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/080-creative-phase-metrics)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/080-creative-phase-metrics"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/080-creative-phase-metrics/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/080-creative-phase-metrics"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/080-creative-phase-metrics.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 | $0.02385 |
| Opus 5 | $0.00000 | $0.01192 |
| Sonnet 5 | $0.00000 | $0.00477 |
| Haiku 4.5 | $0.00000 | $0.00238 |
Grade A, and why
080-creative-phase-metrics 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 8d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN entering a creative phase ENSURE comprehensive exploration and validation globs: ["/*.md", "/*.mdc"] alwaysApply: true
TL;DR: The Creative Phase Metrics system ensures all creative work meets quality standards through structured exploration, validation, and verification processes.
1.0.0
1. **Problem Analysis**
- Define current state
- Identify limitations
- Clarify requirements
- Establish constraints
2. **Solution Exploration**
- Generate multiple viable approaches (minimum 3)
- Document pros/cons of each approach
- Consider extreme alternatives
- Explore non-obvious solutions
3. **Solution Evaluation**
- Create evaluation matrix with weighted criteria
- Score each solution objectively
- Calculate weighted scores
- Identify preferred approach
4. **Implementation Planning**
- Detail implementation steps
- Define interfaces and boundaries
- Address edge cases
- Identify verification checks
5. **Validation**
- Verify against requirements
- Check alignment with constraints
- Confirm backward compatibility
- Document verification process
**Exploration Quality**
- [ ] Multiple approaches explored (minimum 3)
- [ ] Each approach has detailed pros/cons analysis
- [ ] Exploration includes non-obvious alternatives
- [ ] Edge cases and constraints considered for each approach
**Solution Quality**
- [ ] Selection criteria are objective and weighted appropriately
- [ ] Evaluation matrix includes all relevant dimensions
- [ ] Selected solution clearly meets requirements
- [ ] Implementation considerations documented
**Documentation Quality**
- [ ] Decision rationale clearly explained
- [ ] Alternative approaches properly documented
- [ ] Selection criteria explicitly stated
- [ ] Future maintainability addressed
**Implementation Readiness**
- [ ] Clear action steps defined
- [ ] Interfaces and boundaries specified
- [ ] Validation approach documented
- [ ] Backward compatibility addressed
```
## Creative Phase Verification
### Exploration Verification
- [ ] Multiple solutions explored (List: ...)
- [ ] Pros/cons documented for each
- [ ] Non-obvious alternatives considered
- [ ] Edge cases addressed
### Selection Verification
- [ ] Objective criteria established
- [ ] Evaluation matrix completed
- [ ] Selected approach justified
- [ ] Implementation plan outlined
### Documentation Verification
- [ ] Decision rationale documented
- [ ] Alternatives properly archived
- [ ] Future considerations addressed
- [ ] Knowledge transfer ensured
### Technical Verification
- [ ] Backward compatibility confirmed
- [ ] Error handling addressed
- [ ] Performance implications considered
- [ ] Security implications evaluated
```
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.
- 8d ago First seen · 343 lines · 0 tokens per session scan A 468671b5e337
080-creative-phase-metrics 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 2,385 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-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
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.
composer-verification
Always-on proof contract — labeled completion states, proportional evidence, no fabricated success.