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 Taosheng777/BigA-stock-skills --skill a-stock-datagit clone --depth 1 https://github.com/Taosheng777/BigA-stock-skillsWrote 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/taosheng777/biga-stock-skills/a-stock-data)<a href="https://agentmods.dev/skills/taosheng777/biga-stock-skills/a-stock-data"><img src="https://agentmods.dev/badge/skills/taosheng777/biga-stock-skills/a-stock-data/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/taosheng777/biga-stock-skills/a-stock-data"><img src="https://agentmods.dev/badge/skills/taosheng777/biga-stock-skills/a-stock-data.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 | $0.00253 | $0.39792 |
| Opus 5.5 | $0.00101 | $0.15917 |
| Sonnet 5.5 | $0.00051 | $0.07958 |
| Haiku 4.5 | $0.00025 | $0.03979 |
Grade B, and why
a-stock-data scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
r1 = requests.post("https://irm.cninfo.com.cn/newircs/index/queryKeyboardInfo", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
本 SKILL 提供统一的节流入口 `em_get()`(定义见下方「东财数据中心统一查询(共用 helper)」),它自动做到:串行限流(最小间隔 `EM_MIN_INTERVAL=1.0s` + 随机抖动)+ 复用 `EM_SESSION`(Keep-Alive)+ 默认 UA。**所有 `eastmoney.com` 端点的代码块都已改用 `em_get` 而非裸 `requests.get`**,AI 直接抄代码即自带防封。批量 This is a copy
86% identical to a-stock-data — 492 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 2,816 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📦 项目主页:https://github.com/simonlin1212/a-stock-data — 更新、反馈、支持作者
作者:Simon 林 · 抖音「Simon林」· 公众号「硅基世纪」
A股全栈数据工具包 V3.4.0
十层数据架构,43 个端点实测可用(40 主端点 + 3 官方备胎,2026-07 验证),覆盖主板/中小板/科创板/ST。每类数据在「备用源速查」列有独立备胎,主源被封时可降级。
V3.4.0(接口质量 + 备用源韧性,2026-07-11):
- §5.2 财联社快讯复活:旧 nodeapi 2026-05 下线后,改走官方
v1/roll/get_roll_list+ 本地签名(sign=md5(sha1(排序query)),零 key),V3.2 移除的全市场电报能力恢复,与东财 7×24 互为独立备份。实测 errno=0。- 新增「备用源速查 & 降级策略」章节:十层主源→独立备胎速查表(不同域名/不同风控面)+ 3 个实测备胎函数——
dragon_tiger_backup()(沪深交易所官方龙虎榜,含营业部席位)、fund_flow_backup()(新浪日度资金流)、announcements_backup()(深市深交所官方/沪市东财公告+PDF)。端点 40 → 43,数据源 13 → 15(新增沪深交易所官方)。- §3.6 解禁字段修复:东财
RPT_LIFT_STAGE改列名致type/shares恒空 → 改FREE_SHARES_TYPE/FREE_SHARES,并新增able_shares(实际可流通股数,更贴近真实抛压)。- §3.7 行业排名排序修复:clist 请求补
fid=f3,top/bottom现按涨跌幅真实排序(此前缺排序字段,切片结果非涨幅序)。- §3.2 深股通标注:北向盘中披露收紧后 sgt 分钟序列不可靠(hgt 可用),权威北向用 HKEX 官方日统计(见备用源速查)。
- 体验:顶部新增「端点路由速查」总表(§→函数→用途→源,可按需局部读取);FAQ 新增东财被封对策 / 财联社复活 / mootdx 库烂尾说明。
V3.2.3(行业研报新增):
- §2.1 东财行业研报
eastmoney_industry_reports():研报层补上行业研报端点(此前只有个股研报)。与个股研报同端点reportapi.eastmoney.com/report/list,仅qType=1;industry_code="*"拉全行业、传东财行业码(如1238=IT服务Ⅱ)精确过滤,PDF 复用download_pdf(),走em_get限流。端点数 27 → 28。- 实测(2026-06-20):全行业
hits=47928、按行业码1238过滤hits=1863,首篇 PDFH3_{infoCode}_1.pdf下载成功(2.5MB,bxpa等)404 不存在,用"*"拉取后从结果反查行业码。
V3.2.2(失效接口替换 + 隐藏 Bug 修复):
- §3.3 概念板块归属(#18):百度 PAE
getrelatedblock失效(ResultCode 10003+ 空数组)→ 改用东财slist(spt=3)eastmoney_concept_blocks(),一次请求拿全个股所属板块(行业/概念/地域 + BK码 + 涨跌幅 + 龙头股),零鉴权走em_get限流。- §7.1 巨潮公告 orgId(#19):硬编码
gssx0{code}致大量 601xxx 股票totalAnnouncement=0→ 新增_cninfo_orgid()动态查官方映射表szse_stock.json(6198 只股,模块级缓存),硬编码降为 fallback。- 综合示例修复:示例仍调用 v3.1 已删的
baidu_fund_flow_history→ 改eastmoney_fund_flow_minute。- §4.5/§5.1 风控说明:部分大陆住宅 IP 被东财间歇风控(
HTTP 000/空)非代码 Bug,加重试/换网络提示。- 新代码原样 exec smoke test 实测:板块归属 茅台27/五粮液28/绿的谐波21;公告 平安601318/工行601398 原失效股恢复。
V3.2.1(Bug 修复): 修复两个内嵌函数的解析逻辑(预先存在,非 V3.2 引入)——
- §5.1 东财个股新闻:东财实际返回里
result.cmsArticleWebOld直接就是文章列表,旧写法对 list 调.get("list")触发 AttributeError / 返回空 → 改为遍历cmsArticleWebOld列表本身。- §6.4 新浪财报三表:新浪实际结构是
result.data.report_list(按报告期为键的 dict,每期data才是行项列表),旧写法取result.data.{lrb}永久返回空 → 改为遍历report_list期次、从每期data按item_title提取。- 两函数均用茅台 600519 公开 API(零 key)实测返回非空、字段正确。
V3.2(防封 + 失效修复):
- 数据源优先级 + 东财防封:明确「通达信(mootdx)/腾讯不封IP 优先用,东财仅用于其独有数据」原则;新增统一节流入口
em_get(),所有东财接口内置串行限流(间隔≥1s+随机抖动)+ 会话复用,AI 抄代码即自带防封。详见「数据源优先级 & 东财防封」章节。- 财联社快讯下线(#14):
cls.cn旧 API 全面 404,标注弃用并改用东财全球资讯。V3.1 修复: 替换 4 个失效接口(百度 PAE 资金流→东财 push2、大宗交易 RPT 报表名更新、机构席位改用 BUY/SELL 明细筛选)+ 修复东财全球资讯 req_trace 参数 + 修复巨潮公告 orgId 格式。
V3.0 Breaking Change:彻底移除 akshare 依赖,所有数据源改为直连 HTTP API(零第三方数据依赖,仅 mootdx 保留 TCP)。
使用方式: 将本文件放入 ~/.claude/skills/a-stock-data/SKILL.md,Claude Code 会自动识别并在 A 股相关对话中激活。
行情层(实时,不封IP)
├── mootdx → K线 + 五档盘口 + 逐笔成交 (TCP 7709)
├── 腾讯财经 API → PE/PB/市值/换手率/涨跌停/指数/ETF (HTTP)
└── 百度股市通 → K线带MA5/10/20 (V3.0 新增,HTTP)
研报层
├── 东财 reportapi → 个股研报 + 行业研报 + PDF下载 + 评级 + 三年EPS
├── 同花顺 THS → 一致预期EPS (直连 basic.10jqka.com.cn)
└── iwencai → NL语义搜索研报 (唯一能力,需X-Claw)
信号层
├── 同花顺热点 → 当日强势股 + 题材归因 reason tags (零鉴权 73ms)
├── 同花顺北向 → hgt/sgt 分钟资金流向 + 本地自缓存历史
├── 东财 slist → 个股所属板块/概念归属 (V3.2.2 替换百度PAE)
├── 东财 push2 → 个股资金流向 分钟级 (V3.1 替换百度PAE)
├── 龙虎榜席位 → 上榜记录 + 买卖席位 TOP5 + 机构动向 (datacenter-web)
├── 全市场龙虎榜 → 每日全市场上榜股票 + 净买额排名 (datacenter-web)
├── 限售解禁日历 → 历史解禁 + 未来90天待解禁 (datacenter-web)
└── 行业板块排名 → 东财行业涨跌/上涨下跌家数 (V3.0 替换同花顺)
资金面 / 筹码层
├── 融资融券明细 → 日级融资余额/买入/偿还 + 融券 (datacenter-web)
├── 大宗交易 → 成交价/量 + 买卖方营业部 (datacenter-web)
├── 股东户数变化 → 季度股东户数 + 环比变化 (datacenter-web)
├── 分红送转 → 历史每股派息/送股/转增 (datacenter-web)
└── 个股资金流120日 → 主力/大单/中单/小单 日级净流入 (push2his)
新闻层
├── 东财个股新闻 → 个股相关新闻 (search-api-web JSONP)
├── 财联社快讯 → 全市场实时电报 (v1 API+本地签名零key,✅V3.4 复活)
└── 东财全球资讯 → 7×24 财经快讯 (np-weblist,与财联社互备)
基础数据层
├── mootdx finance → 季报快照 (37字段, EPS/ROE/净利)
├── mootdx F10 → 公司资料 (9大类文本)
├── 东财个股信息 → 行业/总股本/流通股/市值/上市日期 (push2)
└── 新浪财报三表 → 资产负债表/利润表/现金流量表 (quotes.sina.cn)
公告层
├── 巨潮 cninfo → 公告全文检索+下载 (cninfo.com.cn)
└── mootdx F10 → 最新公告摘要
打板层 (V3.3 新增)
├── 东财涨停池 → 连板数/几天几板/封板资金/炸板次数/行业 (push2ex)
├── 东财炸板池 → 涨停后开板 + 振幅/涨速 (push2ex)
├── 东财跌停池 → 封单资金/连续跌停/开板次数 (push2ex)
├── 东财昨涨停池 → 昨涨停今表现,算晋级率/赚钱效应 (push2ex)
└── 同花顺涨停揭秘 → 涨停原因题材/封板成功率/板型 (10jqka)
ETF期权层 (V3.3 新增)
├── 合约清单 → 50ETF/300ETF/科创50/500ETF 各月认购认沽 (新浪)
├── T型报价 → 买卖五档/持仓量/行权价/最新价 (新浪)
└── 希腊字母+IV → Delta/Gamma/Theta/Vega/隐含波动率 (新浪)
舆情互动层 (V3.3 新增)
├── 互动易问答 → 投资者提问+公司回复 (巨潮,AI问答独家)
├── 同花顺热榜 → 人气值/概念标签/排名变化 (10jqka)
├── 东财人气榜 → 排名+排名变化+名称价格 (emappdata)
└── 东财概念命中 → 个股被归到哪些概念在炒+热度 (emappdata)
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 · 2,816 lines · 253 tokens per session scan B a1cd1220f7ea
a-stock-data is a skill published in the GitHub repository Taosheng777/BigA-stock-skills (3 stars, last pushed 8d ago), licensed MIT. It adds 253 tokens to every session and 39,792 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 86% identical to a-stock-data, differing in 492 lines, and is treated as a copy.
Other skills, from other repositories
bim-cost-estimation-cwicr
Automated cost estimation from BIM models using DDC CWICR database (8 national bases, 78,228 positions). AI classification + vector search for accurate pricing.
cost-prediction
Predict construction project costs using Machine Learning. Use Linear Regression, K-Nearest Neighbors, and Random Forest models on historical project data. Train, evaluate, and deploy cost prediction models.
evaluate
Evaluate an AI workflow against representative cases and its permitted actions. Use for model, retrieval or agent evaluation; tests do not grant release authority.
data-value-monetization-team
A team guide for taking data from value discovery through use-case design, business-model planning, and ongoing revenue operations.
automodel
Guides the user in discovering a better model structure (e.g. from feature transformations in logistic regression to equation terms within PDEs to neural network layer compositions) out of data. Use when the user asks to create or improve an existing model. Uses an iterative meta/inner agent loop to explore structural…
speckit.payment-fintech
FinTech & Payment Systems Engineer - Idempotency ledger, payment gateways, signature verification, and financial transaction state machines.