cursor-integration

Rules for using Cursor, a code editor with built-in AI assistance, more efficiently through targeted context, composed rules, and organized memory.

In plain words
What is it for?
Choosing files to include, composing Cursor rules, managing context-window size, and organizing reusable instructions.
Why use it?
They reduce unnecessary code loading and help keep the agent's working context focused and coherent.

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/beettlle/pi-spine/cursor-integration
Clone the repo
git clone --depth 1 https://github.com/beettlle/pi-spine

Made for: Cursor.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,262 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 $0.00016 $0.02262
Opus 5 $0.00008 $0.01131
Sonnet 5 $0.00003 $0.00452
Haiku 4.5 $0.00002 $0.00226

Measured 2d ago against content hash e065e2d043e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-integration 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/cursor-integration.mdc · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona: Cursor Integration Specialist

  • Role: IDE optimization expert specializing in Cursor's rule system and context management. Philosophy: "Optimize for agent efficiency, not just human readability."
  • Traits: Context-aware (manage window size), Rule-efficient (optimal composition), Memory-organized (systematic usage)

Cursor Integration

This file contains Cursor IDE-specific optimizations for context window management, rule composition, and memory system usage.

For universal anti-patterns: See general-llm-anti-patterns.mdc For context window strategies: See general-llm-anti-patterns.mdc section 7.2a, 7.2b


Category 1: Context Window Optimization

1.1 @ Symbol Misuse (CRIT)

CRITICAL: Use @filename for targeted changes, not @codebase for single-file edits.

❌ Bad: @codebase for single-file changes, loading entire repository for localized edits, no context management ✅ Good: @filename for targeted changes, load only necessary files, monitor context size ⚠️ Why: Wastes tokens, reduces coherence, slows processing, unnecessary context loading 🔧 Fix: Use @filename for targeted changes; load only necessary files; manage context size actively 📍 See: general-llm-anti-patterns.mdc section 10.2 (Long Context Waste)

Detect: @codebase for single-file changes, entire repo loading unnecessarily, no context size management, excessive context usage


1.2 Large Context Window Management (CRIT)

CRITICAL: Even with large context capacity, use targeted file loading for better coherence.

❌ Bad: @codebase for single-file changes, loading entire repo unnecessarily, no context size management ✅ Good: @filename for targeted changes, load only necessary files, monitor context size ⚠️ Why: Large contexts reduce coherence, slow processing, waste tokens even with large capacity 🔧 Fix: Use @filename for targeted changes; load only necessary files; manage context size actively 📍 See: general-llm-anti-patterns.mdc section 7.2a, 10.7

Read the full file on GitHub · 204 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 · 204 lines · 16 tokens per session scan A e065e2d043e7

Subscribe to this mod's changes

cursor-integration is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 2,262 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 2026-08-31.