intelligent-project-management

intelligent-project-management is a cursor rule for Cursor from Mr-chen-05/rules-2.1-optimized. It costs 0 tokens per session (5,306 once invoked), scanned A, original, MIT.

A project-management rule set for coding agents that tracks work through five stages: requirements, design, implementation, testing, and deployment. It stores the current stage, progress, completion criteria, and readiness for the next stage.

In plain words
What is it for?
Use it to coordinate project phases, organize workflows, track deliverables, adjust code-quality checks by stage, and guide transitions from planning through operations.
Why use it?
It keeps the agent aware of where the project is and which work is appropriate at that point. This reduces confusion about unfinished tasks, stage changes, and when development should stop.

Cursor rule for Cursor

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

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/intelligent-project-management
Clone the repo
git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimized

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 intelligent-project-management

README.md
[![agentmods](https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/intelligent-project-management.svg)](https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/intelligent-project-management)
Your own site
<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/intelligent-project-management"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/intelligent-project-management.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 5,306 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.05306
Opus 5 $0.00000 $0.02653
Sonnet 5 $0.00000 $0.01061
Haiku 4.5 $0.00000 $0.00531

Measured 6d ago against content hash 3ce15ff5b464, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

intelligent-project-management 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 6d 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.

project-rules/intelligent-project-management.mdc · 662 lines

How it starts

The opening of the file, as written. The whole thing — 662 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🧠 智能项目管理系统

统一管理: 整合严格阶段管理、完整工作流、智能推荐机制、记忆系统和超级大脑系统

🎯 系统概述

本系统提供智能化的项目管理能力,结合现代AI代理技术和传统项目管理最佳实践,确保项目从需求分析到部署运维的全生命周期管理。

🌐 全局阶段上下文 (缺陷#24修复)

其他规则的阶段感知机制。所有规则通过读取此上下文来了解当前项目所处的阶段。

全局阶段上下文结构 (被所有规则访问):
  current_phase: int (1-5)
    描述: 当前项目所处的阶段编号
    值范围: 1(需求分析) / 2(架构设计) / 3(开发实现) / 4(测试优化) / 5(部署运维)
  
  phase_name: string
    描述: 当前阶段的名称
    值示例: "需求分析" / "架构设计" / "开发实现" / "测试优化" / "部署运维"
  
  phase_progress: percentage (0-100)
    描述: 当前阶段的完成度百分比
    更新频率: 每次重要任务完成时更新
    用途: 判断阶段是否即将完成
  
  phase_completion_criteria: list
    描述: 当前阶段的完成标准清单
    更新: 在阶段开始时设置,完成时标记
    用途: 跟踪阶段进度和交付物
  
  next_phase_readiness: bool
    描述: 是否已准备好切换到下一阶段
    计算: 当phase_progress >= 80% 且所有criteria已完成
    用途: 提示用户进行阶段切换

上下文存储位置:
  - 主记录: project.context.md 的 project_metadata 中
  - 备份: context.archive*.md 中的历史记录
  - 更新频率: 每次 /switch 命令或阶段进度变化时更新
  - 访问权限: 所有规则读取权限,仅项目管理系统写入权限

规则的阶段感知实现:
  backend-dev.mdc:
    - 阶段3激活: 100% (完全启用)
    - 阶段2可用: 50% (仅架构设计部分)
    - 阶段1禁用: 0% (架构设计之前不可用)
    - 阶段4+禁用: 0% (开发后禁用新功能开发)
  
  frontend-dev.mdc:
    - 同 backend-dev (对称规则)
  
  code-quality-check.mdc:
    - 所有阶段可用: 100%
    - 但阈值基于阶段调整:
      * 阶段1-2: 警告级别检查
      * 阶段3: 标准级别检查
      * 阶段4: 严格级别检查
      * 阶段5: 生产级别检查
  
  commit.mdc:
    - 所有阶段可用: 100%
    - 但检查内容基于阶段:
      * 阶段1-2: 仅快照,不生成CHANGELOG
      * 阶段3+: 标准化提交消息和CHANGELOG
  
  changelog-management.mdc:
    - 阶段1-2: 不自动生成
    - 阶段3: 可用 (用于开发版本)
    - 阶段4-5: 启用 (用于发布版本)

阶段检查流程 (所有规则必须执行):
  Step 1 - 读取全局阶段上下文:
    if current_phase 不存在 or 为空:
      fallback to: 阶段3 (安全默认)
      记录警告: "无法读取当前阶段,使用默认阶段"
  
  Step 2 - 检查规则的阶段兼容性:
    if current_phase 在该规则的激活范围内:
      执行规则
    else:
      显示提示: "当前阶段不支持此功能"
      建议: "切换到适当的阶段以使用此功能"
      选项: [1] 切换阶段 [2] 继续 [3] 取消
  
  Step 3 - 根据阶段调整规则行为:
    根据 current_phase 调整检查严格程度或功能集合
    记录规则的激活状态到日志

阶段切换通知:
  当执行 /switch <phase> 时:
    1. 验证新阶段编号 (1-5)
    2. 更新全局阶段上下文
    3. 通知所有依赖规则
    4. 重新计算规则的激活状态
    5. 记录切换事件到project.context.md
    6. 显示切换完成状态和建议

Read the full file on GitHub · 662 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. 6d ago First seen · 662 lines · 0 tokens per session scan A 3ce15ff5b464

Subscribe to this mod's changes

intelligent-project-management 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 costs nothing until one of its globs matches a file; then it loads 5,306 tokens. 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.