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/a-share-mainline-os --skill stock-dailygit clone --depth 1 https://github.com/Taosheng777/a-share-mainline-osWrote 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/a-share-mainline-os/stock-daily)<a href="https://agentmods.dev/skills/taosheng777/a-share-mainline-os/stock-daily"><img src="https://agentmods.dev/badge/skills/taosheng777/a-share-mainline-os/stock-daily/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/a-share-mainline-os/stock-daily"><img src="https://agentmods.dev/badge/skills/taosheng777/a-share-mainline-os/stock-daily.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 | $0.00165 | $0.09333 |
| Opus 5 | $0.00082 | $0.04666 |
| Sonnet 5 | $0.00033 | $0.01867 |
| Haiku 4.5 | $0.00016 | $0.00933 |
Grade A, and why
stock-daily scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> **⚠️ 沙箱网络**:Bash 环境设了 `HTTPS_PROXY`,Python `requests` 走代理连东财会 `ProxyError`/`RemoteDisconnected`,**但 `curl` 直连正常**。取东财数据时用 `curl` 拉 JSON 再交 Python 解析,或给 session 设 `trust_env = False`。 How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
复盘(v3 唯一日更)
一次交互回答三个问题:今天盘面什么环境 · 哪些主线活着/新生/垂死 · 我的机动仓和主线状态对不对得上。
产品设计与决策合同见仓库 docs/;本文件只保存运行时必需流程。
v3 与 v2 的根本差别:绩效永久交给同花顺,本地不算净值、TWR、回撤、仓位、集中度;不维护逐笔账本;不做券商截图算术核对。断更零债务——复盘结论本身无状态依赖,哪天跑哪天新,不需要把过去的复盘补齐。唯一的例外是板块逐日缓存:它是逐日累积的,断更期间的缺行大概率补不回来,缺了就按下文降级为「本项未验证」,不因此拒绝出复盘。
运行时配置与固定相对路径
运行前读取环境变量 ASM_CONFIG 指向的 JSON;未设置时读取 ~/.config/a-share-mainline/config.json。文件不存在、JSON 非对象或缺 vault_root 时立即停止,列出缺失项与配置方法,不得猜测路径或沿用记忆。
- Vault:配置键
vault_root;下列路径都从它派生。 - 问财 CLI:优先用可选配置键
wencai_cli,否则按当前 skills 根目录下的同级hithink-market-query/scripts/cli.py自动发现。找不到时标记该适配器不可用并按三源规则降级。 - commit 前缀:从
git_identity取当前平台 adapter 键(claude/codex),其次取default,均无则使用中性[ai]。下文以<git_identity>表示解析结果。 - 硬护栏:
00-系统/AI操作规则.md(数据熔断六条,v3 全文有效) - 纪律卡:
01-纪律卡.md(三条线的唯一事实源,每次重读,阈值绝不固化在本文件) - 持仓卡:
03-持仓跟踪/持仓.md(标的 / 角色 / 所属主线 / 止损位) - 主线目录:
05-主线追踪/(活跃主线页;归档/为已退潮) - 主线页模板:
05-主线追踪/_主线页模板.md - 输出目录:
02-盘面日志/ - 首页:
投资笔记.md - 板块逐日缓存:本 Skill 自带
scripts/board_fund_flow_cache.py(本仓库自有代码,不属于上游a-stock-data)。库文件默认在A_STOCK_DATA_HOME指向的目录下,未设置时回落到该脚本内置的用户级数据目录。缓存不存在或覆盖不足时按下文一律降级为「本项未验证」,不阻断其余复盘区。 - 判定器:本 Skill 自带
scripts/mainline_validation.py,提供退潮判定真值表与提名影子观察的确定性实现;行为回归入口见文末「行为回归与研究复跑」。 - 取数通道(三条,调用顺序见下「数据源:调用顺序与权威性」):
a-stock-dataskill(东财 / 腾讯 / 通达信 / 百度,零鉴权、无额度)hithink-financeCLI(同花顺 iFinD,额度独立于问财)- 问财 CLI:运行时解析出的
wencai_cli(每日额度有限、三个 skill 共用,仅限正面清单四类场景)
硬边界
- 只在人在场时手动触发;不做定时、不创建 automation、cron 或后台监控。
- 不下单、不碰委托、不动钱,不替用户作买卖决定。纪律只产生提示,不冻结、不自动卖出。
- 不编数据。每个行情数字必须带来源和数据日;缺失写
未取得,不猜。 - 不写未来行情。次日日期与待观察项可以写,不得附带未来价格、涨跌幅或资金数据。
- 不建主线页。提名只写进当日复盘等用户拍板;用户说「跟」才建页,那是另一轮的事。
- 不算账户绩效:净值、TWR、回撤序列、仓位、集中度一律不碰。
- 白名单只有四类:
02-盘面日志/当日复盘、05-主线追踪/活跃主线页的证据流增量、03-持仓跟踪/持仓.md(仅当用户本轮报了成交或改了止损位)、投资笔记.md(仅当首页 callout 事实变化)。超出立即停止并说明。 - 写
未取得之前必须先走完下面的调用顺序三条通道。单一通道失败或额度耗尽 ≠ 熔断:- 三条通道都拿不到该数据项 → 该数据项熔断,写
未取得(三源均失败:<逐条列出>),任务其余部分照常完成。 - 整轮任务停止只在两种情况:① 关键数据项全部熔断致结论无依据;② 数据日异常或晚于系统当天。
- 涨跌家数以问财为写入源、并必跑东财影子对账(见下 §1「涨跌家数:问财为写入源 + 东财影子强制校验」);问财耗尽时改用影子值写入并标注,不再熔断该项。
- 三条通道都拿不到该数据项 → 该数据项熔断,写
What ships with it
6 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 · 278 lines · 165 tokens per session scan A d8507b4eb5fb
stock-daily is a skill published in the GitHub repository Taosheng777/a-share-mainline-os (2 stars, last pushed 25d ago), licensed MIT. It adds 165 tokens to every session and 9,333 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
quant-statistics
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.
risk-analysis
Risk measurement and stress testing — VaR/CVaR/max drawdown calculation, Monte Carlo simulation, extreme-value tail-risk analysis, and historical scenario stress testing.
strategy-generate
Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.