Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Lzh-xbccz/hermes-financenpx agentmods add skills/lzh-xbccz/hermes-finance/a-share-market-analysisWrote 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/lzh-xbccz/hermes-finance/a-share-market-analysis)<a href="https://agentmods.dev/skills/lzh-xbccz/hermes-finance/a-share-market-analysis"><img src="https://agentmods.dev/badge/skills/lzh-xbccz/hermes-finance/a-share-market-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/skills/lzh-xbccz/hermes-finance/a-share-market-analysis"><img src="https://agentmods.dev/badge/skills/lzh-xbccz/hermes-finance/a-share-market-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 | $0.00062 | $0.09917 |
| Opus 5 | $0.00031 | $0.04959 |
| Sonnet 5 | $0.00012 | $0.01983 |
| Haiku 4.5 | $0.00006 | $0.00992 |
Grade C, and why
a-share-market-analysis scanned grade C 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://web.ifzq.gtimg.cn/appstock/app/fqkline/get?param=sh000001,day,,,30,qfq" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> - ❌ 新浪 hq.sinajs.cn（浏览器 fetch）：CORS + Forbidden；curl CLI 可用 How it starts
The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中国 A 股行情分析
⛔ 铁律：你不是在写行情播报，你是在做证据审计。每个方向判断必须回答"为什么"，并先做反向审计。允许使用"证据不足"、"方向未确认"、"观望"；禁止在证据冲突时硬给做多/做空。
🆕 v3.0 — 集成 Sequoia-X 7策略量化选股引擎
量化选股（a_share_scanner.py）
基于 baostock 免费数据源，收盘后自动扫描全市场 5200+ 只 A 股：
# 首次：回填历史数据 (~12分钟)
python a_share_scanner.py --backfill
# 日常：增量更新 + 7策略扫描
python a_share_scanner.py
# 仅跑特定策略
python a_share_scanner.py --strategy turtle
| 策略 | 说明 |
|---|---|
| 海龟突破 | 20日新高 + 成交额过亿 + 防诱多阳线 |
| 均线放量 | 均线多头排列 + 放量突破 |
| 高窄旗形 | 强动量后极度收敛缩量 |
| 涨停洗盘 | 涨停后回踩确认 |
| 跌停反包 | 上升趋势中跌停后的反包 |
| RPS突破 | 欧奈尔相对强度突破 |
| 定增回补 | 定增破发后的回补机会 |
数据源：baostock（免费、无需注册、后复权）→ 本地 SQLite，彻底规避东方财富反爬。
八维分析框架
| # | 维度 | 核心关注 | 数据源 | 状态 |
|---|---|---|---|---|
| 1 | 📈 技术结构 | K线趋势、量价关系、支撑阻力、形态 | 新浪 API + 腾讯 K 线 | ✅ |
| 2 | 💰 资金面 | 北向资金净流入/流出（A股独有） | 浏览器→东方财富网页 | 🐢 慢但可用 |
| 3 | 📊 市场结构 | 涨跌家数、涨停跌停统计 | 浏览器→东方财富网页 | 🐢 慢但可用 |
| 4 | 😱 情绪量能 | 成交量对比、风险偏好 | 新浪 API + 腾讯 K 线 | ✅ |
| 5 | 🌍 宏观政策 | 美股联动、人民币汇率、政策要闻 | Yahoo Finance + 新浪/腾讯 + Google News RSS | ✅ |
| 6 | 🔄 板块轮动 | 领涨/领跌板块、热点概念、龙头识别 | 东方财富板块流 + 雪球热股 | 🔴 海外严重受限 |
| 7 | 🧮 量化/Sequoia | 7策略扫描、RPS、突破/洗盘/反包信号 | baostock + SQLite | ✅ |
| 8 | 🧭 缠论结构 | CZSC 中枢、笔、背驰、买卖点候补 | 腾讯日线/个股K线 | 可用则跑 |
强制输出规则：
- 先给
各维度证据，只基于第 1-7 维逐项列出每个维度的偏多/偏空/中性/缺失状态及理由。不要用投票计数或权重打分决定方向。 - 必须做
反向审计：若资金、广度、板块或政策新闻与技术方向冲突，最终方向降为震荡或保守档。 - 再给
缠论确认，说明 CZSC 是确认、冲突还是不足。 - 最终方向由你基于各维度证据的逻辑强度综合判断后决定；A 股受 T+1、涨跌停、政策与板块轮动约束，CZSC 不能覆盖这些限制。
- 使用
python3 -m hermes_finance analyze a-share --stock <CODE>或 MCPanalyze_a_share，默认会尽量用采集器 K 线跑 CZSC。
⚠️ 海外服务器实测结果（2026-05-04 更新）：
- ❌ 东方财富 API（push2/datacenter-web）：TLS 成功，nginx 返回 502（Geo-block）
- ❌ 同花顺（10jqka.com.cn）：Nginx forbidden，封海外 IP
- ❌ 新浪 hq.sinajs.cn（浏览器 fetch）：CORS + Forbidden；curl CLI 可用
- ✅ 新浪财经首页（finance.sina.com.cn）：指数数据可 snapshot 提取
- ✅ 腾讯
fqkline/kline：历史日 K +market市场状态可直接返回（含休市/节假日提示）- ✅ 雪球（xueqiu.com）：海外可访问，三大指数+热股榜正常，板块排行 API 需登录
- ✅ 东方财富网页（浏览器）：北向资金历史数据 + 板块持股流可提取，板块排行页 Canvas 渲染不可抓
- ❌ DuckDuckGo 新闻搜索：已触发 bot challenge，不再适合作为主新闻源
- ✅ Google News RSS：可直接解析，适合作为新闻主路径
- 详见
references/china-finance-apis.md
What ships with it
35 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- a_share_scanner.py 5.7 KB runs code
- references/china-finance-apis.md 7.1 KB
- scripts/a_share_analyze.py 15 KB runs code
- scripts/a_share_data.py 6.5 KB runs code
- scripts/a_share_fetch.py 12 KB runs code
- scripts/a_share_remote.py 19 KB runs code
- sequoia/__init__.py 122 B runs code
- sequoia/.env.example 1.0 KB
- sequoia/core/__init__.py 67 B runs code
- sequoia/core/config.py 3.3 KB runs code
- sequoia/core/logger.py 1.0 KB runs code
- sequoia/data/__init__.py 91 B runs code
- sequoia/data/engine.py 13 KB runs code
- sequoia/main.py 3.8 KB runs code
- sequoia/notify/__init__.py 49 B runs code
- sequoia/notify/feishu.py 4.8 KB runs code
- sequoia/pyproject.toml 498 B
- sequoia/README.md 3.6 KB
- sequoia/strategy/__init__.py 64 B runs code
- sequoia/strategy/base.py 2.6 KB runs code
- sequoia/strategy/high_tight_flag.py 2.4 KB runs code
- sequoia/strategy/limit_up_shakeout.py 2.2 KB runs code
- sequoia/strategy/ma_volume.py 1.7 KB runs code
- sequoia/strategy/private_placement.py 2.4 KB runs code
- sequoia/strategy/rps_breakout.py 2.0 KB runs code
- sequoia/strategy/turtle_trade.py 4.1 KB runs code
- sequoia/strategy/uptrend_limit_down.py 2.3 KB runs code
- sequoia/tests/__init__.py 0 B runs code
- sequoia/tests/test_config.py 1.6 KB runs code
- sequoia/tests/test_data_engine.py 1.9 KB runs code
- sequoia/tests/test_feishu.py 3.4 KB runs code
- sequoia/tests/test_logger.py 746 B runs code
- sequoia/tests/test_main.py 872 B runs code
- sequoia/tests/test_strategy.py 1.4 KB runs code
- sequoia/uv.lock 247 KB
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 · 738 lines · 62 tokens per session scan C 0718e28cda6f
a-share-market-analysis is a skill published in the GitHub repository Lzh-xbccz/hermes-finance (24 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 9,917 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tickdb-market-data
A real-time market-data API for foreign exchange, metals, indexes, stocks, and cryptocurrencies. An API is a service that software can call to request data.
ask-a-legend
Get one legendary trader's read on a symbol — Wyckoff, Gann, Elliott Wave, Dow Theory, Livermore, DeMark, Wilder (RSI/ADX), Ichimoku (Hosoda), Weinstein stage analysis, or O'Neil CAN SLIM. Pass the legend and symbol, e.g. "gann on eurusd" or "what would Wyckoff say about AAPL?". Analysis and a second opinion, not a…
convene
Convene the Trading Legends Council — ten legendary traders (Dow, Wyckoff, Livermore, Elliott, Gann, DeMark, Wilder, Ichimoku, Weinstein, O'Neil) each vote blind on a symbol, then a deterministic Chairman aggregates their ballots into one verdict (LONG/SHORT/NOTRADE). Analysis and a second opinion, not signals.
forge-legend
Author a new trading legend/persona from a famous trader's name or a plain-English strategy description, then lint and live-audition it before it joins your roster. E.g. "make a trader who buys liquidity sweeps" or "add an ICT legend".
trade-memory
Compliance-grade decision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state), SHA-256 tamper detection, and structured export for MiFID II / EU AI Act readiness. Works alongside Binance Spot, Futures, and Web3 skills — they execute trades…
risk-management
Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt"…