Create-Cursor-Rule

A guide for creating Cursor rule files, which are Markdown-based instructions that shape how Cursor’s AI works in a project. It covers the file’s layout, location, name, activation patterns, and instructions.

In plain words
What is it for?
Use it to gather rule requirements and draft a correctly structured .mdc file for a language, technology, task, or project-wide rule.
Why use it?
It helps avoid malformed or misplaced rule files and makes the intended behavior explicit before creating one.

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/thesethrose/devrules/create-cursor-rule
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/DevRules

Made for: Cursor.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 657 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 $0.00019 $0.00657
Opus 5 $0.00010 $0.00329
Sonnet 5 $0.00004 $0.00131
Haiku 4.5 $0.00002 $0.00066

Measured yesterday against content hash 9e81ee7ec7ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Create-Cursor-Rule 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.

.cursor/rules/tasks/Create-Cursor-Rule.mdc · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: Create Cursor Rule

You are assisting the user in creating a new Cursor rule (.mdc) file. Your goal is to generate a well-structured rule file adhering to the established project standards.

Process

  1. Gather Requirements: Ask the user for the following information:

    • Rule Purpose/Goal: What should this rule help the AI achieve or understand? (This will inform the description and main content).
    • Target Directory: Where should the new rule file be placed? (tasks/, languages/, technologies/, or root rules/?)
    • Proposed Filename: What should the .mdc file be named? (e.g., GoLang.mdc, Generate-Commit-Message.mdc).
    • Activation Globs: Which file patterns should automatically trigger this rule? (Provide examples like "**/*.go" or "*commit*"). If none, use "".
    • Always Apply?: Should this rule always be applied regardless of file context? (true or false, typically false unless it's a core rule modification).
    • Core Content Ideas: What key instructions, guidelines, or examples should be included in the rule body?
  2. Structure the Rule: Create the content for the new .mdc file using the standard format:

    • Header Block: Generate the YAML frontmatter with description, globs (comma-separated string), and alwaysApply based on user input.
    • Main Title: Use the rule's purpose or filename as the main # title.
    • Introduction: Briefly state the rule's objective.
    • Key Sections: Organize the core content using Markdown headings (##, ###), lists, and code blocks as appropriate (e.g., ## Guidelines, ## Best Practices, ## Examples).
  3. Generate the File Content: Provide the complete content for the new rule file within a single code block, ready for the user to save.

Formatting Requirements

  • Header: Must start with ---, contain description (quoted string), globs (quoted, comma-separated string), alwaysApply (boolean true/false), and end with ---.
  • Content: Use clear Markdown for structure and readability.

Read the full file on GitHub · 61 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. yesterday First seen · 61 lines · 19 tokens per session scan A 9e81ee7ec7ca

Subscribe to this mod's changes

Create-Cursor-Rule is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 19 tokens to every session and 657 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.