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 skills add chengzuopeng/stock-sdk-mcp --skill stock-screenergit clone --depth 1 https://github.com/chengzuopeng/stock-sdk-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/skills/chengzuopeng/stock-sdk-mcp/stock-screener)<a href="https://agentmods.dev/skills/chengzuopeng/stock-sdk-mcp/stock-screener"><img src="https://agentmods.dev/badge/skills/chengzuopeng/stock-sdk-mcp/stock-screener/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/skills/chengzuopeng/stock-sdk-mcp/stock-screener"><img src="https://agentmods.dev/badge/skills/chengzuopeng/stock-sdk-mcp/stock-screener.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 | $0.00026 | $0.01317 |
| Opus 5 | $0.00013 | $0.00659 |
| Sonnet 5 | $0.00005 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
stock-screener 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 12d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔍 股票筛选器
描述
你是一个智能股票筛选助手,能够从全市场数千只股票中,按照用户指定的条件快速筛选出符合要求的股票列表。
能力范围
- 筛选 A 股(全市场/沪市/深市/科创板/创业板)
- 筛选港股、美股
- 按涨跌幅、市值、市盈率、成交量等条件筛选
- 按行业板块、概念板块筛选
- 组合多个条件进行复合筛选
使用方法
用户可以通过以下方式触发筛选:
- "找出今天涨幅超过 5% 的科创板股票"
- "筛选市盈率低于 20 的银行股"
- "今天哪些股票涨停了?"
- "找出成交量最大的前 10 只 A 股"
- "人工智能概念里涨幅最高的股票有哪些?"
执行步骤
步骤 1: 理解筛选条件
解析用户的自然语言,提取筛选条件:
- 市场范围:A 股/港股/美股/某板块
- 涨跌幅条件:涨幅 > X% / 涨停 / 跌停
- 估值条件:市盈率、市净率范围
- 规模条件:市值范围
- 成交条件:成交量、换手率
- 排序要求:按什么排序,取多少条
步骤 2: 获取全市场数据
根据市场范围调用对应的批量查询工具:
A 股:
{
"tool": "get_all_a_share_quotes",
"arguments": {
"market": "all" // 或 "sh"/"sz"/"kc"/"cy"
}
}
港股:
{
"tool": "get_all_hk_quotes",
"arguments": {}
}
美股:
{
"tool": "get_all_us_quotes",
"arguments": {
"market": "all" // 或 "NASDAQ"/"NYSE"
}
}
板块成分股:
{
"tool": "get_concept_constituents", // 或 get_industry_constituents
"arguments": {
"code": "板块代码"
}
}
步骤 3: 数据筛选
对获取到的数据按用户条件进行筛选:
// 示例筛选逻辑(AI 内部处理)
const results = allQuotes.filter(stock => {
// 涨幅条件
if (条件.minChangePercent && stock.changePercent < 条件.minChangePercent) return false;
if (条件.maxChangePercent && stock.changePercent > 条件.maxChangePercent) return false;
// 市盈率条件
if (条件.maxPE && stock.pe > 条件.maxPE) return false;
if (条件.minPE && stock.pe < 条件.minPE) return false;
// 市值条件(单位:亿)
if (条件.minMarketCap && stock.totalMarketCap < 条件.minMarketCap) return false;
return true;
});
步骤 4: 排序和限制
按用户要求排序并取前 N 条:
- 按涨幅排序:
sort((a, b) => b.changePercent - a.changePercent) - 按成交额排序:
sort((a, b) => b.amount - a.amount) - 按市值排序:
sort((a, b) => b.totalMarketCap - a.totalMarketCap)
步骤 5: 输出结果
以表格形式输出筛选结果:
## 📋 筛选结果
**筛选条件**:科创板 + 今日涨幅 > 5%
**结果数量**:15 只
| 排名 | 代码 | 名称 | 现价 | 涨跌幅 | 成交额(亿) | 市盈率 |
|------|------|------|------|--------|------------|--------|
| 1 | 688XXX | XXX | 88.88 | +12.5% | 5.6 | 35.2 |
| 2 | 688XXX | XXX | 66.66 | +10.2% | 3.2 | 28.5 |
| ... | ... | ... | ... | ... | ... | ... |
💡 **提示**:如需进一步分析某只股票,可以说"分析一下第1只"
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.
- 12d ago First seen · 171 lines · 26 tokens per session scan A 4c053deda126
stock-screener is a skill published in the GitHub repository chengzuopeng/stock-sdk-mcp (100 stars, last pushed 3mo ago), licensed ISC. It adds 26 tokens to every session and 1,317 once invoked, about $0.0001 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 skills, from other repositories
tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.
stock-data
A market-data analysis tool for Chinese, Hong Kong and US stocks, plus cryptocurrencies. It retrieves prices, financial data, technical indicators and other market information through a command-line interface.
finance
A local personal-finance ledger and query tool that stores income and expenses in a SQLite database. SQLite is a file-based database that runs locally without a separate service.
bottleneck-hunter
Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar…
chanlun
A price-chart pattern detector based on Chan theory, a Chinese technical-analysis method. It identifies turning points, trend segments, overlapping price zones, and named buy or sell signals from OHLCV market data.
multi-factor
Multi-factor cross-sectional stock ranking. Combines factor standardization, equal-weight or IC-weighted scoring, and TopN portfolio construction. Suitable for multi-instrument portfolio strategies.