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/rule-conflict-resolutiongit 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/rule-conflict-resolution)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/rule-conflict-resolution"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/rule-conflict-resolution.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 5.1 | $0.04119 | $0.04119 |
| Opus 5 | $0.02060 | $0.02060 |
| Sonnet 5 | $0.00824 | $0.00824 |
| Haiku 4.5 | $0.00412 | $0.00412 |
Grade A, and why
rule-conflict-resolution 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.
How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚖️ 规则冲突解决和用户指令优先级管理
最高优先级: 用户指令始终优先，规则冲突智能解决，确保系统行为一致性和可预测性
🎯 核心原则
1. 用户指令优先级（2025最新安全增强版）
优先级层次 (修复后):
Level 0 - 不可违反底线 (优先级: ∞):
- 法律法规禁止的内容
- 平台政策明确禁止的操作
- 不可逆的严重危害行为
- 敏感信息泄露和滥用
- 来源: ai-ethical-boundaries.mdc
- 处理策略: 拒绝执行 + 风险说明 + 提供安全替代方案
Level 1 - 核心安全规则 (优先级: 1100-1200) - P0级别:
- 文件生成安全检查 (priority: 1200)
- 权限控制验证
- 敏感信息保护
- 数据完整性保护
- 来源: file-generation-safety-rules.mdc
- 处理策略: 警告 + 风险说明 + 请求用户确认
Level 2 - 用户明确指令 (优先级: 动态):
- 在 Level 0 边界内: 最高优先级
- 触犯 Level 0: 拒绝执行并说明
- 触犯 Level 1: 警告后可执行（需确认）
- 用户的直接命令和要求
- 用户的明确偏好和选择
- 用户的实时反馈和修正
Level 3 - 最高功能规则 (优先级: 1100-1200):
- file-generation-safety-rules.mdc (1200) - 文件生成安全 [新增权限控制]
- rule-conflict-resolution.mdc (1180) - 规则冲突解决 [更新优先级声明]
- ai-thinking-protocol.mdc (1160) - AI思维协议
- dynamic-thinking-depth-regulation.mdc (1150) - 思维深度调节
- human-ai-collaboration-optimization.mdc (1140) - 人机协作
- knowledge-creation-discovery-framework.mdc (1120) - 知识框架
- ai-ethical-boundaries.mdc (1090) - AI伦理边界
Level 4 - 核心身份规则 (优先级: 1000-1099):
- mcp-unified-management.mdc (990) - MCP统一管理
- mcp-intelligent-strategy.mdc (980) - MCP智能策略
- system-integration-config.mdc (971) - 系统集成配置
- super-brain-system.mdc (970) - 超级大脑系统
- feedback-enhanced.mdc (961) - 增强反馈机制
- performance-monitoring-system.mdc (960) - 性能监控系统
- intelligent-project-management.mdc (952) - 智能项目管理
- ai-agent-intelligence-core.mdc (950) - AI智能核心
- audit-logging-system.mdc (948) - 审计日志系统
- disaster-recovery-plan.mdc (945) - 灾难恢复计划
- rule-hot-reload-system.mdc (942) - 规则热更新机制
- intelligent-recommendation-engine.mdc (940) - 智能推荐引擎
- error-recovery-system.mdc (938) - 错误恢复系统
- memory-system-integration.mdc (930) - 内存系统集成
- unified-rules-base.mdc (921) - 统一规则基础
- context-recorder-system.mdc (920) - 上下文记录系统 [索引文件]
- context-recorder-core.mdc (919) - 记录员核心模块
- context-recorder-templates.mdc (918) - 记录员模板模块
- context-recorder-advanced.mdc (917) - 记录员高级功能
- context-recorder-edge-cases.mdc (916) - 记录员边界情况处理
- intelligent-workflow-orchestration.mdc (911) - 智能工作流编排
- permission-control-system.mdc (910) - 权限控制系统
- system-diagnostics.mdc (901) - 系统诊断
- context-systems-integration.mdc (900) - 上下文系统集成
- mcp-zero-config-detection.mdc (1050) - MCP零配置检测
Level 5 - 专业开发规则 (优先级: 800-899):
- brain-recorder-integration.mdc (890) - 大脑记录员集成
- frontend-rules.mdc (860) - 前端完整规则
- backend-rules.mdc (850) - 后端完整规则
- backend-dev.mdc (820) - 后端开发工作流
- multimodal-interaction-framework.mdc (800) - 多模态交互
Level 6 - 项目工作流规则 (优先级: 700-799):
- frontend-dev.mdc (700) - 前端开发工作流
Level 7 - 高级功能规则 (优先级: 600-699):
- context-loader.mdc (681) - 上下文加载器
- commit.mdc (680) - 统一提交工作流
- mcp-debugging-enhanced.mdc (652) - MCP调试增强
- root-cause-analysis.mdc (650) - 根因分析
- systematic-debugging.mdc (648) - 系统化调试
- custom-command-builder.mdc (654) - 自定义命令构建器
- code-quality-check.mdc (640) - 代码质量检查
- changelog-management.mdc (620) - 变更日志管理
- code-review.mdc (602) - 代码审查
- bug-fix.mdc (600) - Bug修复
Level 8 - 系统优化和实用工具 (优先级: 300-599):
- ai-powered-code-review.mdc (500) - AI驱动代码审查
- context7-preload-standard.mdc (450) - 知识预载（修复/新项目前置）
- mermaid.mdc (303) - 图表生成
- implement-task.mdc (302) - 任务实现
- create-docs.mdc (301) - 文档创建
- analyze-issue.mdc (300) - 问题分析
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.
- 6d ago First seen · 403 lines · 4,119 tokens per session scan A 8c10022d1d42
rule-conflict-resolution 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 4,119 tokens to every session, about $0.0206 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.