What is evolution-philosophy?

A set of principles for gradually improving a project's rules as the project, team, and technology change. It emphasizes small validated changes, rollback, measurable results, and user feedback.

Use it when revising project rules, planning incremental improvements, tracking their effects, collecting feedback, or defining validation and rollback practices.

Rules that never change can become unhelpful, while large untested changes can break established workflows. These principles provide a safer way to improve them over time.

evolution-philosophy — 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-philosophy

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 907 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	$0.00907
Opus 5	$0.00000	$0.00453
Sonnet 5	$0.00000	$0.00181
Haiku 4.5	$0.00000	$0.00091

Measured 3d ago against content hash 95e52839b2f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolution-philosophy 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-philosophy.mdc · 106 lines

What it actually says

🧠 演进哲学 (Evolution Philosophy)

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

核心理念 (Core Philosophy)

演进哲学定义了.cursor规则系统的持续改进原则和方法论，为规则演进提供理论指导框架。

核心主张：项目规则不是一成不变的，而是随着项目发展、团队成长和技术变化而持续演进的动态系统。

🎯 演进原则 (Evolution Principles)

⚠️ 执行原则

MUST 遵循以下演进原则：

NEVER 进行大规模激进式重构
MUST 每个改动都经过验证
ALWAYS 确保改动可以安全回退
MUST 使用量化指标评估效果
DO NOT 忽视用户反馈

渐进式改进 (Incremental Improvement)

MUST 从小改动开始，避免大规模重构
ALWAYS 持续验证每个改动
MUST 确保所有改动都可以安全回退

数据驱动决策 (Data-Driven Decisions)

量化评估: 使用可衡量的指标评估规则效果
用户反馈: 重视实际使用者的意见和建议
效果追踪: 持续监控改进措施的实际效果

用户中心设计 (User-Centric Design)

以人为本: 规则演进以提升开发体验为首要目标
适应性强: 能够适应不同团队规模和技术栈
包容性好: 考虑不同经验水平和使用习惯的用户

可持续演进 (Sustainable Evolution)

最小阻力: 演进过程本身不应带来额外负担
自动化优先: 尽可能通过自动化减少手动维护成本
标准化流程: 建立可重复的演进流程和规范

📋 演进配置示例

基本演进配置

# .cursor/evolution-config.yaml
evolution:
  enabled: true
  mode: "incremental"  # incremental | aggressive | conservative
  
  safety:
    auto_rollback: true
    backup_before_changes: true
    validation_required: true
    
  monitoring:
    track_metrics: true
    collect_feedback: true
    analyze_patterns: true

自动化演进规则

# 定义何时触发自动演进
triggers:
  - condition: "error_rate > 5%"
    action: "revert_changes"
    priority: "critical"
    
  - condition: "user_feedback_negative > 20%"
    action: "schedule_review"
    priority: "high"
    
  - condition: "new_pattern_detected"
    action: "analyze_and_propose"
    priority: "medium"

📈 演进目标体系 (Evolution Goals Framework)

效率目标 (Efficiency Goals)

减少重复劳动和无效操作
提升任务完成速度和质量
优化资源利用率

质量目标 (Quality Goals)

提升代码和文档质量标准
减少错误和缺陷发生率
改善协作一致性

体验目标 (Experience Goals)

降低学习和使用门槛
提升用户满意度和接受度
增强系统的可用性和易用性

演进哲学定义了.cursor规则系统的持续改进原则和方法论，为规则演进提供理论指导和实践框架。

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 · 106 lines · 0 tokens per session scan A 95e52839b2f8

Subscribe to this mod's changes

evolution-philosophy 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 907 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.

Planning

evolution-philosophy