message string. Log errors appropriately based on context (console.error for CLI, return error for library API).
- catch (error) { return { success: false, error: error instanceof Error ? error.message : 'Unknown error occurred', }; }
- process.on('error', (err) => { resolve({ installed: false, error: err.message, }); });
-
Async/Await Usage: Always use async/await for asynchronous operations, never Promise chains (.then/.catch). Make async functions return Promise with explicit type. Use try-catch blocks for error handling in async functions. Wrap callback-based APIs (like spawn) in Promise constructors.
- export async function generateRules(config: GenerateRulesConfig = {}): Promise { try { const result = await analyzeCodebase({ verbose }); // ... } catch (error) { // handle error } }
- export async function checkCursorAgent(): Promise { return new Promise((resolve) => { // callback-based logic }); }
-
Function Organization: Export functions at module level. Group related functions together. Use helper functions to break down complex logic. Keep functions focused on a single responsibility. Document exported functions with JSDoc comments.
- export async function generateRules(...) { }
- export async function checkAgent() { }
- export async function analyze(...) { }
- function createAnalysisPrompt(): string { }
- function parseRawOutput(rawOutput: string): AnalysisData | null { }
-
TypeScript Type Usage: Define interfaces for all data structures. Use optional properties (?) for values that may be undefined. Use explicit return types on all exported functions. Use union types for literal value sets. Avoid any type, use unknown if type is truly unknown.
- export interface AnalysisResult { success: boolean; data?: AnalysisData; error?: string; rawOutput?: string; }
- ruleType?: 'always' | 'auto-attached' | 'agent-requested' | 'manual';
- export async function generateRules(config: GenerateRulesConfig = {}): Promise
-
Default Parameters: Use default parameters for optional configuration options. Provide sensible defaults. Use object destructuring with defaults in function parameters.
- export async function generateRules(config: GenerateRulesConfig = {}): Promise
- export async function analyzeCodebase(options: AnalyzeOptions = {}): Promise { const { timeout = 300000, verbose = false } = options; }
- export async function analyze(verbose: boolean = false): Promise
-
Result Objects: Use result objects with success boolean and additional data/error fields for function returns. This pattern allows for consistent error handling and data extraction. Include arrays for operation results (created, updated, unchanged).
- interface RulesManagerResult { success: boolean; created: string[]; updated: string[]; unchanged: string[]; error?: string; }
- return { success: true, created: ['file1.mdc'], updated: [], unchanged: [], };
-
Verbose Logging Pattern: Accept verbose boolean parameter for detailed logging. Check verbose flag before logging detailed information. Use console.log for verbose output, console.error for errors. Provide helpful progress messages during long operations. For large outputs, truncate and show length/preview.
- if (verbose) {
console.log(
Using cursor-agent: ${agentCheck.version}); } - if (verbose && analysisResult.success && analysisResult.data) { console.log('Analysis successful, data received'); }
- if (analysisResult.rawOutput.length < 500) { console.log('Raw output:', analysisResult.rawOutput); } else { console.log('Raw output (first 500 chars):', analysisResult.rawOutput.substring(0, 500)); }
- if (verbose) {
console.log(
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.
- 3d ago First seen · 139 lines · 1,446 tokens per session scan A 77a819cadc75
conventions is a cursor rule published in the GitHub repository Srajangpt1/agent-rule-sync (12 stars, last pushed 5mo ago), licensed MIT. It adds 1,446 tokens to every session, about $0.0072 per session on Opus 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.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.