global

A set of general rules for a Cursor project, including where long-term project notes, technology rules, and feature-specific rules are stored. It also defines which files an agent should read first and how rules are applied.

In plain words
What is it for?
Use it to organize `.cursor` files, establish reading priorities, and guide how memory, feature rules, and technology-specific instructions are combined.
Why use it?
It gives the agent an order for loading project context and instructions, reducing the chance that important rules or current project information are missed.

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/hansonli05/cursor-rules-system/global
Clone the repo
git clone --depth 1 https://github.com/Hansonli05/Cursor-rules-system

Made for: Cursor.

Per session 2,251 This file is loaded in full into every session.
When invoked 2,251 The same file — it is already loaded in full.
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 $0.02251 $0.02251
Opus 5 $0.01125 $0.01125
Sonnet 5 $0.00450 $0.00450
Haiku 4.5 $0.00225 $0.00225

Measured 2d ago against content hash 047cdf026f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

global 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.

.cursor/rules/global.mdc · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

#Global Rules

Purpose: Defines cross-cutting rules and instructions that apply to all AI-assisted development in this project.

1. Folder Structure Protocol

The .cursor/ directory contains a hierarchical rule system with three interdependent domains:

  • memory-bank/ - Long-term context and project intelligence (strategic decisions, progress tracking)
  • tech-stack/ - Tech-specific coding patterns and constraints (implementation guidance)
  • feature-rules/ - Rules for individual features (reusable logic, feature-specific patterns)

Essential Reading Order

AI should prioritize reading these files at the start of every task:

  1. memory-bank/activeContext.mdc - Current work focus and session goals
  2. memory-bank/progress.mdc - What works, what's left to build
  3. cursor-memory-bank.mdc - Memory Bank operation instructions

2. Rule Execution Hierarchy

When performing any task, Cursor must follow this sequence:

flowchart TD
    Start[Task Begins] --> MB[Read Memory Bank Core]
    MB --> Feature[Identify Current Feature]
    Feature --> LoadFR[Load feature-rules/*.md]
    LoadFR --> Tech[Determine Technologies]
    Tech --> LoadTS[Load tech-stack/*.md] 
    LoadTS --> Arch[Reference systemPatterns.md]
    Arch --> Execute[Execute Task]
    Execute --> Update[Update Documentation]

Execution Steps:

  1. Read memory-bank/activeContext.mdc and progress.mdc
  2. Identify the current feature and load its corresponding feature-rules/*.md
  3. Determine relevant technologies and load corresponding tech-stack/*.md
  4. Reference memory-bank/systemPatterns.mdc for architectural consistency
  5. Check for conflicts: Verify no conflicting logic exists across rule domains before proceeding
  6. Follow fallback logic:
    • If no rule exists, ask for clarification or document the new pattern
    • Update appropriate .md files once confirmed

3. Integrated Rule Domains

The .cursorrules/ system is composed of three interdependent rule domains:

Read the full file on GitHub · 240 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. 2d ago First seen · 240 lines · 2,251 tokens per session scan A 047cdf026f87

Subscribe to this mod's changes

global is a cursor rule published in the GitHub repository Hansonli05/Cursor-rules-system (2 stars, last pushed 1y ago), licensed MIT. It adds 2,251 tokens to every session, about $0.0113 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 2026-08-31.