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/300-testing-standards)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/300-testing-standards"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/300-testing-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 | $0.02754 | $0.02754 |
| Opus 5 | $0.01377 | $0.01377 |
| Sonnet 5 | $0.00551 | $0.00551 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade A, and why
300-testing-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 6d 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TL;DR: This rule establishes comprehensive testing standards for BIG BRAIN components, ensuring reliable operation through structured verification approaches, consistency validation, and performance evaluation.
1.0.0
1. **Component Verification**
- Individual component functionality testing
- Interface contract validation
- Implementation correctness
- Edge case handling
- Documentation accuracy
2. **Integration Testing**
- Component interaction validation
- Cross-component dependencies
- Information flow verification
- Interface compatibility
- Combined functionality
3. **Consistency Validation**
- Cross-file consistency
- Terminology alignment
- Pattern adherence
- Standard compliance
- Version compatibility
4. **Memory Persistence Verification**
- Memory reset survival testing
- Knowledge retention verification
- Information retrieval accuracy
- Context restoration correctness
- Transition consistency
5. **Performance Evaluation**
- Response time measurement
- Memory efficiency assessment
- Context window utilization
- Operational scalability
- Resource optimization
Each testing category requires specific approaches, tools, and verification criteria.
1. **Functionality Testing**
- Verify each requirement is implemented
- Test for correct behavior in normal conditions
- Validate outputs match expected results
- Confirm side effects are as intended
- Check that operations occur in correct sequence
2. **Edge Case Testing**
- Test boundary conditions
- Verify error handling
- Test with empty or minimal inputs
- Test with maximum allowed inputs
- Check handling of malformed inputs
3. **Contract Validation**
- Verify component adheres to its interface
- Test all exposed operations
- Confirm requirements are satisfied
- Validate documentation accuracy
- Check version compatibility
4. **Implementation Inspection**
- Review for logic correctness
- Verify algorithm implementation
- Check for pattern adherence
- Confirm style consistency
- Ensure documentation matches implementation
Component verification ensures each part works correctly in isolation.
1. **Dependency Verification**
- Identify all component dependencies
- Verify correct version compatibility
- Test interaction between components
- Confirm information flow is correct
- Check for circular dependencies
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.
- 6d ago First seen · 449 lines · 2,754 tokens per session scan A 5fe24a5b4dcf
300-testing-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 2,754 tokens to every session, about $0.0138 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
propose-test-cases
Propose comprehensive test cases for PR changes.
jest
Jest: describe/it, matchers, mocking, async testing.
testing
Testing: test design, mocking strategy, coverage philosophy.
cypress
Cypress: cy commands, selectors, fixtures, intercepts.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.
pytest
You are an expert in pytest testing. Follow these rules.