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 adambbhe/TDX-finance-mcp-plugin-v3 --skill tdx-daban-yijinerb-ps-skillgit clone --depth 1 https://github.com/adambbhe/TDX-finance-mcp-plugin-v3Wrote 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/adambbhe/tdx-finance-mcp-plugin-v3/tdx-daban-yijinerb-ps-skill)<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-daban-yijinerb-ps-skill"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-daban-yijinerb-ps-skill/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/adambbhe/tdx-finance-mcp-plugin-v3/tdx-daban-yijinerb-ps-skill"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-daban-yijinerb-ps-skill.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 | $0.00203 | $0.03075 |
| Opus 5 | $0.00102 | $0.01537 |
| Sonnet 5 | $0.00041 | $0.00615 |
| Haiku 4.5 | $0.00020 | $0.00308 |
Grade A, and why
一进二量化打板 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 13d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
一进二量化打板（盘后建池 + 次日竞价定夺）
为什么聚焦一进二（设计前提）
- 采样池小：只取上一交易日首板涨停的股票（通常几十只），数据分析快，且可以逐只做深度多维分析（封板质量、资金、龙虎榜席位、题材身位），不像全市场打板那样只能粗筛。
- 更贴合实战：一进二是有明确母体（昨日首板）的接力博弈，逻辑链清晰、可验证，比"凭空猜哪只首板"更可落地。
⏰ 两种运行时段（先判断现在是哪种）
- 模式A —— 盘后（收盘时段，约 15:00 后）：取当日封住首板的涨停股（=次日一进二候选母体），逐只深度分析，产出"次日竞价重点监测股"清单。
- 模式B —— 次日 9:25-9:29 竞价窗口：对监测池逐只调
tdx_quotes取实时竞价数据，套阈值+排雷+评分+可成交性，定出当日最终一进二可打标的。
时段判断：盘后/收盘/"选监测股"→模式A；竞价/早盘/"今天打哪只"→模式B（无现成监测池则先即时重建首板池再进竞价）。
⚠️ 数据能力声明
- 竞价数据（模式B）：9:25-9:29 窗口内
tdx_quotes现价=竞价撮合价、成交量=竞价量，即真实竞价。量比/委比/席位取不到则标注"近似/证据不足"，不臆造。 - 首板池：模式A 取"当日涨停"后须逐只用日 K 验证"确为首板（非二板及以上）"。
- 选股调用格式（重要，避免"NLP 服务宕机"）：
tdx_screener走 NLP 服务JNLPSE:wendaQuery，请求体必须是数组[{"message":"涨停","rang":"AG","pageNo":"1","pageSize":"20"}]；切勿构造{"Head":{...},"Question":"涨停"}之类旧格式（会触发"NLP 服务宕机"）。用 MCP 工具tdx_screener message="涨停" rang="AG"调用即为正确格式。该 NLP 服务偶发繁忙，报错时应重试 2-3 次或稍后再跑，不要当成"无数据"（脚本run-modeA/B.mjs已内置选股自动重试）。
配套运行器脚本（本地直跑，已按 6/18 实盘校准）
技能逻辑同时落地为可本地运行的脚本，便于自动化与回归：
run-modeA.mjs（盘后建池）：取当日涨停→验证首板→封板质量评分（封流比为主指标 + 封成比 + 开板次数 + 首封时间 + 板型）→ 输出modeA-result.md（人读）与modeA-pool.json（供模式B 读取）。node run-modeA.mjs --token=TDX-xxxx --top=20
run-modeB.mjs（次日 9:25-9:29 竞价定夺）：读modeA-pool.json→逐只取实时竞价 quotes→竞价评分（高开 + 量比LB+ 委比Wtb）+ 可成交性（Now>=ZTPrice判顶一字买不进）+ 板块梯队身位（同题材聚类排龙头/卡位/跟风）→综合分选最终标的→modeB-result.md。弱势退潮自动停做。node run-modeB.mjs --token=TDX-xxxx --top=10
- 回归测试：
node test-modeA.mjs、node test-modeB.mjs（离线，用真实返回数据形状验证解析与评分）。
阈值已按 6/18 真实分布校准：封流比 ≥3%极硬/1.5-3%硬/0.8-1.5%中/<0.8%偏软；封成比 ≥60高/30-60中/<30低。
Overview
工具：tdx_screener、tdx_quotes、tdx_kline、tdx_api_data、tdx_lookup_stock、tdx_indicator_select。
一进二目标：首次封涨停（首板）、次日有望再次封板晋级二板的主板个股。 连板容错极低，板块梯队与昨日封板质量权重最高。深度评分见 references/scoring-rules.md。
Workflow — 模式A（盘后：深度分析，选出次日重点监测股）
池子小，对每只首板都尽量跑全下面 5 项，不要只看涨停就入池。
- 取当日首板池：
tdx_screener message="涨停"（盘后口径=当日涨停）；名称解析代码用tdx_lookup_stock。 - 验证"当日首板"（地基）：
tdx_kline period="4" wantNum="4"——当日涨幅≥9.8% 且 前一日未涨停（<9.8%）。此前已连板的剔除。 - ① 封板质量：
tdx_api_data entry="TdxSharePCCW.tdxf10_gg_jyds" fixedTag="ztfx"读T011 首次涨停时间、fdje 封单金额、zt 主题、yy 原因；结合日 K 判断一字/秒板/换手板/烂板。首封早、封单大、换手板=优质；烂板（尾盘炸板回封）降权或剔除。 - ③ 板块梯队与身位：
tdx_api_data fixedTag="zttzbkz"（题材族谱）+fixedTag="sjcd"（事件驱动）定主线归属；tdx_screener（如"2连板"、题材词）判断该股在梯队里的身位（龙一/龙二/后排）与梯队完整度。孤票淘汰。 - ④ 资金与筹码：
fixedTag="zjlx"看主力净额是否支持；如当日有龙虎榜，先fixedTag="comreq"+jglhb查可用日期再取fixedTag="jglhb"看席位接力（游资/一线席位为佳；权限不足则跳过标注）；用tdx_indicator_select message="<名称> 换手率"/流通市值看筹码。 - ⑤ 位置/空间 + 市场环境：
tdx_kline period="4" wantNum="30"看是否高位套牢/前高压制、近 5 日涨幅是否透支；指数+涨停/2连板/3连板家数判明日环境（弱势退潮则预警"明日大概率停做"）。 - 输出监测池：按 scoring-rules 初步打分排序，给"次日竞价重点监测股"清单（建议 5-15 只），每只标注：代码|名称|封板质量|题材与身位|资金|监测理由|次日竞价要盯什么（高开是否落 4.5-7%、竞价量占比、是否一字买不进）。
What ships with it
9 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.
- 13d ago First seen · 86 lines · 203 tokens per session scan A a8deb8fa16ac
一进二量化打板 is a skill published in the GitHub repository adambbhe/TDX-finance-mcp-plugin-v3 (35 stars, last pushed 2mo ago), licensed MIT. It adds 203 tokens to every session and 3,075 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
hithink-finance
A routing guide for accessing Chinese A-share financial data, including prices, company reports, valuations, funds, indices, sectors, and local data storage.
hithink-finance-fund
A command-line guide for querying fund information, including profiles, managers, holdings, prices, returns, financial data, news, and exchange-traded fund snapshots. A command-line tool is a program controlled by typed terminal commands.
hithink-finance-data
A local data-management skill for the HiThink Finance command-line tool and its DuckDB database. DuckDB is a database stored in a local file.
hithink-finance-market
A command-line tool entry for retrieving ordinary Chinese A-share market data, including snapshots, historical price bars, trading calendars, adjustment factors, and company actions.
hithink-finance-special-data
A command-line tool entry for retrieving special Chinese market lists and event data, such as limit-up stocks, limit-down stocks, unusual moves, hot stocks, and Dragon-Tiger records.
hithink-finance-futures
A command-line data source for public futures-market information, including contracts, positions, warehouse receipts, basis, trading schedules, and price charts. Futures are agreements to buy or sell an asset at a set future date.