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/creative-phase-examples)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/creative-phase-examples"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/creative-phase-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/creative-phase-examples"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/creative-phase-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 | $0.04626 |
| Opus 5 | $0.00000 | $0.02313 |
| Sonnet 5 | $0.00000 | $0.00925 |
| Haiku 4.5 | $0.00000 | $0.00463 |
Grade A, and why
creative-phase-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 creative-phase-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 — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CREATIVE PHASE EXAMPLES
TL;DR: These examples demonstrate the correct format for documenting different types of creative phases across complexity levels. Use these as templates when engaging in creative work during tasks.
⚠️ CORRECT CREATIVE PHASE EXAMPLES ⚠️
Example 1: Algorithm Design Creative Phase
🎨🎨🎨 ENTERING CREATIVE PHASE: ALGORITHM DESIGN 🎨🎨🎨
Focus: Data sorting algorithm
Objective: Efficient sorting of large datasets with minimal memory overhead
Constraints: O(n log n) performance, stable sort, memory efficient
Working on sorting algorithm for large datasets:
- Need O(n log n) performance
- Must handle duplicate values
- Should be stable sort
- Memory constraints: O(1) extra space preferred
Options being considered:
1. Modified QuickSort with median-of-three pivot
- Pros: Very fast average case
- Cons: Not stable, worst case O(n²)
2. MergeSort with in-place merging
- Pros: Stable, guaranteed O(n log n)
- Cons: In-place version is complex
3. Custom hybrid approach
- Pros: Can optimize for specific data patterns
- Cons: More complex implementation
Analysis:
- Standard QuickSort isn't stable and can degrade to O(n²)
- Standard MergeSort uses O(n) extra space
- In-place merge is possible but complex
- Tim Sort could be a good option but more complex to implement
Decision: Implementing modified MergeSort with block-based in-place approach
- Using block size of sqrt(n) for balanced performance
- Implementing rotation-based in-place merging
- Adding adaptive optimization for already-sorted runs
🎨 CREATIVE CHECKPOINT: Initial algorithm design
- Progress: Selected core algorithm approach
- Decisions made:
- Block-based MergeSort as foundation
- In-place merging with rotation technique
- Adaptive optimization for already-sorted runs
- Open questions:
- Optimal block size determination method
- Thread safety considerations
- Next creative milestone: Implementation details and edge cases
[Algorithm pseudocode and implementation details...]
🎨🎨🎨 EXITING CREATIVE PHASE - RETURNING TO TASK TRACKING 🎨🎨🎨
🔄 CREATIVE PHASE SUMMARY:
- Completed: Algorithm design for large dataset sorting
- Key decisions: Modified MergeSort with block-based approach
- Next steps:
1. Implement the algorithm in code
2. Create test cases for edge cases
3. Benchmark performance
- Documentation: Algorithm design details added to systemPatterns.md
🔄 TASK UPDATE: Implement sorting algorithm - In Progress
- Updated in tasks.md ✓
- Creative work completed: Algorithm design
- Implementation details added to activeContext.md ✓
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 · 645 lines · 4,626 tokens per session scan A 7cd747471eb0
creative-phase-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 4,626 tokens. A static security scan graded it A with 0 findings. It is 100% identical to creative-phase-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).