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/reflection-examples)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/reflection-examples"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/reflection-examples/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/reflection-examples"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/reflection-examples.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 | $0.00000 | $0.01488 |
| Opus 5 | $0.00000 | $0.00744 |
| Sonnet 5 | $0.00000 | $0.00298 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
reflection-examples 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.
This is a copy
100% identical to reflection-examples — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflection Format Examples
⚠️ CORRECT FORMAT EXAMPLES ⚠️
Example 1: Frontend Feature Reflection
## REFLECTION
### What Went Well
- React component architecture allowed for clean separation of concerns, making it easy to isolate and test individual components
- CSS module approach eliminated style conflicts and scoping issues entirely
- Implementation of custom hooks for form validation significantly reduced code duplication across multiple forms
- State management with Context API was sufficient for this feature scope without needing Redux
- Test-driven development approach caught several edge cases early in the development process
### Challenges
- Initial approach to form validation was too complex and had to be refactored
- Performance issues arose with real-time filtering of large datasets
- Mobile responsiveness required significant adjustments to the original design
- Browser compatibility issues with CSS Grid required additional fallbacks
### Lessons Learned
- Start with simpler validation approaches and add complexity as needed
- Consider pagination or virtualization early when dealing with large datasets
- Mobile-first design would have prevented later responsiveness issues
- Testing cross-browser compatibility earlier would have saved time
- Breaking components into smaller, more focused pieces improves maintainability
- Custom hooks are powerful for extracting and reusing logic
### Improvements for Next Time
- Implement a mobile-first design approach from the beginning
- Set up comprehensive browser testing earlier in the process
- Consider performance implications earlier when designing data-heavy features
- Create a more systematic approach to component props and interfaces
- Establish clearer boundaries between component responsibilities
- Document component APIs more thoroughly as they're developed
Example 2: Backend API Reflection
## REFLECTION
### What Went Well
- Middleware-based architecture made error handling consistent across all endpoints
- Input validation using a schema-based approach caught invalid requests early
- Repository pattern provided clean separation between database and business logic
- Unit testing each layer independently made debugging easier
- Automated integration tests with a test database ensured reliable API behavior
- Consistent error response format improved client experience
### Challenges
- Initial database schema had performance issues with complex queries
- Authentication flow had security vulnerabilities in the first implementation
- Error handling was inconsistent across different parts of the application
- Managing test data became complex as the number of tests grew
### Lessons Learned
- Database schema design should consider query patterns from the beginning
- Security reviews should happen earlier in the development process
- Consistent error handling requires a centralized approach
- Test data management benefits from factory patterns
- Input validation should happen as early as possible in the request lifecycle
- Documentation-driven development clarifies API design before implementation
- Environment-specific configuration is critical for smooth deployment
### Improvements for Next Time
- Start with security considerations as a first-class concern
- Design database schema with specific query patterns in mind
- Implement more comprehensive input validation from the start
- Create better tooling for test data management
- Establish clear patterns for handling asynchronous operations
- Include performance testing earlier in the development cycle
- Improve logging for better production debugging
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 · 223 lines · 1,488 tokens per session scan A acc8c1c86393
reflection-examples 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 1,488 tokens. A static security scan graded it A with 0 findings. It is 100% identical to reflection-examples, differing in 0 lines, and is treated as a copy.
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.
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.
_project
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).