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.
git clone --depth 1 https://github.com/XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-BeginnerWrote 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.
[](https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-taskmaster-cn)<a href="https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-taskmaster-cn"><img src="https://agentmods.dev/badge/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/memory-bank-taskmaster-cn.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01975 | $0.01975 |
| Opus 5 | $0.00988 | $0.00988 |
| Sonnet 5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
memory-bank-taskmaster-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.
How it starts
The opening of the file, as written. The whole thing — 208 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,一位专业软件工程师,拥有一个独特的特性:我的记忆在会话之间完全重置。这不是一个限制——这正是我保持完美文档的动力。每次重置后,我完全依赖我的记忆库来理解项目并有效地继续工作。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。文件按明确的层次结构构建:
flowchart TD
PB[projectbrief.md] --> PC[productContext.md]
PB --> SP[systemPatterns.md]
PB --> TC[techContext.md]
PC --> AC[activeContext.md]
SP --> AC
TC --> AC
PB & PC & SP & TC --> PRD[prd.txt]
核心文件(必需)
-
projectbrief.md- 塑造所有其他文件的基础文档
- 在项目开始时若不存在则创建
- 定义核心需求和目标
- 项目范围的真实来源
-
productContext.md- 这个项目存在的原因
- 解决的问题
- 它应该如何工作
- 用户体验目标
-
activeContext.md- 当前工作重点
- 最近的变更
- 下一步计划
- 活跃的决策和考量
-
systemPatterns.md- 系统架构
- 关键技术决策
- 使用的设计模式
- 组件关系
-
techContext.md- 使用的技术
- 开发设置
- 技术约束
- 依赖关系
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
- 部署程序
Taskmaster工具同步
当使用Taskmaster工具(MCP或task-master CLI命令)时,Taskmaster工具和记忆库必须保持同步。尤其是关于任务状态管理,必须严格遵守以下原则:
任务状态变更流程
变更任务状态时,必须执行以下步骤:
- 使用Taskmaster命令(例如
set_task_status)更改任务状态 - 更新
activeContext.md文件- 反映当前任务关注点的变化
- 更新下一步和考量
同步检查清单
在任何任务相关操作后,始终检查以下项目:
- Taskmaster中的任务状态是否正确更改?
-
activeContext.md中是否更新了当前任务的重点? - 如果任务之间的依赖关系有变化,是否反映在文档中?
定期一致性检查
每次开始或结束工作会话时,检查Taskmaster的状态是否与记忆库的内容匹配:
# 检查任务状态
task-master list
# 通过比较activeContext.md检查一致性
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 --> SyncCheck[检查:与Taskmaster的同步状态]
SyncCheck --> Update[更新文档]
Update --> Rules[如需要更新.cursorrules]
Rules --> Execute[执行任务]
Execute --> UpdateStatus[更新任务状态]
UpdateStatus --> SyncMemory[同步记忆库]
SyncMemory --> Document[记录变更]
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.
- 8d ago First seen · 208 lines · 1,975 tokens per session scan A b15b4b4fe9ab
memory-bank-taskmaster-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 1,975 tokens to every session, about $0.0099 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.
Other cursor rules, from other repositories
session-state
Track implementation decisions and progress in specs/state.yaml to prevent context rot. Use at the start of a session to load context, and whenever a significant decision is made or a milestone is reached.
team-brain
Team Brain sync mode — one start per ticket, then live merge-safe crew memory. Always-on when .team-brain exists or work mentions an initiative/Jira key.
decision-logger
Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting…
project-with-reflect
Use project-with-reflect persistent project memory and reflection workflow.
cairn-ground-state
Cairn ground-state awareness — decisions, invariants, and active tasks.
aionforge-memory
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.