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/structuregit 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 | $0.00010 | $0.00641 |
| Opus 5 | $0.00005 | $0.00320 |
| Sonnet 5 | $0.00002 | $0.00128 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
structure 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 2d 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
-
Directory Organization: Source code in src/ directory. Compiled output in dist/ directory. Configuration files (package.json, tsconfig.json) at root. Documentation (README.md, LICENSE) at root. Use .cursor/rules/ for generated rules output.
- src/ ├── types.ts ├── analyzer.ts ├── rules-manager.ts ├── cli.ts └── index.ts
- dist/ (generated) .cursor/ rules/ (generated)
-
File Naming Conventions: Use kebab-case for file names: analyzer.ts, rules-manager.ts, cli.ts. Use descriptive names that indicate file purpose. Keep file names short but clear. Use .ts extension for TypeScript source files.
- analyzer.ts - cursor-agent integration
- rules-manager.ts - rules file management
- cli.ts - command-line interface
-
Module Structure: Each file should represent a single module with a clear responsibility. index.ts serves as the main entry point and re-exports public APIs. Group related functionality together. Keep modules focused and cohesive.
- index.ts - main API, re-exports types
- analyzer.ts - all cursor-agent interaction logic
- rules-manager.ts - all file system operations for rules
-
Import/Export Patterns: Use relative imports for local modules (./types, ./analyzer). Use absolute imports for node_modules. Export public API from index.ts. Keep internal implementation details private (don't export utility functions unless needed by other modules).
- import { generateRules } from './index';
- import { checkCursorAgent } from './analyzer';
- export * from './types';
-
Entry Points: index.ts is the main library entry point exporting public API. cli.ts is the CLI entry point (has shebang #!/usr/bin/env node). Package.json defines main (dist/index.js) and bin (dist/cli.js) entry points. Build script should set executable permissions on CLI (chmod +x dist/cli.js).
- // index.ts export async function generateRules(...) { }
- #!/usr/bin/env node // cli.ts import { Command } from 'commander';
- "scripts": { "build": "tsc && chmod +x dist/cli.js" }
-
Configuration Files: tsconfig.json at root with strict settings. package.json defines scripts, dependencies, and metadata. Keep configuration files at root level. Use standard naming conventions for config files.
- tsconfig.json - TypeScript compiler options
- package.json - npm/yarn package configuration
-
Type Definition Centralization: All TypeScript interfaces and types should be defined in types.ts. This provides a single source of truth for type definitions and makes them easily importable across modules.
- // types.ts export interface GenerateRulesConfig { ... } export interface AnalysisResult { ... }
- // Other files import { GenerateRulesConfig, AnalysisResult } from './types';
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.
- 2d ago First seen · 53 lines · 10 tokens per session scan A fd193abb1efe
structure is a cursor rule published in the GitHub repository Srajangpt1/agent-rule-sync (12 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 641 once invoked, about $0.0001 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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.