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 shouldnotappearcalm/a-share-skill --skill a-share-paper-tradinggit clone --depth 1 https://github.com/shouldnotappearcalm/a-share-skillWrote 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/shouldnotappearcalm/a-share-skill/a-share-paper-trading)<a href="https://agentmods.dev/skills/shouldnotappearcalm/a-share-skill/a-share-paper-trading"><img src="https://agentmods.dev/badge/skills/shouldnotappearcalm/a-share-skill/a-share-paper-trading/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/shouldnotappearcalm/a-share-skill/a-share-paper-trading"><img src="https://agentmods.dev/badge/skills/shouldnotappearcalm/a-share-skill/a-share-paper-trading.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.02318 |
| Opus 5 | $0.00030 | $0.01159 |
| Sonnet 5 | $0.00012 | $0.00464 |
| Haiku 4.5 | $0.00006 | $0.00232 |
Grade A, and why
a-share-paper-trading scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A股模拟盘
独立的模拟盘 skill。交易服务、CLI、账户、撮合与行情适配都在本目录内，不依赖其他 skill 脚本。
何时使用
- 启动或检查模拟盘服务
- 创建/重置账户
- 限价买卖、市价买卖、撤单
- 查询账户、持仓、订单、成交
- 验证涨跌停、T+1、收盘过期
- 跑简单回测
启动
SKILL_DIR="<本skill绝对路径>"
python3 "$SKILL_DIR/scripts/paper_trading_service.py" --host 127.0.0.1 --port 18765
默认监听 http://127.0.0.1:18765，默认数据库不再落在 skill 目录，而是落到用户级数据目录：
- macOS:
~/Library/Application Support/a-share-paper-trading/paper_trading.db - Linux:
${XDG_DATA_HOME:-~/.local/share}/a-share-paper-trading/paper_trading.db
若本机该端口已有模拟盘进程在跑，不要再启动第二个实例：会报 Address already in use，且多进程可能争用同一 SQLite 库文件。启动前可先检查端口是否在监听，例如：
lsof -iTCP:18765 -sTCP:LISTEN
或向 http://127.0.0.1:18765/accounts 发 GET（CLI 默认 --base-url 与此一致）。已有服务时直接用 paper_trade_cli.py 即可。
更推荐使用控制脚本常驻运行：
python3 "$SKILL_DIR/scripts/paper_trading_ctl.py" start
python3 "$SKILL_DIR/scripts/paper_trading_ctl.py" status
python3 "$SKILL_DIR/scripts/paper_trading_ctl.py" stop
在 macOS 上，如需持续自启动，可安装 launchd：
python3 "$SKILL_DIR/scripts/paper_trading_ctl.py" install-launchd
服务会：
- 交易时段定时撮合挂单
- 非交易时段停止撮合
- 收盘后让当日未成单过期
- 定时写账户净值快照
可用启动参数：
--host--port--db-path--match-interval--valuation-interval--idle-valuation-interval
默认端口与 CLI 基址已改为 18765，避免和常见本地开发服务冲突。
CLI
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" create-account alpha --cash 500000
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" list-accounts
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" show-default-account
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" set-default-account alpha
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" reset-account alpha --cash 300000
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" add-cash alpha 50000 --note 入金
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" deduct-cash alpha 10000 --note 出金
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" buy alpha 600519 100 --market
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" sell alpha 600519 100 --price 1450
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" orders alpha
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" positions alpha
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" show-account alpha
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" trades alpha
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" cancel <order_id>
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" process-orders
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" run-snapshots
python3 "$SKILL_DIR/scripts/paper_trade_cli.py" backtest 600519 --strategy sma_cross --start 2025-01-01 --end 2026-03-31 --cash 200000
What ships with it
14 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.
- README.md 2.5 KB
- scripts/backtest_batch_validation.py 2.0 KB runs code
- scripts/full_function_smoke_check.py 11 KB runs code
- scripts/paper_trade_cli.py 8.0 KB runs code
- scripts/paper_trading_ctl.py 6.5 KB runs code
- scripts/paper_trading_runtime.py 1.3 KB runs code
- scripts/paper_trading_service.py 1.2 KB runs code
- scripts/paper_trading/__init__.py 69 B runs code
- scripts/paper_trading/engine.py 36 KB runs code
- scripts/paper_trading/market_data.py 22 KB runs code
- scripts/paper_trading/service.py 7.7 KB runs code
- scripts/real_stock_rule_validation.py 3.7 KB runs code
- scripts/rule_regression_check.py 3.9 KB runs code
- scripts/test_market_data_intraday_snapshot.py 3.6 KB runs code
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.
- 11d ago First seen · 209 lines · 60 tokens per session scan A 661069e9fb7e
a-share-paper-trading is a skill published in the GitHub repository shouldnotappearcalm/a-share-skill (238 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 2,318 once invoked, about $0.0003 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
china-dcf-model
A documented discounted-cash-flow model for valuing non-financial A-share companies. A discounted-cash-flow model estimates today’s value from expected future cash flows and makes its assumptions, valuation date, and adjustments explicit.
industry-etf-research
A research workflow for studying Chinese A-share industry ETFs and the indexes they track. It compares index rules, holdings, company fundamentals, industry conditions, valuations and market evidence.
pptx-author
Produce a .pptx file on disk for headless Chinese A-share market research, using python-pptx with Chinese font support. Use when no controllable Office session is available.
china-market-data
A routing and quality-check process for obtaining Chinese stock-market and company-financial data from sources such as Tushare Pro and AKShare.
china-market-researcher
A research workflow for analysing Chinese-listed stocks by industry or investment theme, including companies, competitors, ETFs, and market data. A-share means shares listed on mainland Chinese stock exchanges.
a-share-factor-validation
A research checklist and toolkit for testing stock-selection factors and backtests in China's A-share market, the mainland Chinese stock market. It checks whether results avoid future-data leakage and account for trading rules, costs, and statistical uncertainty.