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-screenergit 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-screener)<a href="https://agentmods.dev/skills/taosheng777/a-share-mainline-os/stock-screener"><img src="https://agentmods.dev/badge/skills/taosheng777/a-share-mainline-os/stock-screener/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-screener"><img src="https://agentmods.dev/badge/skills/taosheng777/a-share-mainline-os/stock-screener.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 | $0.00191 | $0.04639 |
| Opus 5 | $0.00096 | $0.02320 |
| Sonnet 5 | $0.00038 | $0.00928 |
| Haiku 4.5 | $0.00019 | $0.00464 |
Grade A, and why
stock-screener 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.
> 沙箱内 Python `requests` 走 `HTTPS_PROXY` 连东财会失败，**用 `curl` 拉 JSON 再解析**，或 `session.trust_env = False`。 How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
载体筛选 / 选股（stock-screener）
本 SKILL.md 即运行时唯一执行依据（自包含）；产品设计与决策合同见仓库 docs/。
v3 定位：主线决策链的载体环节——「这条主线要买，买什么」。产出载体清单 + 强弱排序 + 排序理由，交给 stock-buddy 做账户适配与参考条件位。与 stock-buddy 严格不重叠。
运行时配置（先做，fail closed）
- 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，停止并给出配置指引，不猜路径。 vault_root是 vault 唯一绝对路径；下文所有投资笔记/与相对目录都从它派生。screen.py也遵守同一配置。wencai_cli可覆盖问财 CLI；未配置时按当前 skills 根目录下的同级hithink-market-query/scripts/cli.py自动发现。ifind_evidence_helper是可选适配器；未配置就标明降级，core 名单照常完成。- commit 前缀从
git_identity读取：优先取当前平台 adapter 键（claude/codex），其次default，均无则用中性[ai]。下文以<git_identity>表示解析结果。
能力边界（铁律）
| ✅ 做（本 skill） | ❌ 不做（交给 stock-buddy） |
|---|---|
| 主线 → 载体候选发现（ETF / 龙头股） | 主线本身成不成立（那是提名答辩） |
| 相关度校验、剔除名不副实 | 账户适配（持仓重叠、交易权限） |
| 资金/强度/流动性/弹性打分排序 | 参考条件位（进场/加减仓/退出） |
| 排序理由（可溯源到数据） | 买入/观察/放弃裁决、止损止盈、仓位 |
| 载体 T+N 跟踪（验排序准不准） | 主线退潮判定 |
越界自检：用户若问"这只能不能买 / 估值贵不贵 / 这条主线还行吗"，不作答，软提示：
这属于深度研判。对该标的或主线说「用 stock-buddy 分析」即可。
模式一 · 载体筛选（v3 主流程）
第 1 步 · 确认主线已立项
读 <vault_root>/05-主线追踪/ 下该主线页，取叙事、关键词、死亡条件、当前阶段、已有载体清单。
没有立项主线就没有载体筛选——提示用户先让 stock-daily 提名、拍板建页，或用 stock-buddy 做提名答辩。不要凭一个主题名就开筛。
第 2 步 · 载 Key 与选源
source ~/.zshrc。三条通道额度与鉴权互相独立，任一条能取到就不许写「未取得」。
调用顺序（为省问财额度，从上往下试）：
| 调用顺序 | 通道 | 载体筛选用它拿什么 | 额度 |
|---|---|---|---|
| 1 | a-stock-data（东财/腾讯/通达信/百度） |
§3.7 行业排名（含 leader 领涨股）· §3.8 板块资金流 行业/概念×今日/5日/10日 · §3.3 个股所属板块归属 · §4.5 个股资金流 120 日 · §1.2 腾讯批量行情（ETF 也支持） |
零鉴权、无额度 |
| 2 | hithink-finance CLI |
行情快照/K线/指数成分（快照不含 ETF） | 额度独立于问财，Key 在钥匙串（看 auth status 不是 doctor） |
| 3 | 问财 hithink-market-query |
主题 ETF 检索、ETF 技术指标与资金流、复合条件筛股问句 | 每日额度有限、三个 skill 共用，仅限正面清单内场景 |
权威性（同一数字多源冲突时以谁为准）：hithink-finance（T1 官方结构化） > 问财（T2） > a-stock-data（T3 公开爬取）。写入 vault 的数字，若 T1 取得到则以 T1 为准并标注来源。
T 编号表权威性，不是调用顺序。 这两条不是同一个排序：调用顺序管的是"先问谁省钱"，权威性管的是"打架听谁的"。任何地方都不得把 a-stock-data 说成比 hithink-finance 更权威，也不得把问财说成应该优先调用。
What ships with it
5 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 · 194 lines · 191 tokens per session scan A e8fe55472794
stock-screener is a skill published in the GitHub repository Taosheng777/a-share-mainline-os (2 stars, last pushed 26d ago), licensed MIT. It adds 191 tokens to every session and 4,639 once invoked, about $0.0010 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.