memory-bank-paths

memory-bank-paths is a cursor rule for Cursor from Angry-Robot-Deals/ace-mcp. It costs 384 tokens per session, scanned A, a copy of memory-bank-paths, MIT.

A set of fixed locations for the project's Memory Bank files, a collection of Markdown files that stores task details, project context, technical notes, and progress. It also explains how active task information is archived when work is complete.

In plain words
What is it for?
Use it to find or update task tracking, project context, progress, technical patterns, style guidance, creative documents, and archived task records.
Why use it?
It prevents important project notes from being scattered across different folders or lost during task cleanup.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to find or update task tracking, project context, progress, technical patterns, style guidance, creative documents, and archived task records.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/angry-robot-deals/ace-mcp/memory-bank-paths
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/Angry-Robot-Deals/ace-mcp

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 memory-bank-paths

README.md
[![agentmods](https://agentmods.dev/badge/rules/angry-robot-deals/ace-mcp/memory-bank-paths/github.svg)](https://agentmods.dev/rules/angry-robot-deals/ace-mcp/memory-bank-paths)
Your own site
<a href="https://agentmods.dev/rules/angry-robot-deals/ace-mcp/memory-bank-paths"><img src="https://agentmods.dev/badge/rules/angry-robot-deals/ace-mcp/memory-bank-paths/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.

agentmods 80×15 button for memory-bank-paths

Your own site · 80×15
<a href="https://agentmods.dev/rules/angry-robot-deals/ace-mcp/memory-bank-paths"><img src="https://agentmods.dev/badge/rules/angry-robot-deals/ace-mcp/memory-bank-paths.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 384 This file is loaded in full into every session.
When invoked 384 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 97% copy Near-identical to another mod 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 $0.00384 $0.00384
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured 10d ago against content hash 2f58a650a625, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

memory-bank-paths 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 10d 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

This is a copy

97% identical to memory-bank-paths — 2 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.

.cursor/rules/isolation_rules/Core/memory-bank-paths.mdc · 24 lines

What it actually says

CORE MEMORY BANK FILE LOCATIONS

CRITICAL: All core Memory Bank files reside within the memory-bank/ directory at the project root. Do NOT create or modify these files outside this directory unless explicitly instructed for archiving purposes.

  • Tasks File: memory-bank/tasks.md - This file is used for active, in-progress task tracking, detailing steps, checklists, and component lists. Its content, particularly the detailed checklists, is merged into the main archive document for the task upon completion. After archival, tasks.md is cleared to be ready for the next task. It is an ephemeral working document during a task's lifecycle, with its persistent record captured in the task's archive file.
  • Active Context File: memory-bank/activeContext.md
  • Progress File: memory-bank/progress.md
  • Project Brief File: memory-bank/projectbrief.md
  • Product Context File: memory-bank/productContext.md
  • System Patterns File: memory-bank/systemPatterns.md
  • Tech Context File: memory-bank/techContext.md
  • Style Guide File: memory-bank/style-guide.md
  • Creative Phase Docs: memory-bank/creative/creative-[feature_name].md
  • Reflection Docs: memory-bank/reflection/reflection-[task_id].md
  • Archive Directory: docs/archive/archive-[task_id].md

Verification Mandate: Before any create_file or edit_file operation on these core files, verify the path starts with memory-bank/. If attempting to create a new core file (e.g., tasks.md at the start of a project), ensure it is created at memory-bank/tasks.md.

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. 10d ago First seen · 24 lines · 384 tokens per session scan A 2f58a650a625

Subscribe to this mod's changes

memory-bank-paths is a cursor rule published in the GitHub repository Angry-Robot-Deals/ace-mcp (4 stars, last pushed 6mo ago), licensed MIT. It adds 384 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to memory-bank-paths, differing in 2 lines, and is treated as a copy.