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.
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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.
[](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/401-memory-bank-structure)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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>
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.
- 9d ago First seen · 111 lines · 0 tokens per session scan A 2791d66c47c6
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.
Other cursor rules, from other repositories
wrapup
End-of-session wrap-up: summarizes the session and pushes a log to the project's linked NotebookLM notebook. Activate with @wrapup in chat, or "wrap up", "save this session", or "end of session".
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
composer-debugging
Root-cause debugging — reproduce, trace data flow, test cheapest hypothesis, fix the cause not the symptom.