Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-Banknpx agentmods add rules/savagelysubtle/big-brain-memory-bank/410-mermaid-diagram-standardsWrote 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/410-mermaid-diagram-standards)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/410-mermaid-diagram-standards"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/410-mermaid-diagram-standards/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/410-mermaid-diagram-standards"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/410-mermaid-diagram-standards.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 | $0.03115 | $0.03115 |
| Opus 5 | $0.01558 | $0.01558 |
| Sonnet 5 | $0.00623 | $0.00623 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
410-mermaid-diagram-standards 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 12d 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TL;DR: This rule defines standards for creating, storing, and using Mermaid diagrams in the BIG BRAIN documentation, ensuring visual consistency and maintainability across all diagrams.
1.0.0
```
/images/
├── *.mermaid # Source files for all diagrams
├── *.png # PNG exports of diagrams
├── *.svg # SVG exports of diagrams
└── README.md # Directory documentation
/docs/assets/
├── *.png # Diagram PNGs used in documentation
├── *.svg # Diagram SVGs used in documentation
└── .gitkeep # Ensures directory exists in git
```
Each diagram must have:
1. A source `.mermaid` file in the `/images` directory
2. Corresponding `.png` and `.svg` exports in `/images`
3. Copies of exported images in `/docs/assets` when used in documentation
Diagram naming must be:
- Descriptive of content (e.g., `memory-bank-structure.mermaid`)
- Kebab-case format (lowercase with hyphens)
- Consistent across source and export files (same base name)
1. **Flowcharts** (`flowchart` or `graph`)
- For process flows, algorithms, and decision trees
- Direction: TD (top-down) for procedures, LR (left-right) for sequences
- Example use: Bedtime Protocol process flow
2. **Sequence Diagrams** (`sequenceDiagram`)
- For interaction between components over time
- Example use: Memory Bank initialization sequence
3. **Class Diagrams** (`classDiagram`)
- For system structure and relationships
- Example use: Memory Bank component relationships
4. **State Diagrams** (`stateDiagram-v2`)
- For state transitions and lifecycle management
- Example use: Task state transitions
5. **Entity Relationship Diagrams** (`erDiagram`)
- For data relationships
- Example use: Memory file relationships
6. **Gantt Charts** (`gantt`)
- For project planning and timelines
- Example use: Implementation phase schedule
Choose the diagram type that best communicates the concept being documented.
1. **Color Scheme**
- Use consistent colors for specific component types:
- Foundation Layer: `#4285F4` (blue)
- Verification Framework: `#34A853` (green)
- Command Protocol: `#FBBC05` (yellow)
- Creative Phase: `#EA4335` (red)
- Files/Documents: `#9AA0A6` (gray)
- User Interaction: `#8AB4F8` (light blue)
- External Systems: `#F6AEA9` (light red)
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.
- 12d ago First seen · 386 lines · 3,115 tokens per session scan A 089c99244d33
410-mermaid-diagram-standards is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 3,115 tokens to every session, about $0.0156 per session on Opus 5. 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
web
Web build conventions (separate from native and RN JS).
components
Component patterns and UI conventions.
git
Git workflow and commit conventions.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
_project
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).
full-stack-ship-discipline
Require frontend changes and their DB/RPC/RLS/storage/secret dependencies to ship and be remotely verified together. Apply when implementing code that reads or writes backend state. Do not apply to plan- or present-then-stop audits; production data mutation still requires confirmation.