401-memory-bank-structure

401-memory-bank-structure is a cursor rule for Cursor from savagelysubtle/BIG-BRAIN-Memory-Bank. It costs 0 tokens per session (968 once invoked), scanned A, original, MIT.

A rule for maintaining a memory bank: structured project files that preserve context between coding sessions. It defines files for product goals, current work, architecture, and technical information, along with when to update them.

In plain words
What is it for?
Use it when documenting project context, recording recent changes, tracking next steps, or updating architectural and technical decisions.
Why use it?
It makes important project knowledge easier to restore and keep current across sessions.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when documenting project context, recording recent changes, tracking next steps, or updating architectural and technical decisions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure
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.

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 401-memory-bank-structure

README.md
[![agentmods](https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure/github.svg)](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure)
Your own site
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 401-memory-bank-structure

Your own site · 80×15
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00968
Opus 5 $0.00000 $0.00484
Sonnet 5 $0.00000 $0.00194
Haiku 4.5 $0.00000 $0.00097

Measured 9d ago against content hash 2791d66c47c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

401-memory-bank-structure 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 9d 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.

inspiration/original-concepts/My-memory-bank/.cursor/rules/401-memory-bank-structure.mdc · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: WHEN user mentions "memory bank" or "update memory bank" PROVIDE complete memory bank structure and update procedures globs: */

  <file name="productContext.md">
    <purpose>Explains why project exists, problems it solves, user experience goals</purpose>
    <importance>High - provides business context</importance>
    <update-frequency>When product requirements evolve</update-frequency>
  </file>

  <file name="activeContext.md">
    <purpose>Documents current work focus, recent changes, next steps</purpose>
    <importance>Very High - tracks current state</importance>
    <update-frequency>Frequent - after each significant work session</update-frequency>
  </file>

  <file name="systemPatterns.md">
    <purpose>Outlines system architecture, technical decisions, component relationships</purpose>
    <importance>High - guides implementation approach</importance>
    <update-frequency>When architectural decisions are made</update-frequency>
  </file>

  <file name="techContext.md">
    <purpose>Lists technologies, development setup, technical constraints</purpose>
    <importance>Medium - provides technical foundation</importance>
    <update-frequency>When technology stack changes</update-frequency>
  </file>

  <file name="progress.md">
    <purpose>Tracks what works, what's left to build, known issues</purpose>
    <importance>Very High - shows progress status</importance>
    <update-frequency>Frequent - after completing features or discovering issues</update-frequency>
  </file>
</core-files>

<additional-context>
  <context-type>Complex feature documentation</context-type>
  <context-type>Integration specifications</context-type>
  <context-type>API documentation</context-type>
  <context-type>Testing strategies</context-type>
  <context-type>Deployment procedures</context-type>
</additional-context>
<update-process>
  <step>Review all Memory Bank files to understand current state</step>
  <step>Identify which files need updates based on recent work</step>
  <step>Make targeted updates preserving all critical information</step>
  <step>Focus especially on activeContext.md and progress.md</step>
  <step>Ensure all files remain consistent with each other</step>
</update-process>

<critical-instruction>
  When triggered by "update memory bank," MUST review EVERY memory bank file, even if some don't require updates. Focus particularly on activeContext.md and progress.md as they track current state.
</critical-instruction>

Read the full file on GitHub · 111 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. 9d ago First seen · 111 lines · 0 tokens per session scan A 2791d66c47c6

Subscribe to this mod's changes

401-memory-bank-structure 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 968 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.