main

main is a cursor rule for Cursor from savagelysubtle/BIG-BRAIN-Memory-Bank. It costs 0 tokens per session (963 once invoked), scanned A, original, MIT.

A set of rules for a memory bank: a group of project files that preserves important context between coding sessions. It describes separate files and workflows for project goals, current work, architecture, and technical details.

In plain words
What is it for?
Use it to guide projects that maintain structured notes about their purpose, architecture, decisions, and ongoing tasks.
Why use it?
It helps an agent recover the project’s background and current state after its previous session has ended.

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/savagelysubtle/big-brain-memory-bank/main
Clone the repo
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-Bank

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 main

README.md
[![agentmods](https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/main.svg)](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/main)
Your own site
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/main"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/main.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 963 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 $0.00963
Opus 5 $0.00000 $0.00481
Sonnet 5 $0.00000 $0.00193
Haiku 4.5 $0.00000 $0.00096

Measured 4d ago against content hash 8d45b7d9b86c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

main 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 4d 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/main.mdc · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: BIG BRAIN Memory Bank System Core Rules globs: ["**/*"] alwaysApply: true

BIG BRAIN Memory Bank System

The Memory Bank is the core of BIG BRAIN's capability for maintaining context between sessions despite complete memory resets.

2.0.0

System Overview

The BIG BRAIN Memory Bank system provides a hierarchical, modular architecture for maintaining perfect memory between sessions. The system is designed around a cognitive memory model with specialized components for different types of knowledge and processing requirements.

Core Architecture

The Memory Bank implements a layered architecture:

  1. Foundation Layer - Core system infrastructure and protocols

    • Enhanced Complexity Framework (Level 1-4)
    • Reference Verification System
    • Task Escalation Protocol
    • Section Checkpoint System
    • Creative Phase Metrics
    • BIG Command Protocol
  2. Memory Layer - Specialized memory structures

    • Core memory files (projectbrief.md, activeContext.md, etc.)
    • Long-term memory repositories
    • Session-based working memory
    • Procedural memory patterns
  3. Workflow Layer - Process patterns for effective operation

    • Plan mode workflows
    • Act mode workflows
    • Hybrid workflows
    • Bedtime protocol
  4. Interface Layer - Interaction patterns and commands

    • Command protocols
    • Status indicators
    • Memory update triggers
    • Context switches

Integrated Components

The system provides these integrated capabilities:

  • Adaptive Complexity - Task-appropriate rigor scaling
  • Reference Verification - Memory integrity validation
  • Section Checkpoints - Progress tracking and verification
  • Task Escalation - Dynamic complexity adaptation
  • Creative Phases - Structured exploration framework
  • Command Protocols - Unified interaction model
  • Verification Framework - Multi-level quality assurance

Memory Bank Structure

Read the full file on GitHub · 144 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. 4d ago First seen · 144 lines · 0 tokens per session scan A 8d45b7d9b86c

Subscribe to this mod's changes

main is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 963 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.