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/system-overview)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/system-overview"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/system-overview.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.01838 |
| Opus 5 | $0.00005 | $0.00919 |
| Sonnet 5 | $0.00002 | $0.00368 |
| Haiku 4.5 | $0.00001 | $0.00184 |
Grade A, and why
system-overview 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.
This is a copy
100% identical to system-overview — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADAPTIVE MEMORY BANK SYSTEM OVERVIEW
TL;DR: This system uses structured documentation as AI memory across sessions. It offers four complexity levels that scale from quick bug fixes to complex systems, adapting the process while maintaining documentation quality. Tasks.md serves as the single source of truth for task tracking.
🎯 SYSTEM PURPOSE
The Adaptive Memory Bank System creates persistent memory for AI assistants through structured documentation that scales based on task complexity. It addresses the fundamental limitation of LLMs forgetting context between interactions.
🧠 CORE PRINCIPLES
- Documentation as Memory - Documentation is mission-critical infrastructure
- Adaptive Process Scaling - Process complexity matches task requirements
- Single Source of Truth - Tasks.md is the only place for task status tracking
- Strategic Content Organization - Balance between core files and detailed examples
- Verification Steps - Explicit checks prevent steps from being skipped
- Reference Triggers - Force documentation consultation at critical points
- Processing Efficiency - Optimized structure for LLM comprehension
- Structured Creative Thinking - Creative phases as dedicated thinking spaces for complex problem-solving
📏 ADAPTIVE PROCESS LEVELS
Level 1: Quick Bug Fix
- Focus: Simple errors, UI glitches, minor issues
- Process: Streamlined with minimal documentation
- Task Updates: 2-3 updates (start/end)
- Memory Bank Impact: Targeted updates to relevant files
Level 2: Simple Enhancement
- Focus: Small features, minor improvements
- Process: Basic with essential documentation
- Task Updates: 4-6 updates at key milestones
- Memory Bank Impact: Updates to related files
Level 3: Intermediate Feature
- Focus: Complete features, significant changes
- Process: Standard with full section tracking
- Task Updates: 8-12 updates at defined points
- Memory Bank Impact: Comprehensive updates to most files
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.
- 4d ago First seen · 219 lines · 9 tokens per session scan A fb1082e38c75
system-overview is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 9 tokens to every session and 1,838 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to system-overview, differing in 0 lines, and is treated as a copy.
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".
client-workflow-bootstrap
Cursor rule "client-workflow-bootstrap" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, interview process and gate before generating.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
_project
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.