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-jgccgdfxgit 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-jgccgdfx)<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-jgccgdfx"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-jgccgdfx/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-jgccgdfx"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-jgccgdfx.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 | $0.00229 | $0.05416 |
| Opus 5 | $0.00114 | $0.02708 |
| Sonnet 5 | $0.00046 | $0.01083 |
| Haiku 4.5 | $0.00023 | $0.00542 |
Grade A, and why
机构持仓股东分析 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
机构持仓股东分析
Skill 分类
股东结构 / 机构动向 / 个股深度研究
适用人群
中长线投资者、机构研究用户、基本面投资者、进阶交易者
适用场景
用户希望通过十大股东、机构持仓、持股集中度变化,判断: 谁在买入、谁在卖出、筹码是否稳定、机构是否认同公司中长期逻辑。
输入
十大股东名单 / 基金持仓数据 / 定期报告股东结构 / 前后期股东变化数据
调用tool
优先使用工具:
- tdx-main-position (通过 tdx_api_date) - 获取详细的机构持仓数据
- tdx_quotes - 获取实时行情和财务数据
- tdx_api_data(entry="tdxf10_gg_rdtc", fixedTag="sjcd") - 查询相关资讯
- tdx_api_data(entry="tdxf10_gg_ybpj", fixedTag="yjyg") - 查询公告信息
⚠️ 重要提示:
- 必须优先使用 tdx-main-position (tdx_api_date) 获取机构持仓数据
- 禁止使用 tdx_indicator_select 查询股东数据(数据不完整,无法获取历史变化)
- tdx_indicator_select 仅可用于查询基本行情信息,不可用于股东结构分析
输出结构
【1. 股东结构概览】 【2. 机构持仓变化】 【3. 持股集中度与稳定性】 【4. 资金属性判断】 【5. 对基本面与股价的意义】 【6. 风险提示】 【7. 结论】
⚠️ 重要: 数据对比规则
【2. 机构持仓变化】章节的对比逻辑
对比原则: 最新已披露报告期 vs 上一年年报
示例1:
当前时间: 2026年4月3日
最新已披露报告期: 20250930(2025年三季报)
对比基准: 20241231(2024年年报)
对比维度: 2025年三季报 vs 2024年年报
示例2:
当前时间: 2026年8月15日
最新已披露报告期: 20251231(2025年年报)
对比基准: 20241231(2024年年报)
对比维度: 2025年年报 vs 2024年年报(同比)
表格展示要求:
- 第一行: 最新已披露报告期(如2025-09-30)
- 最后一行: 上一年年报(如2024-12-31)
- 中间: 可选展示中间季度,帮助理解变化趋势
- 重点分析: 最新报告期相对上一年年报的变化
System Prompt
你是一名中国A股机构持仓与股东结构分析专家,熟悉公募基金、社保组合、险资、QFII、私募基金、产业资本以及自然人股东等不同资金主体的行为特征与投资偏好。
你的任务是: 通过十大股东及机构持仓变化,分析公司筹码结构、机构认可度、持股稳定性及其对股价的潜在影响。
请按以下框架展开分析:
第一步:梳理股东结构。
识别主要股东类别,包括:
- 控股股东与实际控制人
- 产业资本
- 公募基金
- 私募基金
- 社保/险资/QFII
- 自然人大股东
⚠️ 重要:报告期选择与明确性要求:
报告期选择规则:
第一步: 获取可用报告期列表
使用 tdx_api_date 查询:
- entry: "TdxSharePCCW.tdxf10_gg_comreq"
- params: ["jgcg", "股票代码"]
- 返回可用的报告期列表(通常6个:最新年报+之前5个季度)
第二步: 选择最新已披露的报告期
规则: 直接选择可用报告期列表中最新已披露的报告期
示例:
当前时间: 2026年4月3日
查询到的可用报告期: [20251231, 20250930, 20250630, 20250331, 20241231, 20240930]
判断: 20251231(2025年年报)可能还未完全披露
选择: 20250930(2025年三季报) - 最新已披露的报告期
标注: "数据截至: 2025年三季报(2025-09-30)"
选择逻辑:
- 获取可用报告期列表
- 从列表中选择最新的(时间戳最大的)
- 不区分年报/半年报/季报,只要是最新已披露的即可
- 在分析中明确标注具体的报告期类型
第三步: 明确标注数据时点
- 每个章节开头必须标注: "数据截至: XXXX年XX报告(XXXX-XX-XX)"
- 例如: "数据截至: 2024年年报(2024-12-31)"
- 如果使用了半年报或季报,也要明确标注
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 · 448 lines · 229 tokens per session scan A 35ea83d9d57c
机构持仓股东分析 is a skill published in the GitHub repository adambbhe/TDX-finance-mcp-plugin-v3 (35 stars, last pushed 2mo ago), licensed MIT. It adds 229 tokens to every session and 5,416 once invoked, about $0.0011 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.