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/400-documentation-standards)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/400-documentation-standards"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/400-documentation-standards.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 | $0.00000 | $0.01986 |
| Opus 5 | $0.00000 | $0.00993 |
| Sonnet 5 | $0.00000 | $0.00397 |
| Haiku 4.5 | $0.00000 | $0.00199 |
Grade A, and why
400-documentation-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 8d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN creating or updating BIG BRAIN components ENSURE proper documentation standards are followed globs: ["/*.mdc", "/*.md"] alwaysApply: true
TL;DR: This rule defines documentation standards for BIG BRAIN components, ensuring consistent, complete, and high-quality documentation that persists across memory resets.
1.0.0
1. **TL;DR Summary**
- Concise overview (1-3 sentences)
- Placed at the beginning after description
- Formatted with blockquote for visual emphasis
- Example: `> **TL;DR:** This component provides verification mechanisms for memory file integrity.`
2. **Version Information**
- Clear version number
- Located near the top
- Follows semantic versioning (MAJOR.MINOR.PATCH)
- Format: `<version>1.0.0</version>`
3. **Context Description**
- Explains the purpose and importance
- Provides essential background
- Clarifies when/why the component is needed
- Format: `<context>Description here...</context>`
4. **Requirements List**
- Explicit enumeration of what the component must accomplish
- Individual requirements clearly tagged
- Concise, action-oriented statements
- Format:
```
<requirements>
<requirement>First requirement</requirement>
<requirement>Second requirement</requirement>
</requirements>
```
5. **Implementation Details**
- Organized in separate named sections
- Progressive disclosure (most important first)
- Visual hierarchy with headers, lists, tables
- Format:
```
<details>
<section-name>SECTION NAME</section-name>
<content>
Section content here...
</content>
</details>
```
6. **Version History**
- Table of changes by version
- Author of each change
- Date of modification
- Brief description of changes
- Format:
```
## 📝 Version History
| Version | Date | Author | Changes |
| ------- | ---------- | --------- | ----------------------- |
| 1.0.0 | 2025-03-24 | BIG BRAIN | Initial implementation |
```
1. **Markdown Structure**
- Use ATX-style headers (`#`, `##`, etc.)
- Use fenced code blocks with language identifiers
- Use unordered lists for collections without sequence
- Use ordered lists for sequential steps
- Use tables for structured data
2. **Visual Hierarchy**
- Consistent emoji markers for section types:
- 📌 for key points
- 🔍 for implementation details
- 📋 for checklists
- 🧠 for insights
- ⏭️ for next steps
- 📝 for version history
- Use horizontal rules (`---`) to separate major sections
- Use indentation for hierarchical information
- Use bold and italics for emphasis
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.
- 8d ago First seen · 293 lines · 0 tokens per session scan A 3abb5c003c42
400-documentation-standards 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 1,986 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-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.
composer-reasoning
High-stakes judgment for architectural or multi-option work — tradeoffs, one-way doors, reason-then-re-evaluate, honest pushback.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
composer-fullstack-delivery
New screen, feature, endpoint, or multi-layer slice — freeze seams, ship one demoable path, failure modes, Run/Wired handoff.
composer-deep-research
Edge-case research for audits, vendor comparisons, and unfamiliar APIs — primaries first, iterative retrieval, explicit conflicts; not the default build path.