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/goranerhartic/cursor-development-rules/rule-indexgit clone --depth 1 https://github.com/GoranErhartic/cursor-development-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/goranerhartic/cursor-development-rules/rule-index)<a href="https://agentmods.dev/rules/goranerhartic/cursor-development-rules/rule-index"><img src="https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/rule-index.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.01380 |
| Opus 5 | $0.00020 | $0.00690 |
| Sonnet 5 | $0.00008 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
rule-index 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 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.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule Index
Use this index when you need to discover which rules exist for a given stack or topic. Each router file is the table of contents for that stack; read the router first, then the specific rule files it points to.
Quick Decision Tree
- Need first-run guidance or fast navigation? ->
QUICK_START.mdc - Need stack-specific implementation guidance? -> open the matching stack router below
- Need cross-cutting concepts (testing/security/architecture)? -> use
patterns/* - Need workflow/process guidance (TDD/review/onboarding)? -> use
development/*
Always-Applied Rules (in every context)
| File | Purpose |
|---|---|
agent-behavior.mdc |
Persona, Never Assume, Rule Flagging; links to workflow/TDD/docs |
project-context.mdc |
Project-specific routing: active stacks, directory→router mapping, key deps; generated by onboarding |
Agent-requestable (request when needed): retrospective.mdc (end-of-task review, rule gaps, IMPROVEMENTS.md). See agent-behavior.mdc "See also".
Per-Stack Routers (glob-activated; read when working in that stack)
Each stack has one router that loads when matching files are open. All other rules in that stack are agent-requestable — the router lists them by task; load the 2–3 relevant to the current sub-task.
| Stack | Router File | When to Use |
|---|---|---|
| AWS Lambda / Node.js | languages/aws-lambda/nodejs-lambda.mdc |
Lambda functions, CDK, DynamoDB, SQS, SNS, API Gateway |
| Node.js / TypeScript (base) | languages/nodejs/nodejs-base.mdc |
Express, Fastify, NestJS, Hono; non-Lambda TS backends |
| Java / Spring Boot | languages/java/java-spring.mdc |
Spring Boot 3, JPA, Spring Security, Resilience4j |
| C# / .NET | languages/csharp/csharp-dotnet.mdc |
ASP.NET Core, EF Core, FluentValidation, Polly, Rebus |
| React / TypeScript | languages/react/react-frontend.mdc |
React 18+, TanStack Query, React Router v7, Tailwind |
Agent-Requestable Pattern & Workflow Rules
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 · 79 lines · 41 tokens per session scan A 16412e73fbc7
rule-index is a cursor rule published in the GitHub repository GoranErhartic/cursor-development-rules (19 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,380 once invoked, about $0.0002 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 2026-09-03.
Other cursor rules, from other repositories
project-structure
This document outlines the recommended project structure for the Atlan MCP server.
python
You are an AI assistant specialized in Python development. Your approach emphasizes.
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.