800-memory-operations-workflow

800-memory-operations-workflow is a cursor rule for Cursor from savagelysubtle/BIG-BRAIN-Memory-Bank. It costs 3,178 tokens per session, scanned A, original, MIT.

A set of written procedures for storing and restoring project information across coding sessions. It covers loading, updating, checking, and summarizing a project's memory files.

In plain words
What is it for?
Use it when starting or ending sessions, updating project notes, restoring context, switching tasks, or checking that stored project information is consistent.
Why use it?
It reduces the risk of losing context or using inconsistent steps after a session reset. Checks help detect missing, inconsistent, or damaged information.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when starting or ending sessions, updating project notes, restoring context…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/800-memory-operations-workflow
Install

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.

Clone the repo
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-Bank

Made for: Cursor.

Wrote 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.

agentmods badge for 800-memory-operations-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/800-memory-operations-workflow.svg)](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/800-memory-operations-workflow)
Your own site
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/800-memory-operations-workflow"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/800-memory-operations-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,178 This file is loaded in full into every session.
When invoked 3,178 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03178 $0.03178
Opus 5 $0.01589 $0.01589
Sonnet 5 $0.00636 $0.00636
Haiku 4.5 $0.00318 $0.00318

Measured 6d ago against content hash d8ff34727377, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

800-memory-operations-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 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.

.cursor/rules/BIG_BRAIN/Workflows/800-memory-operations-workflow.mdc · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TL;DR: This rule establishes standardized workflows for memory bank operations, ensuring consistent processes for initialization, updates, verification, and session transitions despite memory resets.

1.0.0

1. **Initialization Workflows**
   - Session startup procedures
   - Memory bank loading
   - Context restoration
   - System verification
   - Task preparation

2. **Operational Workflows**
   - Memory bank updates
   - State tracking
   - Information retrieval
   - Progressive knowledge building
   - Context switching

3. **Verification Workflows**
   - Integrity checking
   - Consistency validation
   - Reference verification
   - Performance monitoring
   - Error detection and recovery

4. **Transition Workflows**
   - Session summarization
   - State preservation
   - Bedtime procedures
   - Wakeup sequence
   - Continuity maintenance

Each workflow type has specific processes, checks, and documentation requirements.
1. **Memory Bank Loading**
   - Retrieve core memory files:
     - projectbrief.md
     - productContext.md
     - activeContext.md
     - systemPatterns.md
     - techContext.md
     - progress.md
   - Verify file existence and accessibility
   - Load content into working memory
   - Note any missing or inaccessible files

2. **Context Assessment**
   - Review activeContext.md for current focus
   - Identify recent changes and current status
   - Note open issues and questions
   - Understand overall progress
   - Recognize next planned steps

3. **System Verification**
   - Check version compatibility
   - Verify cross-references
   - Validate memory bank structure
   - Confirm rule availability
   - Identify any integrity issues

4. **Task Contextualization**
   - Relate current task to project context
   - Position within implementation plan
   - Identify relevant components
   - Determine complexity level
   - Prepare appropriate resources

5. **Readiness Confirmation**
   - Verify all required information is available
   - Confirm understanding of current state
   - Identify any missing context
   - Request additional information if needed
   - Signal initialization completion

This workflow ensures proper system readiness before task execution.
1. **Change Assessment**
   - Identify what information has changed
   - Determine impacted memory files
   - Assess change significance
   - Categorize change type
   - Identify related components

Read the full file on GitHub · 487 lines

Changes

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.

  1. 6d ago First seen · 487 lines · 3,178 tokens per session scan A d8ff34727377

Subscribe to this mod's changes

800-memory-operations-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 3,178 tokens to every session, about $0.0159 per session on Opus 5. 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.