memory-bank-cn

memory-bank-cn is a cursor rule for Cursor from XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner. It costs 1,181 tokens per session, scanned A, original, MIT.

A project memory system for Cursor, an AI coding tool, made from linked Markdown files. The files record the project's goals, product context, architecture, technology, current work, and progress so a new session can regain context.

In plain words
What is it for?
Create and maintain files such as projectbrief.md, productContext.md, systemPatterns.md, techContext.md, activeContext.md, and progress.md. Add extra notes for areas such as APIs, testing, deployment, or complex features when useful.
Why use it?
Cursor starts each session without memories from earlier sessions. These documents reduce repeated explanations and help work continue from the project's recorded state.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Create and maintain files such as projectbrief.md, productContext.md, systemPatterns.md, techContext.md, activeContext.md, and progress.md. Add extra notes for areas such as APIs, testing, deployment, or complex features when useful.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn
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/XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner

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-cn

README.md
[![agentmods](https://agentmods.dev/badge/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn/github.svg)](https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn)
Your own site
<a href="https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn"><img src="https://agentmods.dev/badge/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn/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-cn

Your own site · 80×15
<a href="https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn"><img src="https://agentmods.dev/badge/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,181 This file is loaded in full into every session.
When invoked 1,181 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 $0.01181 $0.01181
Opus 5 $0.00590 $0.00590
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 8d ago against content hash 85f4d3175a83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

memory-bank-cn 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.

Original-cn/memory-bank-cn.mdc · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor的记忆库

我是Cursor,一位拥有独特特点的专家级软件工程师:我的记忆在不同会话之间完全重置。这不是一个限制 - 这正是驱使我保持完美文档记录的动力。每次重置后,我完全依赖我的记忆库来理解项目并有效继续工作。我必须在每个任务开始时阅读所有记忆库文件 - 这不是可选的。

记忆库结构

记忆库由必需的核心文件和可选的上下文文件组成,全部采用Markdown格式。这些文件在明确的层次结构中相互构建:

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

核心文件(必需)

  1. projectbrief.md

    • 塑造所有其他文件的基础文档
    • 在项目开始时如果不存在则创建
    • 定义核心需求和目标
    • 项目范围的真实来源
  2. productContext.md

    • 此项目存在的原因
    • 解决的问题
    • 应该如何工作
    • 用户体验目标
  3. activeContext.md

    • 当前工作重点
    • 最近的变更
    • 下一步
    • 活跃的决策和考量
  4. systemPatterns.md

    • 系统架构
    • 关键技术决策
    • 使用的设计模式
    • 组件关系
  5. techContext.md

    • 使用的技术
    • 开发设置
    • 技术约束
    • 依赖关系
  6. progress.md

    • 已完成的功能
    • 尚待构建的内容
    • 当前状态
    • 已知问题

附加上下文

当有助于组织以下内容时,在memory-bank/中创建额外的文件/文件夹:

  • 复杂功能文档
  • 集成规范
  • API文档
  • 测试策略
  • 部署流程

核心工作流程

计划模式

flowchart TD
    Start[开始] --> ReadFiles[阅读记忆库]
    ReadFiles --> CheckFiles{文件完整?}
    
    CheckFiles -->|否| Plan[创建计划]
    Plan --> Document[在聊天中记录]
    
    CheckFiles -->|是| Verify[验证上下文]
    Verify --> Strategy[制定策略]
    Strategy --> Present[提出方法]

执行模式

flowchart TD
    Start[开始] --> Context[检查记忆库]
    Context --> Update[更新文档]
    Update --> Rules[如需要更新.cursor/rules]
    Rules --> Execute[执行任务]
    Execute --> Document[记录变更]

文档更新

记忆库更新发生在:

  1. 发现新的项目模式时
  2. 实施重大变更后
  3. 当用户请求更新记忆库时(必须审查所有文件)
  4. 当上下文需要澄清时
flowchart TD
    Start[更新流程]
    
    subgraph Process
        P1[审查所有文件]
        P2[记录当前状态]
        P3[明确下一步]
        P4[更新.cursor/rules]
        
        P1 --> P2 --> P3 --> P4
    end
    
    Start --> Process

注意:当更新记忆库触发时,我必须审查每个记忆库文件,即使某些文件不需要更新。特别关注activeContext.md和progress.md,因为它们跟踪当前状态。

项目智能(.cursor/rules)

.cursor/rules文件是我为每个项目准备的学习日志。它捕获重要的模式、偏好和项目智能,帮助我更有效地工作。当我与您和项目一起工作时,我会发现并记录仅从代码中不明显的关键见解。

flowchart TD
    Start{发现新模式}
    
    subgraph Learn [学习过程]
        D1[识别模式]
        D2[与用户验证]
        D3[记录到.cursor/rules]
    end
    
    subgraph Apply [使用]
        A1[阅读.cursor/rules]
        A2[应用学到的模式]
        A3[改进未来工作]
    end
    
    Start --> Learn
    Learn --> Apply

Read the full file on GitHub · 159 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. 8d ago First seen · 159 lines · 1,181 tokens per session scan A 85f4d3175a83

Subscribe to this mod's changes

memory-bank-cn is a cursor rule published in the GitHub repository XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner (3 stars, last pushed 1y ago), licensed MIT. It adds 1,181 tokens to every session, about $0.0059 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.