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/workflowgit clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWhat 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 | $0.03450 | $0.03450 |
| Opus 5 | $0.01725 | $0.01725 |
| Sonnet 5 | $0.00690 | $0.00690 |
| Haiku 4.5 | $0.00345 | $0.00345 |
Grade A, and why
workflow 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 2d 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 workflow — 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Adaptive structured workflow implementation protocol globs: /src/", "/.cursorrules", "/memory-bank/** alwaysApply: true
ADAPTIVE STRUCTURED WORKFLOW PROTOCOL
TL;DR: Follow a workflow process that scales based on task complexity. Level 1 (Bug Fix) uses a streamlined process, while Level 4 (Complex System) uses the complete formal process with all checkpoints.
🔧 TASK COMPLEXITY LEVELS
The workflow scales across four complexity levels:
-
Level 1: Quick Bug Fix
- Simple errors, UI glitches, minor issues
- Streamlined process with minimal documentation
- Focus on rapid resolution and targeted updates
-
Level 2: Simple Enhancement
- Small features, minor improvements
- Basic process with essential documentation
- Focus on clean implementation and clear documentation
-
Level 3: Intermediate Feature
- Complete features, significant changes
- Standard process with full section tracking
- Focus on comprehensive planning and documentation
-
Level 4: Complex System
- Major systems, architectural changes
- Full formal process with detailed checkpoints
- Focus on architectural integrity and complete documentation
🚨 SECTION TRANSITION MARKERS
These visual markers indicate workflow section transitions (Level 3-4 only):
======== INITIALIZATION COMPLETE ⟹ STARTING DOCUMENTATION SETUP ========
======== DOCUMENTATION SETUP COMPLETE ⟹ STARTING TASK PLANNING ========
======== TASK PLANNING COMPLETE ⟹ STARTING CREATIVE PHASES ========
======== CREATIVE PHASES COMPLETE ⟹ STARTING IMPLEMENTATION ========
======== IMPLEMENTATION COMPLETE ⟹ STARTING REFLECTION ========
======== REFLECTION COMPLETE ⟹ STARTING ARCHIVING ========
======== ARCHIVING COMPLETE ⟹ TASK FINISHED ========
🎨 CREATIVE PHASE MARKERS
For tasks requiring extended creative work, use these prominent markers to create a dedicated thinking space:
🎨🎨🎨 ENTERING CREATIVE PHASE: [DESIGN/ALGORITHM/ARCHITECTURE] 🎨🎨🎨
Focus: [Specific focus area]
Objective: [What you aim to accomplish]
Constraints: [Any constraints to consider]
Breaking down the problem:
- [Component 1]
- [Component 2]
- [Component 3]
[Structured creative exploration with systematic analysis]
🎨 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]
🎨🎨🎨 EXITING CREATIVE PHASE - RETURNING TO TASK TRACKING 🎨🎨🎨
🔄 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]
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.
- 2d ago First seen · 489 lines · 3,450 tokens per session scan A ea8a260cba11
workflow is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 3,450 tokens to every session, about $0.0173 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to workflow, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
skill-workflows
Capabilities catalog for cursor-kenji skills. Routes requests to the right skill or bundled workflow. Always-on routing index — the agent consults this to pick between individual skills and bundled workflows.
composer-2.5-execution
Guard execution of approved plan/burndown work: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Apply to approved plan-.md, complete-everything, or burndown-full runs; binding for any implementation model.
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.
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.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.