HiThink-Tech/Financial-API is an official Tonghuashun service that provides A-share market data, including prices, financial statements, indices, sectors, funds and trading activity through APIs and developer tools. It serves AI agents, quantitative researchers and application developers. The catalogue add-ons help coding agents access and use this financial data.
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 HiThink-Tech/Financial-API --skill hithink-finance-researchgit clone --depth 1 https://github.com/HiThink-Tech/Financial-APIWrote 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/hithink-tech/financial-api/hithink-finance-research)<a href="https://agentmods.dev/skills/hithink-tech/financial-api/hithink-finance-research"><img src="https://agentmods.dev/badge/skills/hithink-tech/financial-api/hithink-finance-research/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/hithink-tech/financial-api/hithink-finance-research"><img src="https://agentmods.dev/badge/skills/hithink-tech/financial-api/hithink-finance-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 12 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00069 | $0.00816 |
| Opus 5 | $0.00034 | $0.00408 |
| Sonnet 5 | $0.00014 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
hithink-finance-research 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 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.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hithink-finance-research
研究工作流路由。它不拥有独立 research 命令，而是指导 Agent 组合 data、db 和 market panel 产出可复现数据证据。
前置条件表
| 条件 | 操作 |
|---|---|
| 开始任何 CLI 调用 | 先读取并遵循 hithink-finance-shared |
| 不确定命令是否存在或参数是否变化 | 运行 hithink-finance capabilities --format json，再运行 hithink-finance schema <id> --format json |
| 需要执行下表某个命令 | 先读取对应 reference 文件，不要只凭命令名猜参数 |
| 结果可能是全市场、分页、多标的或长区间 | 使用命令声明的 --output <path> 落盘；远端 stdout 只返回摘要 |
快速决策
| 用户意图 | 首选命令 / 路由 |
|---|---|
| 用户要构造研究样本/面板 | 先 data status 和 data validate，再 market panel --output <file> |
| 用户要 SQL 统计或因子分布 | 用 db query 小结果或 db export 大结果 |
| 用户要解释数据缺口 | 先 data validate，必要时 data sync 或 data repair |
| 用户要实时快照或最新榜单 | 切到对应业务 skill，不在 research 中直接取数 |
| 用户要投资建议/策略推荐 | 拒绝给出建议，可提供中立数据分析边界 |
Shortcuts
| 命令 | 何时使用 |
|---|---|
| research-workflow.md | 组合 data/db/market panel 做中立研究数据准备 |
原生命令与 schema
hithink-finance capabilities --format json
hithink-finance schema <capability-id> --format json
hithink-finance data <command> --help
hithink-finance db <command> --help
hithink-finance market panel --help
What ships with it
1 file 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 · 59 lines · 69 tokens per session scan A 7f4ded9d172a
hithink-finance-research is a skill published in the GitHub repository HiThink-Tech/Financial-API (3,149 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 816 once invoked, about $0.0003 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
通达信TQ
A connection between Python strategy files and TdxQuant, TongdaXin's platform for securities data analysis and quantitative investment research. It uses the platform's tqcenter.py module to interact with the TongdaXin client.
机构持仓股东分析
A research workflow for examining an A-share company’s major shareholders and institutional holdings. It compares ownership structure, changes in holdings, concentration, and possible investor behavior.
问小达选A股
A Chinese-language stock screener for A-shares, the shares traded on mainland Chinese stock exchanges. It turns natural-language requests into filters for prices, trends, company finances, industries, concepts, and money flows.
政策解读与受益分析
A research assistant for interpreting Chinese policies and tracing how they may affect industries and companies. It is designed for policy research, thematic investing, event-driven analysis, and mapping policy changes to potential beneficiaries.
仓位决策
A Chinese-language decision aid for managing how much money is invested in A-share trades. It considers market conditions, current holdings, risk tolerance, and investment timeframe.
生成交易计划
A trading-plan workflow for an already selected A-share stock. It covers possible entry, adding or reducing a position, profit-taking, stop-losses, and exit conditions.