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 litaolemo/xtquant_big_convert --skill qmt-tradergit clone --depth 1 https://github.com/litaolemo/xtquant_big_convertWrote 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/litaolemo/xtquant_big_convert/qmt-trader)<a href="https://agentmods.dev/skills/litaolemo/xtquant_big_convert/qmt-trader"><img src="https://agentmods.dev/badge/skills/litaolemo/xtquant_big_convert/qmt-trader.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00190 | $0.04800 |
| Opus 5 | $0.00095 | $0.02400 |
| Sonnet 5 | $0.00038 | $0.00960 |
| Haiku 4.5 | $0.00019 | $0.00480 |
Grade A, and why
qmt-trader 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 4d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QMT Trader — 大模型驱动的 QMT 交易/行情工具
概述
本 skill 提供一个确定性 CLI 脚本 scripts/qmt.py,让大模型通过命令行调用大 QMT 的全部
交易与行情能力,避免每次现场写 Python 代码。所有命令默认输出 JSON(便于解析),加 --table
切换人类可读表格。
前置条件:本 skill 依赖 xtquant_big_convert 桥接服务已部署运行。若 ping 失败或用户尚未部署,
先按下文「首次部署」引导完成:装包 → 同步 QMT 端文件 → 写配置 → QMT 里运行入口 → 验证。
首次部署(只需一次,AI 逐步引导用户完成)
部署分两端:客户端(跑本 skill/策略的开发机)和服务端(大 QMT 客户端内置 Python)。
第 1 步:客户端安装包
pip install "xtquant-big-convert[redis]" # redis 传输(默认,推荐)
# 或 zmq 同机低延迟:pip install xtquant-big-convert(基础版已含 pyzmq)
没发布到 PyPI 的私有 fork 用源码安装:
git clone <repo> && cd xtquant_big_convert && pip install -e .[redis]
第 2 步:把服务端文件同步到 QMT 的 python 目录
需要拷 4 项到大 QMT 的 python 目录(如 D:\国金证券QMT交易端\python\):
bigqmt_signal_trader/ (整个包,pip 装的在 site-packages 里)
bigqmt_signal_trader_strategy.py
bigqmt_signal_trader_redis_rpc_runtime.py
BIGQMT_REDIS_DRYRUN.py (★ QMT 编辑器入口,GBK 编码)
pip 安装后的文件位置可以用这条命令定位(输出目录里就有全部 4 项):
python -c "import bigqmt_signal_trader_strategy as m, os; print(os.path.dirname(m.__file__))"
QMT 沙箱若拒绝
import redis(部分券商白名单拦截),改用仓库里的bigqmt_no_redis/无 redis 版本(自包含 ZMQ 传输)。
第 3 步:创建 QMT 端私有配置
在 QMT 的 python 目录创建 bigqmt_signal_trader_local_config.py(含账号密码,不要提交 git):
# coding: utf-8
BIGQMT_ACCOUNT_ID = "资金账号"
BIGQMT_REDIS_CONFIG = {
"host": "Redis地址", "port": 6379, "db": 5, "password": "Redis密码",
"rpc_allow_order_methods": False, # 下单开关,默认关闭;确认风控后改 True
"rpc_process_in_listener": True,
"rpc_listener_methods": ("*",),
"rpc_background_threads": False, # 若切 zmq/mysql 传输必须改 True
"schedule_adjust": True,
"schedule_adjust_interval": "500nMilliSecond",
}
切 zmq:配置里加
"transport": "zmq"并把rpc_background_threads改True(QMT 端需装 pyzmq 19.0.2,Python 3.6 最后支持的版本)。
第 4 步:在 QMT 策略编辑器运行入口
QMT 策略编辑器里只加载运行 BIGQMT_REDIS_DRYRUN.py 一个文件(它自动 import 其余模块)。
若 QMT 装在非默认路径且用 exec 方式加载,需改文件里 _known_qmt_python_dir() 的 fallback 路径。
What ships with it
2 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.
- 4d ago Changed · +4 lines de04931a1f6f
- 8d ago First seen · 347 lines · 190 tokens per session scan A 4a68077cae10
qmt-trader is a skill published in the GitHub repository litaolemo/xtquant_big_convert (524 stars, last pushed today), licensed MIT. It adds 190 tokens to every session and 4,800 once invoked, about $0.0010 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.