What is evolution-manual?

A set of Chinese-language rules for manually reviewing and updating project rules over time. It requires discussion, testing, records of changes, approval for core-rule edits, consistency, and backups.

Reviewing rule effectiveness, handling conflicts, adapting rules to technology or team changes, and recording and validating updates.

It provides a controlled process for changing rules when projects, technology, teams, or rule conflicts change.

evolution-manual — Cursor rule by wangqiqi

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/wangqiqi/cursor-ai-rules/evolution-manual

Clone the repo

git clone --depth 1 https://github.com/wangqiqi/cursor-ai-rules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 1,211 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01211
Opus 5	$0.00000	$0.00606
Sonnet 5	$0.00000	$0.00242
Haiku 4.5	$0.00000	$0.00121

Measured 3d ago against content hash f28eb2b38d3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolution-manual 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.

.cursor/rules/evolution/evolution-manual.mdc · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

📋 手动演进流程 (Manual Evolution Process)

版本: v4.3.0 | 最后更新: {{GENERATION_TIME}} | 作者: wangqiqi (https://github.com/wangqiqi)

⚠️ 执行原则

MUST 遵循以下手动演进准则：

MUST 在修改规则前进行充分讨论
NEVER 跳过测试和验证步骤
ALWAYS 记录演进原因和变更内容
DO NOT 在未经批准的情况下修改核心规则
MUST 保持规则间的一致性
ALWAYS 备份当前规则版本

🎯 演进触发机制 (Evolution Triggers)

🔄 定期演进 (Regular Evolution)

里程碑回顾 (Milestone Reviews)

触发时机: 每完成一个主要功能、版本发布、季度结束 检查清单:

规则执行效果评估
流程效率分析
团队反馈收集
改进建议整理

月度回顾 (Monthly Reviews)

触发时机: 每月最后一个工作日 检查清单:

本月规则使用统计
发现的问题和解决方案
新需求和技术挑战
团队协作效率评估

⚡ 事件驱动演进 (Event-Driven Evolution)

规则冲突处理 (Rule Conflicts)

触发条件: 发现规则之间存在矛盾或冲突 处理流程:

识别冲突的具体表现和影响
分析冲突的根本原因和涉及规则
制定解决方案并评估影响
实施修改并验证效果
更新相关文档和团队通知

技术栈变化适配 (Technology Stack Changes)

触发条件: 项目引入新的技术栈或框架 处理流程:

评估新技术栈对现有规则的影响范围
制定相应的规则更新计划和时间表
创建新规则或修改现有规则
逐步引入并进行团队培训

团队变化响应 (Team Changes)

触发条件: 团队成员、规模或结构发生变化 处理流程:

了解新的团队动态和协作模式
评估现有规则的适用性和复杂度
根据团队规模调整规则的严格程度
更新沟通和协作规范

📊 演进评估指标 (Evolution Metrics)

效率指标 (Efficiency Metrics)

开发周期: 功能从需求到上线的平均时间
代码审查时间: PR从提交到合并的平均时间
缺陷密度: 每千行代码的缺陷数量
部署频率: 每周/月的部署次数

质量指标 (Quality Metrics)

测试覆盖率: 单元测试和集成测试覆盖率
代码质量评分: 静态分析工具评分
安全漏洞: 已知安全漏洞数量
文档完整性: 技术文档覆盖率

协作指标 (Collaboration Metrics)

沟通效率: 会议时间 vs 决策时间比
知识共享: 文档更新频率和技术分享次数
冲突解决时间: 从问题发现到解决的平均时间
团队满意度: 定期团队健康度调查

🔧 实施指南 (Implementation Guide)

数据收集 (Data Collection)

收集清单：
- [ ] 规则使用频率和执行时间统计
- [ ] 团队成员反馈和建议记录
- [ ] 遇到的困难和解决方案日志
- [ ] 当前规则的实际效果评估

问题分析 (Problem Analysis)

分析框架：
- **频率**: 问题发生的频率高低
- **影响**: 对开发效率的影响程度
- **根因**: 问题的根本原因分析
- **趋势**: 问题是否在增加或减少

解决方案制定 (Solution Development)

解决方案要素：
- **目标**: 明确的改进目标
- **方法**: 具体的实施步骤
- **资源**: 所需的时间和人力
- **衡量**: 成功标准的定义

实施与验证 (Implementation & Validation)

实施步骤：
1. [ ] 制定详细的实施计划
2. [ ] 准备必要的资源和工具
3. [ ] 分阶段实施变更
4. [ ] 收集反馈并调整
5. [ ] 验证改进效果
6. [ ] 固化成功经验

---

*手动演进流程提供了结构化的规则改进方法，确保演进过程的可控性和有效性。*

Read the full file on GitHub · 132 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.

3d ago First seen · 132 lines · 0 tokens per session scan A f28eb2b38d3e

Subscribe to this mod's changes

evolution-manual is a cursor rule published in the GitHub repository wangqiqi/cursor-ai-rules (15 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,211 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.

Building agents

evolution-manual