context-systems-integration

A coordination design for three project-context systems: one analyzes a project, one records ongoing work, and one gathers task-specific knowledge. It defines their responsibilities, triggers, outputs, and handoffs.

In plain words
What is it for?
Analyzing a new project, preparing background before a task, recording progress and decisions, maintaining project context files, and archiving older context.
Why use it?
It prevents overlapping context systems from doing the same work or losing important decisions. It keeps project analysis, task preparation, and long-term records connected.

Cursor rule

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/mr-chen-05/rules-2.1-optimized/context-systems-integration
Clone the repo
git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimized
Per session 2,769 This file is loaded in full into every session.
When invoked 2,769 The same file — it is already loaded in full.
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 $0.02769 $0.02769
Opus 5 $0.01385 $0.01385
Sonnet 5 $0.00554 $0.00554
Haiku 4.5 $0.00277 $0.00277

Measured 3d ago against content hash 62206af05178, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-systems-integration 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 3d 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.

global-rules/context-systems-integration.mdc · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔗 Context Systems Integration - 上下文系统集成

解决 Context Loader 与记录员系统的功能重叠,实现协同工作和智能分工。

🎯 系统分工定义

Context Loader (项目分析器)

主要职责:
  - 项目技术栈识别和分析
  - 代码结构和架构模式分析
  - 开发工具和配置推荐
  - 项目健康度评估
  - 一次性深度项目分析

触发时机:
  - 首次接触新项目
  - 项目结构发生重大变化
  - 用户主动请求项目分析
  - 技术栈升级或迁移

输出内容:
  - 项目技术栈报告
  - 配置推荐建议
  - 项目健康度评分
  - 改进建议清单

Context Recorder (记录员系统)

主要职责:
  - 持续的项目进度记录
  - 决策和任务状态跟踪
  - 问题和解决方案归档
  - 增量式上下文更新
  - 长期项目记忆管理

触发时机:
  - 每次对话和任务执行
  - 重要决策制定时
  - 问题解决过程中
  - 项目里程碑达成

输出内容:
  - project.context.md (实时状态)
  - context.archive*.md (历史归档,多归档文件支持)
  - 任务进度跟踪
  - 决策记录链

### Context7(知识引擎)
```yaml
主要职责:
  - 针对性知识检索与聚合(架构、接口、约束、历史决策、相关代码)
  - 在具体任务执行前进行知识预载(Bug 修复/新项目/新功能)
  - 为工作流提供“最小充分理解”所需材料
触发时机:
  - /analyze-issue、/implement-task、/frontend-dev、/backend-dev 之前
  - 检测到错误关键词或新项目初始化意图
输出内容:
  - 知识预载摘要(关键结论、文件链接、风险与约束、下一步建议)
  - 写入 project.context.md 的 Pinned/Notes,并触发用户确认
协同声明:
  - Context Loader 负责首次深度项目分析;Context7 专注于任务前置知识预载
  - 记录员系统接收预载摘要并维护连续上下文

## 🔄 协同工作流程

### 1. 项目初始化阶段
```yaml
Step 1 - Context Loader 启动:
  - 执行深度项目分析
  - 生成技术栈报告
  - 提供配置推荐
  - 评估项目健康度

Step 2 - 记录员系统接管:
  - 基于 Context Loader 分析结果初始化 project.context.md
  - 将技术栈信息记录到 Pinned 区块
  - 将配置推荐转化为 TODO 任务
  - 开始持续记录模式

集成数据流:
  Context Loader 分析结果 → 记录员系统 Pinned 区块
  配置推荐 → TODO 任务列表
  项目健康度 → Notes 区块

2. 日常开发阶段

记录员系统主导:
  - 持续记录开发进度
  - 跟踪任务状态变化
  - 记录决策和问题解决
  - 维护项目上下文连续性

Context Loader 辅助:
  - 仅在重大变化时重新分析
  - 提供技术栈更新建议
  - 监控项目健康度变化

3. 项目重构/升级阶段

双系统协作:
  - Context Loader 重新分析项目变化
  - 记录员系统记录重构决策过程
  - 新的分析结果更新到 project.context.md
  - 重构任务纳入 TODO 管理

🚫 冲突避免机制

功能边界清晰化

Context Loader 不应该:
  - 创建或修改 project.context.md
  - 进行持续的状态跟踪
  - 记录具体的任务执行过程
  - 管理长期项目记忆

记录员系统不应该:
  - 进行深度技术栈分析
  - 提供配置推荐建议
  - 评估项目健康度
  - 分析代码架构模式

数据交换协议

Context Loader → 记录员系统:
  数据格式: 结构化分析报告
  传递方式: 通过 Pinned 区块记录关键信息
  更新频率: 仅在重大变化时

记录员系统 → Context Loader:
  数据格式: 项目变化通知
  传递方式: 通过状态变化触发重新分析
  更新频率: 检测到重大项目变化时

Read the full file on GitHub · 350 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. 3d ago First seen · 350 lines · 2,769 tokens per session scan A 62206af05178

Subscribe to this mod's changes

context-systems-integration is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 9mo ago), licensed MIT. It adds 2,769 tokens to every session, about $0.0138 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.