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-yijinerb-dabangit 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-yijinerb-daban)<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yijinerb-daban"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yijinerb-daban/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-yijinerb-daban"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yijinerb-daban.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 | $0.00262 | $0.03315 |
| Opus 5.5 | $0.00105 | $0.01326 |
| Sonnet 5.5 | $0.00052 | $0.00663 |
| Haiku 4.5 | $0.00026 | $0.00331 |
Grade B, and why
tdx-yijinerb-daban scanned grade B 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 2d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
py -3.13 scripts/run_modeA_cloud.py --top=20 # 盘后建池，token 同 .mcp.json / TDX_API_TOKEN How it starts
The opening of the file, as written. The whole thing — 111 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 · 本地通道）
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、板块梯队、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。
⏰ 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：对监测池逐只取实时竞价快照，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（无现成监测池则先跑模式A 再进竞价）。
⚠️ 数据能力声明（本地通道 v3.3）
☁️ 云端通道（tdx-finance-mcp 同源，无需本地终端）
scripts/run_modeA_cloud.py：涨停池/封板明细/涨停原因改走 screener 路由（JNLPSE:wendaQuery，
一条查询自带 首封时间/开板次数/封单额/最大封单额/封成比/板型/几天几板/原生涨停原因——字段比本地 ZDT 全），
首板验证走 PBFXT 日K，封流比分母用 PBHQInfo 流通市值（比例法）。
默认剔 ST/20cm/连板；产出三件套与本地版同构（modeB 可读）。
py -3.13 scripts/run_modeA_cloud.py --top=20 # 盘后建池，token 同 .mcp.json / TDX_API_TOKEN
对照实测（2026-10-23）：云端池 53 只 vs 本地 52（screener 84 vs B007 82，口径±2）；湘佳封流比 7.22%/封成比 276.1 两通道一致； 云端额外给出首封时间/开板次数/原生原因（当日本地 ZDT 缺失时云端明显更优）。 差异：市场环境仅 涨停/跌停 家数（简化口径，闸门 GATE_DT 照用），完整 regime 需终端本地版。
- 数据全部来自本地通达信终端（tqcenter 直连，Python 脚本，无需 token/云端服务）。前提：终端已启动。
- 涨停池：内置条件选股公式
B007 沪深京涨跌停选股跑全A → 逐只用日K验证"确为首板（非二板及以上）"。 - 封板明细（首封时间/开板次数/最大封单）：
get_zdt_data涨跌停接口；封单为量（手）×涨停价换算金额。 - 题材/涨停原因：云端"涨停原因"接口本地无等价物 → 用
get_relation概念板块近似，输出标注themeSource=concept-approx，不臆造。 - 量比(LB)：本地快照无量比字段 → 竞价评分量比项自动跳过（竞价满分 70），池内统一缺失不影响排序。
- 委比(Wtb)/涨停价/流通市值：由五档、昨收×1.1、流通股本自算。
- 事实、推断、交易动作分开写；缺失字段标注"近似/证据不足"。
配套运行器脚本（本地直跑，评分逻辑与 v3.2.4/442 样本校准版逐位一致）
scripts/run_modeA.py（盘后建池）：B007 取当日涨停 → 日K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）、modeA-pool.json（全量字段，供模式B 读取）与modeA-features.csv（扁平特征表，按日归档history/）。py -3.13 scripts/run_modeA.py --top=20scripts/run_modeB.py（次日 9:25-9:29 竞价定夺）：读modeA-pool.json→ 逐只取实时竞价快照 → 竞价评分（高开+委比）+ 可成交性（Now>=ZTPrice判顶一字买不进）+ 板块梯队身位（概念聚类排龙头/卡位/跟风）→ 综合分选最终标的 →modeB-result.md+modeB-features.csv。市场闸门触发自动停做（盘后跌停≥8 或 池均高开≤1.3%）。py -3.13 scripts/run_modeB.py --top=10scripts/backtest.py（攒够 ≥5 交易日跑）：读history/*/modeA-pool.json+ 日K回补 T+1/T+2/T+3 →backtest-samples.csv（分析主表）+backtest-report.md。py -3.13 scripts/backtest.py- 回归测试（离线，不联网不连终端）：
py -3.13 scripts/test_scoring.py→ 应 60/60 全过。
What ships with it
16 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.
- DATA-SCHEMA.md 7.3 KB
- references/scoring-rules.md 11 KB
- RUNBOOK.md 4.3 KB
- scripts/_regime_analyze.py 3.4 KB runs code
- scripts/_regime_study.py 3.3 KB runs code
- scripts/_xlsx_read.py 2.1 KB runs code
- scripts/backtest.py 6.9 KB runs code
- scripts/build_pool_yday.py 6.3 KB runs code
- scripts/common.py 13 KB runs code
- scripts/replay_auction.py 2.6 KB runs code
- scripts/run_modeA_cloud.py 13 KB runs code
- scripts/run_modeA.py 9.7 KB runs code
- scripts/run_modeB.py 9.6 KB runs code
- scripts/scoring.py 18 KB runs code
- scripts/test_scoring.py 12 KB runs code
- scripts/track_daban.py 4.5 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.
- 2d ago First seen · 111 lines · 262 tokens per session scan B 81e8cf762fae
tdx-yijinerb-daban is a skill published in the GitHub repository adambbhe/TDX-finance-mcp-plugin-v3 (42 stars, last pushed 3d ago), licensed MIT. It adds 262 tokens to every session and 3,315 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.
Other skills, from other repositories
gendangzou-skill
A Chinese-language research tool for analyzing sectors in China's stock market using platform, API, and independently installable application data.
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.
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.