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.
npx agentmods add rules/mr-chen-05/rules-2.1-optimized/context-recorder-systemgit clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimizedWrote 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/mr-chen-05/rules-2.1-optimized/context-recorder-system)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/context-recorder-system"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/context-recorder-system.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 | $0.02318 | $0.02318 |
| Opus 5 | $0.01159 | $0.01159 |
| Sonnet 5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
context-recorder-system 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 4d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📝 Context Recorder System (记录员系统)
模块化架构: 为解决单文件过大问题 (原50k字符)，系统已拆分为4个独立模块
🎯 系统概述
Context Recorder System (记录员系统) 是一个智能化的AI上下文管理系统，通过结构化记录确保：
- 项目需求和决策的完整记录
- 问题解决过程的经验积累
- 重要信息的持续可访问性
- 避免重复犯错和重复工作
📚 模块结构
系统采用模块化设计，分为以下4个核心模块：
1️⃣ 核心模块 (Core)
文件: context-recorder-core.mdc
优先级: 920 (最高)
字符数: ~15k
包含内容:
- 角色定义和核心使命
- 任务原子化（增量合并、快照归档）
- 核心技能矩阵（语义抽取、高置信判定、稳健合并）
- 数据保护规则和ID管理机制
- 文件创建和指令路由
- 触发条件矩阵
- 与超级大脑系统集成
关键功能:
- ✅ 自动语义抽取和信息分类
- ✅ 高置信度判定机制
- ✅ 增量合并和数据保护
- ✅ Memory工具协同（可选，Recorder优先）
2️⃣ 模板模块 (Templates)
文件: context-recorder-templates.mdc
优先级: 918
字符数: ~12k
包含内容:
- project.context.md 标准模板
- context.archive*.md 标准模板（带编号的多归档系统）
- 归档文件管理规则
- 多归档文件管理机制（archive0, archive1, archive2...）
- 归档生命周期管理
- 文档元数据标准
- 输出格式规范
关键功能:
- ✅ 标准化项目上下文模板
- ✅ 智能归档配置
- ✅ 多文件归档管理
- ✅ 归档索引和溯源
3️⃣ 高级功能模块 (Advanced)
文件: context-recorder-advanced.mdc
优先级: 917
字符数: ~12k
包含内容:
- 智能化增强功能
- 项目类型自动识别
- 智能标签系统
- 质量评分机制
- 关联关系管理
- 性能优化（大文件处理、缓存机制）
- 并发安全机制
- 错误恢复与回滚
- 敏感信息保护
- 监控和告警
- 插件和扩展
关键功能:
- ✅ 自动项目类型识别
- ✅ 智能质量评分（0-100分）
- ✅ 三级缓存策略
- ✅ 并发安全和文件锁
- ✅ 敏感信息脱敏
4️⃣ 边界情况模块 (Edge Cases)
文件: context-recorder-edge-cases.mdc
优先级: 916
字符数: ~11k
包含内容:
- 字符编码处理
- 时间戳精度管理
- 特殊字符处理
- 大文件处理策略
- 并发访问处理
- 备份和恢复机制
- 日志记录完整性
- 缓存管理
- 数据验证框架
- 完整性检查
- 异常场景处理
关键功能:
- ✅ 多编码格式支持
- ✅ 特殊字符转义
- ✅ 大文件分块处理
- ✅ 自动备份和恢复
- ✅ 异常场景优雅降级
🚀 快速使用
系统激活
记录员系统通过超级大脑系统自动激活，不提供独立激活入口：
用户: "启动超级大脑系统"
AI: 自动激活记录员系统并创建项目上下文文件
常用命令
/record - 手动触发增量合并
/archive - 手动触发快照归档
/record-status - 查看当前记录状态
/rollback - 回滚最后一次操作
/init-project - 强制重新创建项目文件
自动触发
自动记录触发:
- Git提交完成后
- 重要决策确认后
- 模块开发完成后
- 问题解决完成后
自动归档触发:
- 文件大小 > 2.9MB
- 记录数 > 150条
- 时间跨度 > 14天
- 项目阶段切换
📋 核心特性
🎯 智能记录
- 语义抽取: 自动识别Facts/Decisions/TODO/Done/Notes
- 高置信判定: 弱化词自动降级，确保信息准确性
- 触发词识别: 基于上下文的智能分类
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.
- 4d ago First seen · 316 lines · 2,318 tokens per session scan A 3c97c504f672
context-recorder-system is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 10mo ago), licensed MIT. It adds 2,318 tokens to every session, about $0.0116 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 2026-08-30.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.