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.
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/van-protocolgit 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/van-protocol)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/van-protocol"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/van-protocol.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 | $0.02023 | $0.02023 |
| Opus 5 | $0.01012 | $0.01012 |
| Sonnet 5 | $0.00405 | $0.00405 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
van-protocol 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 van-protocol — 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADAPTIVE VAN PROTOCOL
TL;DR: When user types "VAN", respond with "OK VAN", determine task complexity level, and adapt the workflow process accordingly. The system scales from quick bug fixes to complex system implementations.
🚀 QUICK START RESPONSE
When the user types ONLY "VAN", immediately respond:
OK VAN
I'll determine the appropriate process level based on the task complexity:
## COMPLEXITY ANALYSIS
[ ] Analyzing task type and complexity...
[ ] Determining appropriate process level...
## FILE VERIFICATION
[ ] .cursorrules
[ ] memory-bank directory
[ ] docs/archive directory
[ ] tasks.md
Checking these now...
📋 TASK COMPLEXITY DETERMINATION
Analyze the task to determine the appropriate complexity level:
Level 1: Quick Bug Fix
- Keywords: "fix", "broken", "not working", "issue", "bug", "error"
- Scope: Single component or simple UI element
- Purpose: Restore existing functionality
- Examples: "Fix login button", "Fix styling issue", "Fix validation error"
Level 2: Simple Enhancement
- Keywords: "add", "improve", "update", "change", "enhance"
- Scope: Single component or subsystem
- Purpose: Small feature addition or enhancement
- Examples: "Add logout button", "Improve form validation", "Update header style"
Level 3: Intermediate Feature
- Keywords: "implement", "create", "develop", "build"
- Scope: Complete feature requiring multiple components
- Purpose: Significant new functionality
- Examples: "Implement user profiles", "Create dashboard", "Develop search functionality"
Level 4: Complex System
- Keywords: "system", "architecture", "redesign", "integration", "framework"
- Scope: Multiple subsystems or entire application
- Purpose: Major architectural changes
- Examples: "Implement authentication system", "Build payment processing", "Create microservice architecture"
📋 FILE VERIFICATION PROCESS
Check for critical files and create them if missing:
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 · 307 lines · 2,023 tokens per session scan A b29bbb02a3af
van-protocol is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 2,023 tokens to every session, about $0.0101 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to van-protocol, 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".
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…
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
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.