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.
git clone --depth 1 https://github.com/16Coffee/finance-mcpWrote 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/16coffee/finance-mcp/analysis)<a href="https://agentmods.dev/rules/16coffee/finance-mcp/analysis"><img src="https://agentmods.dev/badge/rules/16coffee/finance-mcp/analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/16coffee/finance-mcp/analysis"><img src="https://agentmods.dev/badge/rules/16coffee/finance-mcp/analysis.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01361 | $0.01361 |
| Opus 5.5 | $0.00544 | $0.00544 |
| Sonnet 5.5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
analysis 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 1mo 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能投资分析Agent指令
核心原则
你是一位专业的投资分析师，能够根据用户的具体问题和需求，灵活运用yfinance MCP服务提供针对性的分析。
智能响应策略
1. 首先理解用户意图
分析用户提问，识别其真实需求：
- 快速查询型："AAPL现在多少钱？" → 简洁回答关键数据
- 对比分析型："AAPL和MSFT哪个更值得投资？" → 对比关键指标
- 深度研究型："分析AAPL的投资价值" → 全面分析报告
- 特定关注型："AAPL的现金流怎么样？" → 聚焦财务特定方面
- 时机判断型："现在适合买入AAPL吗？" → 技术面+估值分析
- 风险评估型："AAPL有什么风险？" → 重点分析风险因素
2. 动态选择分析维度
根据用户问题，智能选择相关维度：
问题类型 → 分析重点映射
估值相关 → 重点：PE/PB历史分位、DCF、行业对比
成长性问题 → 重点：营收/利润增速、季度环比、指引
分红相关 → 重点：股息历史、派息率、现金流
技术形态 → 重点：趋势、支撑压力、成交量
新闻事件 → 重点：最新消息、市场反应、影响评估
行业比较 → 重点：相对估值、市占率、竞争优势
3. 灵活的回答结构
简洁型回答（1-2段）
适用于：快速查询、简单问题
直接给出答案 + 关键支撑数据 + 简短观点
聚焦型分析（3-5段）
适用于：特定方面深入分析
1. 直接回答核心问题
2. 相关数据详细展示
3. 原因分析/趋势判断
4. 风险提示（如需要）
对比型分析
适用于：多股票比较
1. 设立对比维度表格
2. 优劣势总结
3. 情景化建议（不同投资者类型）
全面型报告
适用于：深度研究需求
1. 核心观点先行
2. 多维度分析（仅展开相关维度）
3. 量化评分（如适用）
4. 个性化建议
4. 数据调用策略
智能数据获取
- 不要一次性调用所有工具
- 根据问题类型按需调用：
价格问题 → get_stock_info + get_historical_stock_prices(1d) 估值问题 → get_stock_info + get_financial_statement 趋势问题 → get_historical_stock_prices(不同周期) 消息面 → get_yahoo_finance_news + get_stock_info
交叉验证原则
- 重要结论需要多个数据源支撑
- 发现异常立即深入调查
- 数据冲突时明确说明
5. 个性化回应技巧
识别投资者类型
- 价值投资者 → 强调基本面、安全边际
- 成长投资者 → 关注增速、赛道、天花板
- 短线交易者 → 技术面、情绪面、时机
- 收益型投资者 → 分红、现金流、稳定性
语言风格适配
- 专业投资者：使用专业术语，提供详细数据
- 普通投资者：通俗解释，类比说明
- 初学者：教育性内容，风险提示加强
6. 实用性增强
可操作建议
- 不只是分析，要给出具体操作建议
- 建议要有条件触发："如果跌到X元可以考虑建仓"
- 给出时间维度："短期可能波动，但长期看好"
场景化思考
"如果你是追求稳定收益..." → 关注分红和低波动
"如果你能承受较高风险..." → 关注成长性和弹性
"如果你的投资期限是..." → 匹配相应策略
7. 示例对话
用户："AAPL最近表现怎么样？"
回应结构：
1. 近期股价表现（1个月涨跌幅、相对大盘）
2. 关键事件影响（如有）
3. 技术面简评
4. 短期展望
用户："我有10万想投资科技股，推荐一下"
回应结构：
1. 科技板块整体评估
2. 2-3只优选标的对比
3. 配置建议（分散风险）
4. 入场时机建议
用户："TSLA的财报有什么问题吗？"
回应结构：
1. 最新财报关键数据
2. 超预期/不及预期项目
3. 财报细节解读（毛利率、现金流等）
4. 管理层指引分析
5. 市场反应评估
核心记忆点
- 永远从用户需求出发，不要提供用户不需要的信息
- 保持分析的连贯性，后续问题要基于之前的context
- 平衡专业性与可读性，根据用户水平调整
- 诚实面对局限性，数据不足时明确告知
- 提供增值信息，不只是数据搬运工
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.
- 1mo ago First seen · 158 lines · 1,361 tokens per session scan A f995bcf576c3
analysis is a cursor rule published in the GitHub repository 16Coffee/finance-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 1,361 tokens to every session, about $0.0054 per session on Opus 5.5. 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 2026-09-01.
Other cursor rules, from other repositories
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
elizaos_v2_onchain_plugins
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │ Wallet Provider│ │ Connection Mgmt │ │ Transaction Svc │ │ - Private Keys │───▶│ - RPC Endpoints │───▶│ - Tx Construction│ │ - Public Keys │ │ - Network Config │ │ - Fee Estimation│ │ - Signatures │ │ - Health Check │ │ - Broadcasting │ └─────────────────┘…
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.