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/090-big-command-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/090-big-command-protocol)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/090-big-command-protocol"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/090-big-command-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 | $0.00000 | $0.01923 |
| Opus 5 | $0.00000 | $0.00962 |
| Sonnet 5 | $0.00000 | $0.00385 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
090-big-command-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 5d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN user issues "BIG" command ENSURE comprehensive initialization and task setup globs: ["/*.md", "/.mdc", "**/README"] alwaysApply: true
TL;DR: The BIG command protocol provides a unified initialization approach for the Memory Bank system, automating platform detection, file verification, and workflow setup based on task complexity.
1.0.0
- `BIG <task description>` - Standard format
- `BIG: <task description>` - Colon format
- `@BIG <task description>` - Tag format
These variants are all recognized as BIG commands and will trigger the full protocol.
1. **Platform Detection**:
- Identify operating system from user info
- Set platform-specific command formats
- Adjust file paths for platform
2. **File Verification**:
- Check all required Memory Bank files exist
- Verify .cursor/rules directory is properly configured
- Create any missing files using templates
3. **Task Analysis**:
- Parse task description
- Assess complexity factors (scope, risk, dependencies, difficulty)
- Determine appropriate complexity level (1-4)
4. **Workflow Initialization**:
- Set up appropriate workflow based on complexity
- Initialize task tracking in activeContext.md
- Set up section checkpoints appropriate to complexity
5. **Memory Bank Preparation**:
- Update activeContext.md with new task focus
- Review and reference relevant memory files
- Prepare session structure based on complexity
```
📋 MEMORY BANK VERIFICATION
- Core active files: [✓/X]
- Long-term memory structures: [✓/X]
- Bedtime protocol files: [✓/X]
- Rule system files: [✓/X]
🛠️ PLATFORM VERIFICATION
- Operating System: [Windows/Mac/Linux]
- Appropriate command format: [PowerShell/Bash/Other]
- Path format: [Windows/Unix]
⚙️ TASK SETUP VERIFICATION
- Complexity assessment: [Level 1-4]
- Workflow mode: [PLAN/ACT]
- Task tracking initialized: [✓/X]
- Section checkpoints configured: [✓/X]
```
If any verification fails, automatic correction will be attempted before proceeding.
1. **Scope**:
- Level 1: Single function/method change
- Level 2: Single component change
- Level 3: Multiple component changes
- Level 4: System-wide architecture changes
2. **Risk**:
- Level 1: Minimal risk, isolated change
- Level 2: Low risk, limited impact
- Level 3: Moderate risk, broader impact
- Level 4: High risk, critical system impact
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.
- 5d ago First seen · 269 lines · 0 tokens per session scan A fff0b4693ae3
090-big-command-protocol 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 1,923 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
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-reasoning
High-stakes judgment for architectural or multi-option work — tradeoffs, one-way doors, reason-then-re-evaluate, honest pushback.
composer-debugging
Root-cause debugging — reproduce, trace data flow, test cheapest hypothesis, fix the cause not the symptom.
composer-deep-research
Edge-case research for audits, vendor comparisons, and unfamiliar APIs — primaries first, iterative retrieval, explicit conflicts; not the default build path.