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/900-component-templategit 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/900-component-template)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/900-component-template"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/900-component-template.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 | $0.03622 |
| Opus 5 | $0.00000 | $0.01811 |
| Sonnet 5 | $0.00000 | $0.00724 |
| Haiku 4.5 | $0.00000 | $0.00362 |
Grade A, and why
900-component-template 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TL;DR: This template provides the standard structure for BIG BRAIN component rule files, ensuring consistent formatting, comprehensive documentation, and proper integration with the memory bank system.
1.0.0
```
---
description: WHEN [activation context] APPLY/ENSURE/FOLLOW [action or requirement]
globs: ["**/*.mdc", "**/*.md"]
alwaysApply: true/false
---
> **TL;DR:** Brief 1-3 sentence summary of the component's purpose and function.
<version>1.0.0</version>
<context>
Detailed explanation of why this component exists, what problem it solves,
and its importance within the BIG BRAIN system. Provide sufficient background
for understanding the component's purpose without requiring extensive
cross-referencing.
</context>
<requirements>
<requirement>First specific requirement this component must fulfill</requirement>
<requirement>Second specific requirement this component must fulfill</requirement>
<requirement>Additional requirements as needed</requirement>
<requirement>Be specific, actionable, and verification-friendly</requirement>
<requirement>Focus on WHAT must be achieved, not HOW</requirement>
</requirements>
<details>
<section-name>SECTION NAME IN UPPERCASE</section-name>
<content>
Detailed content for this section, organized in a structured manner.
Use consistent formatting throughout:
1. **Primary Items**
- Sub-item details
- Additional details
- More information
2. **Secondary Items**
- Supporting information
- Implementation guidance
- Best practices
Add as many structured sections as needed to fully document the component.
Use numbered lists for sequential processes and bulleted lists for collections.
</content>
</details>
<details>
<section-name>ANOTHER SECTION NAME</section-name>
<content>
Additional section content organized similarly.
Include relevant:
- Implementation details
- Usage guidelines
- Integration information
- Examples
- Edge cases
Ensure comprehensive coverage of the component's functionality.
</content>
</details>
<details>
<section-name>COMPLEXITY ADAPTATION</section-name>
<content>
Explain how the component adapts to different complexity levels:
**Level 1 (Simple)**
- Simplified behavior for basic tasks
- Minimal requirements
- Streamlined processing
**Level 2 (Moderate)**
- Standard behavior for routine tasks
- Complete but focused requirements
- Regular processing depth
**Level 3 (Complex)**
- Enhanced behavior for complex tasks
- Comprehensive requirements
- Thorough processing
**Level 4 (Critical)**
- Maximum behavior for mission-critical tasks
- Exhaustive requirements
- Rigorous processing with additional validation
Specific details should explain how the component's behavior changes
based on task complexity level.
</content>
</details>
<details>
<section-name>INTEGRATION WITH MEMORY BANK</section-name>
<content>
Explain how this component integrates with the memory bank:
1. **Documentation Updates**
- What updates are made to activeContext.md
- What is recorded in progress.md
- What patterns are documented in systemPatterns.md
- What technical details are updated in techContext.md
2. **Knowledge Preservation**
- How critical information is preserved
- How decisions are documented
- How component state is maintained
- How reference integrity is preserved
3. **Cross-Component Integration**
- How this component interacts with others
- Key integration points
- Dependency relationships
- Interface contracts
This section is crucial for ensuring the component works within the
overall memory bank system.
</content>
</details>
<details>
<section-name>EXAMPLES</section-name>
<content>
Provide concrete examples of the component in action:
**Example 1: [Brief Description]**
```
[Detailed example implementation or usage]
```
**Example 2: [Brief Description]**
```
[Another example showing different aspect]
```
Examples should be practical, illustrative, and cover both typical
usage and important edge cases.
</content>
</details>
## 📝 Version History
| Version | Date | Author | Changes |
| ------- | ---------- | --------- | --------------------------------- |
| 1.0.0 | YYYY-MM-DD | BIG BRAIN | Initial component implementation |
```
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 · 494 lines · 0 tokens per session scan A 1bf4ea13972a
900-component-template 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 3,622 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.
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-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.