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 Lzh-xbccz/hermes-finance --skill futures-market-analysisgit clone --depth 1 https://github.com/Lzh-xbccz/hermes-financeWrote 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/futures-market-analysis)<a href="https://agentmods.dev/skills/lzh-xbccz/hermes-finance/futures-market-analysis"><img src="https://agentmods.dev/badge/skills/lzh-xbccz/hermes-finance/futures-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/futures-market-analysis"><img src="https://agentmods.dev/badge/skills/lzh-xbccz/hermes-finance/futures-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 | $0.00128 | $0.21336 |
| Opus 5 | $0.00064 | $0.10668 |
| Sonnet 5 | $0.00026 | $0.04267 |
| Haiku 4.5 | $0.00013 | $0.02134 |
Grade C, and why
futures-market-analysis scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s -H "User-Agent: Mozilla/5.0" "https://query1.finance.yahoo.com/v8/finance/chart/${SYMBOL}?interval=1d&range=30d" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### ⚠️ 强制规则：一键脚本采集（禁止手动 curl Yahoo） How it starts
The opening of the file, as written. The whole thing — 1,249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
期货市场八维分析全流程
⛔ 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。
核心理念：期货价格由宏观驱动 + 供需基本面 + 市场结构共同决定。 地缘政治和库存数据可在瞬间覆盖所有技术位。技术分析在期货中的权重远低于加密货币——不可颠倒。
⛔ 禁止调用 mcp_yfinance 系列工具：Yahoo Finance 频繁 429。所有数据通过
scripts/目录下的 fetch 脚本获取（内置延迟+重试）。模型不要额外调mcp_yfinance_get_historical_stock_prices等 MCP 工具。
一、铁律（不可违反）
1. 先判断是否有方向优势
- 输出只能是 🟢 做多 / 🔴 做空 / ⚪ 观望，但默认不是强行二选一。
- 方向由你基于各维度证据的逻辑强度和可靠性综合判断得出，不要用投票计数或权重打分决定方向；不能把 DXY/10Y/VIX/ETF 等同类代理拆成多票。
- 只要方向质量差、事件风险主导、关键证据缺失或多空证据接近，必须输出 ⚪ 观望。
- 可以给"触发条件"：例如"若 4H 收盘站回 X 且 OVX 回落，再从观望切到偏多"，但最终方向仍写观望。
2. 止盈止损必须锚定客观技术结构
- ✅ 允许参考的结构：前高/前低（独立摆点）、形态颈线、趋势线交点、斐波那契回撤位、密集成交区上沿/下沿、EMA21/EMA55
- ❌ 禁止使用：24h 最高/最低点、今日开盘价、「跌 2% 就走」等固定百分比、任何以时间为边界而非结构为边界的价位
- 每一个 SL/TP 价位必须在报告中标注「结构依据」——具体说明这是哪个结构、什么时候形成的
3. 止损幅度由结构决定
- 做多止损：放在最近关键结构低点下方 0.2%-0.3%
- 做空止损：放在最近关键结构高点上方 0.2%-0.3%
- 期货跳空风险高于加密——止损可适当放宽 0.1%-0.2%（共 0.3%-0.5%），但仍必须锚定结构位
- 止损幅度不由百分比决定（但如果结构决定的幅度超过账户风控上限，需特别标注风险，建议减小仓位而非放宽止损）
4. 必须带失效条件
- 至少 2 个明确的「不等止损、立即手动平仓」的条件
- 失效条件必须是客观可观察的（K 线收盘、OVX/VIX 异动、关键新闻事件升级、关联市场破位等）
5. 数据缺口必须降级处理
- 报告开头必须标注分析时间（UTC）
- 若 Yahoo Finance 返回 429、4xx、空数据或结构变更，先减少请求并复用已拉取数据；仍失败则停止补抓，绝不编造
- 技术结构、波动率代理、交叉验证三项里只要缺 1 项，默认降级为 ⚪ 观望
- 新闻、库存等非关键块缺失时，可继续分析，但必须明确写出「数据缺口」
- 若处于周末或美国节假日，期货电子盘虽仍在交易但流动性极低，宏观块仅以最近收盘作背景参考
- COT 报告数据天然滞后 3 天，仅作中长期背景参考，不得用于日内决策
6. 先复盘轨迹，再谈方向
- 每做一个品种，必须先看它最近
30D日线和4H轨迹是怎么走出来的，再看当前截面 - 必须回答：这个品种最近更像
趋势推进 / 箱体洗盘 / 冲高派发 / 跌破回收 / 阴跌磨人里的哪一种 - 如果你连最近主导手法都说不清，就不能把当前波动解读为高置信度机会
7. 事件面前，技术面自动降权
- 一级事件（海峡关闭/全面战争）：技术面完全无效，强制 ⚪ 观望
- 二级事件（军事冲突升级/停火破裂）：技术面权重降至 10%，以事件方向为主
- 三级事件（停火谈判/库存数据/EIA/OPEC）：技术面权重降至 30%，等数据落地后确认
- 四级事件（常规供需/评论）：技术面保持正常权重
8. OVX 与价格背离 = 方向不可靠 ⚠️ CL 专属铁律
地缘危机中常见：价格暴跌后反弹 7-10%，但 OVX 纹丝不动。这种情况必须识破。
经典陷阱：crash-and-bounce
- 价格 3 小时跌 -12% → 随后反弹 +7%
- 但 OVX 仍停在 70+，完全未跟随回落
- 这不是利好驱动的趋势反转——是空头回补 + 短线抄底的超卖修复
- 真正的趋势反转必须伴随 OVX 同步崩塌（如 75→45 以下）
- 如果 OVX 不跌，恐慌未解除，不可据此做多
OVX-价格背离速查：
| 价格 | OVX | 真实含义 | 操作 |
|---|---|---|---|
| ↑ +7% | → 不动 | 🟡 超卖修复 | ⚪ 观望 |
| ↑ +7% | ↓ -20% | 🟢 恐慌消退 | 可考虑做多 |
| ↓ -10% | ↑ +15% | 🔴 恐慌加速 | 可考虑做空 |
| ↓ -10% | → 不动 | ⚪ 有序下跌 | 等 OVX 给出方向 |
What ships with it
4 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.
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 · 1,249 lines · 128 tokens per session scan C 6d59c5978f8f
futures-market-analysis is a skill published in the GitHub repository Lzh-xbccz/hermes-finance (24 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 21,336 once invoked, about $0.0006 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"…