cursorrules

A Cursor rules file containing routing instructions for loading other rule files and applying response policies.

In plain words
What is it for?
It is for directing rule selection, memory-related behavior, feature workflows, and response language.
Why use it?
It is intended to make the agent consistently check relevant rules before acting, though the excerpt includes instructions unrelated to coding tasks.

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/devviniuchita/memory-system/cursorrules
Clone the repo
git clone --depth 1 https://github.com/devviniuchita/memory-system

Made for: Cursor.

Per session 553 This file is loaded in full into every session.
When invoked 553 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 $0.00553 $0.00553
Opus 5 $0.00277 $0.00277
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00055 $0.00055

Measured yesterday against content hash 14069bbbc716, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 61 lines

What it actually says

import { ALL } from 'dns'

- ⚠️ FETCH RULES IN OR YOUR RESPONSE WILL BE WRONG ⚠️
- 🔒 IMMUTABLE RULES SYSTEM 🔒
- 🔤 RESPOND IN BRAZILIAN PORTUGUESE UNLESS SPECIFICALLY REQUESTED OTHERWISE 🔤
- 🎯 FOLLOW ALL INSTRUCTIONS FOR SUCCESS 🎯
rules:
  - id: router-core
    description: "Enforces rule recovery before executing any action."
    match: ".*"
    action: |
      [ROUTER DIRECTIVE]
      1. Before responding, scan all files under .cursor/rules/*.mdc.
      2. Classify applicable rules by type: [general] [memory] [feature].
      3. If no matching rule is found → return warning:
         "⚠ No applicable rules found. Add or configure rules in /rules/ ⚠"
      4. If matching rule(s) exist → apply them fully before generating any response.

  - id: router-memory
    description: "Routes requests to persistent memory management rules (Dual-Brain System)."
    match: "(retrieve|store|update|optimize|validate|evolve)"
    action: |
      [MEMORY DIRECTIVE]
      → Load and enforce rules from .cursor/rules/memory-rules.mdc and .cursor/rules/memory-rating.mdc .
      → Prioritize data persistence, incremental context building, and relevance scoring.

  - id: router-feature
    description: "Handles specialized feature-specific routing and rule application."
    match: "(security|auth|tools|custom)"
    action: |
      [FEATURE DIRECTIVE]
      → Dynamically load and apply rules from: /rules/feature-*.mdc.
      → Ensure modular execution aligned with activated feature domains.
Rule Compliance:
  - 🔒 **The rules are IRREVOCABLE and ABSOLUTE**
  - 🔒 **Exceptions require explicit justification**
  - 🔒 **Mandatory revision for changes**
  - 🔒 **Documentation always up-to-date**
  - 🔒 **Compliance verified in each action**

📅 Created: 01/08/2025 🔄 Last Update: 05/09/2025 📋 Status: ACTIVE AND MANDATORY 🎯 Application: ALL FUTURE INTERACTIONS 🛠️ Purpose: Ensure consistent, high-quality responses aligned with project goals Linked: .cursor/rules/*.mdc


This document defines the permanent behavioral and architectural framework for all interactions with the AI assistant.

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 · 553 tokens per session scan A 14069bbbc716

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository devviniuchita/memory-system (7 stars, last pushed 11mo ago), licensed MIT. It adds 553 tokens to every session, about $0.0028 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.