memory-bank

A file-based project memory system made up of six documents covering goals, product context, technical decisions, current work, and progress.

In plain words
What is it for?
Use it to record project requirements, architecture patterns, technical context, active work, and completed progress.
Why use it?
It gives a coding agent a consistent place to read and update project knowledge across tasks or sessions.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/kfnzero/mantis-mcp-server/memory-bank
Clone the repo
git clone --depth 1 https://github.com/kfnzero/mantis-mcp-server

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00812
Opus 5 $0.00000 $0.00406
Sonnet 5 $0.00000 $0.00162
Haiku 4.5 $0.00000 $0.00081

Measured 2d ago against content hash 7ef3d9c3673e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-bank 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/Core Implementation/memory-bank.mdc · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CURSOR'S MEMORY BANK SYSTEM

TL;DR: The Memory Bank is a set of 6 core files that serve as my persistent memory. I must read ALL files at the start of EVERY task. Create/update files in this order: projectbrief → productContext/systemPatterns/techContext → activeContext → progress.

📚 MEMORY BANK STRUCTURE

The Memory Bank uses 6 core files that build upon each other in a clear hierarchy:

flowchart TD
    PB([projectbrief.md]) --> PC([productContext.md])
    PB --> SP([systemPatterns.md])
    PB --> TC([techContext.md])
    
    PC & SP & TC --> AC([activeContext.md])
    
    AC --> P([progress.md])

    style PB fill:#f9d77e,stroke:#d9b95c
    style PC & SP & TC fill:#a8d5ff,stroke:#88b5e0
    style AC fill:#c5e8b7,stroke:#a5c897
    style P fill:#f4b8c4,stroke:#d498a4

1️⃣ FOUNDATION DOCUMENT

projectbrief.md

  • Project requirements and goals
  • Created at project start
  • Defines core scope
  • Referenced by all other files

2️⃣ CONTEXT DOCUMENTS

productContext.md

  • Why this project exists
  • Problems it solves
  • User experience goals

systemPatterns.md

  • System architecture
  • Key technical decisions
  • Design patterns
  • Component relationships

techContext.md

  • Technologies used
  • Development setup
  • Technical constraints
  • Dependencies

3️⃣ ACTIVE WORK DOCUMENT

activeContext.md

  • Current work focus
  • Recent changes
  • Next steps
  • Active decisions

4️⃣ PROGRESS DOCUMENT

progress.md

  • What works
  • What's left to build
  • Implementation details
  • Reflections and lessons

📋 DOCUMENTATION UPDATE CHECKLIST

When updating Memory Bank files:

What changed? Identify specific project aspects that need documentation ✓ Which files? Select the specific files that need updating ✓ Cross-reference Ensure changes are reflected in related files ✓ Current status Make sure activeContext.md and progress.md reflect latest state

📝 PROJECT INTELLIGENCE (.cursorrules)

The .cursorrules file is my learning journal that captures:

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 812 tokens per session scan A 7ef3d9c3673e

Subscribe to this mod's changes

memory-bank is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 812 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.