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/creative-phase-guidelinesgit 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-guidelines)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/creative-phase-guidelines"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/creative-phase-guidelines.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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
creative-phase-guidelines 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.
This is a copy
100% identical to creative-phase-guidelines — 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎨 ENHANCED CREATIVE PHASE HANDLING
TL;DR: Use creative phases as dedicated thinking spaces for complex problem-solving. Apply structured thinking with explicit verification steps, especially for Level 3-4 tasks. Include regular checkpoints, analyze options systematically, and provide comprehensive summaries when exiting. Creative phase handling scales with task complexity.
🎨 CREATIVE PHASE AS STRUCTURED THINKING SPACE
Creative phases serve as dedicated thinking spaces for complex problem-solving, similar to the "think" tool approach. They're most valuable for:
- Sequential decision making where each step builds on previous ones
- Complex design choices with multiple trade-offs
- Scenarios where mistakes would be costly to fix later
- Tasks requiring policy adherence or constraint verification
🎨 CREATIVE PHASE MARKERS
For maximum visibility, use these prominent markers:
🎨🎨🎨 ENTERING CREATIVE PHASE: [DESIGN/ALGORITHM/ARCHITECTURE] 🎨🎨🎨
[Creative work happens here]
🎨🎨🎨 EXITING CREATIVE PHASE - RETURNING TO TASK TRACKING 🎨🎨🎨
Always include a creative phase summary when exiting:
🔄 CREATIVE PHASE SUMMARY:
- Completed: [Brief description of creative work]
- Key decisions: [Important decisions made]
- Next steps: [Follow-up implementation tasks]
- Documentation: [Where decisions were documented]
- Verification: [Confirmation that solution meets requirements and constraints]
🎨 CREATIVE PHASE STRUCTURE
1. Starting a Creative Phase
When entering a creative phase, clearly define:
🎨🎨🎨 ENTERING CREATIVE PHASE: [TYPE] 🎨🎨🎨
Focus: [Specific focus area]
Objective: [What you aim to accomplish]
Constraints: [Any constraints to consider]
[Initial exploration of the problem space]
2. During a Creative Phase
For extended creative work, use periodic checkpoints that incorporate structured thinking:
🎨 CREATIVE CHECKPOINT: [Milestone reached]
- Progress: [Brief progress description]
- Decisions made:
- [Decision 1]
- [Decision 2]
- Verification:
- [Verify solution addresses requirements]
- [Verify compliance with constraints]
- [Verify consistency with existing system]
- Open questions:
- [Question 1]
- [Question 2]
- Next creative milestone: [Description]
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 · 179 lines · 1,250 tokens per session scan A 4010eab2a563
creative-phase-guidelines is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to creative-phase-guidelines, differing in 0 lines, and is treated as a copy.
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.