rule-create

rule-create is a cursor rule for Cursor from oakensoul/nextjs-cursor-prompts. It costs 0 tokens per session (1,797 once invoked), scanned A, original, MIT.

A guide for creating Cursor rules, which are standing instructions that shape how an AI coding agent works in a project.

In plain words
What is it for?
Use it to decide which constraints deserve permanent rules, combine related guidance, and avoid rules better suited to one-off prompts.
Why use it?
It helps keep rules focused and consistent, reducing duplicated, conflicting, or overly specific instructions that an agent may ignore.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/oakensoul/nextjs-cursor-prompts/rule-create
Clone the repo
git clone --depth 1 https://github.com/oakensoul/nextjs-cursor-prompts

Made for: Cursor.

Wrote 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.

agentmods badge for rule-create

README.md
[![agentmods](https://agentmods.dev/badge/rules/oakensoul/nextjs-cursor-prompts/rule-create.svg)](https://agentmods.dev/rules/oakensoul/nextjs-cursor-prompts/rule-create)
Your own site
<a href="https://agentmods.dev/rules/oakensoul/nextjs-cursor-prompts/rule-create"><img src="https://agentmods.dev/badge/rules/oakensoul/nextjs-cursor-prompts/rule-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,797 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01797
Opus 5 $0.00000 $0.00898
Sonnet 5 $0.00000 $0.00359
Haiku 4.5 $0.00000 $0.00180

Measured 5d ago against content hash a46ad1238b8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rule-create 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 5d 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.

.cursor/prompts/prompt-engineering/rule-create.mdc · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rule Creation and Composition Guide

You are an expert at creating effective Cursor rules that agents will consistently follow. Your goal is to design well-composed, strategic rules that provide clear constraints without overwhelming the agent with too many directives.

🎯 CORE PRINCIPLE: COMPOSITION OVER PROLIFERATION

CRITICAL INSIGHT: Agents tend to ignore or inconsistently apply rules when there are too many. Create fewer, more comprehensive rules rather than many small ones.

Rule Composition Strategy:

  • Combine related constraints into single, cohesive rules
  • Group by context (e.g., all security constraints in one rule)
  • Integrate methodology with specific constraints
  • Avoid overlapping rules that could conflict or confuse

🚫 AVOID CREATING RULES FOR:

  • Simple preferences that could be stated in a prompt
  • One-time constraints specific to a single task
  • Basic coding practices already covered by existing rules
  • Overly specific scenarios that rarely apply
  • Contradictory directives that conflict with existing rules

CREATE RULES FOR:

  • Cross-cutting constraints that apply to multiple types of work
  • Methodological approaches (how to do work, not what to do)
  • Risk mitigation patterns that prevent common mistakes
  • Quality gates that ensure consistent standards
  • Architectural principles that guide system design

📋 RULE ANALYSIS PROCESS:

Before creating a new rule, analyze the request:

1. Necessity Assessment

QUESTION: Is this truly a rule or could it be handled by:
- Existing rules applied more specifically?
- A prompt modification instead?
- Project-specific guidance in /project/?
- Documentation rather than enforcement?

DECISION CRITERIA:
✅ Create rule if: Applies broadly, enforces methodology, prevents risk
❌ Don't create if: One-time use, already covered, too specific

2. Composition Opportunities

QUESTION: Could this be combined with existing rules?
- Does it relate to code safety? → Consider merging with code-change-minimal.mdc
- Is it about quality? → Could enhance existing quality rules
- Does it address architecture? → Might fit with architectural guidelines

COMPOSITION BENEFITS:
- Reduces cognitive load on agents
- Ensures related constraints work together
- Eliminates potential conflicts
- Creates more powerful, cohesive guidance

Read the full file on GitHub · 248 lines

Changes

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.

  1. 5d ago First seen · 248 lines · 0 tokens per session scan A a46ad1238b8d

Subscribe to this mod's changes

rule-create is a cursor rule published in the GitHub repository oakensoul/nextjs-cursor-prompts (4 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,797 tokens. 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 2026-08-31.