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 Haochenhust/ch-skills --skill tushare-datagit clone --depth 1 https://github.com/Haochenhust/ch-skillsWrote 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/haochenhust/ch-skills/tushare-data)<a href="https://agentmods.dev/skills/haochenhust/ch-skills/tushare-data"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/tushare-data/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/haochenhust/ch-skills/tushare-data"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/tushare-data.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 | $0.00109 | $0.01593 |
| Opus 5.5 | $0.00044 | $0.00637 |
| Sonnet 5.5 | $0.00022 | $0.00319 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
tushare-data 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 2mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tushare Data
Primary structured data source for A-share investment research via the Tushare Pro API. A thin CLI wrapper (scripts/fetch_tushare.py) over the tushare Python SDK.
When to Use
- Any task needing stock fundamentals, valuation, or financial statements
- Preferred over AKShare for: financial statements, PE/PB/PS, shareholder data, earnings forecasts
- AKShare remains preferred for: ETF data, sector fund flows, northbound capital (Tushare needs higher points)
Setup
- Get a token: register at https://tushare.pro and copy your API token from the user center. Financial-statement interfaces need ~2000 points.
- Install deps and export your token:
python3 -m venv .venv
.venv/bin/pip install tushare pandas
export TUSHARE_TOKEN=<your Tushare Pro token> # never hard-code this
PY=.venv/bin/python3
The script reads the token from the TUSHARE_TOKEN env var (or a --token flag). Keep it in your shell profile or a secret manager, not in the skill.
Available Interfaces
Market Data
| Mode | Description | Key Fields |
|---|---|---|
daily |
Daily OHLCV | open, high, low, close, vol, pct_chg |
weekly |
Weekly OHLCV | Same as daily |
monthly |
Monthly OHLCV | Same as daily |
daily_basic |
Daily valuation | PE, PE_TTM, PB, PS, turnover, total_mv, circ_mv, dv_ratio |
adj_factor |
Adjustment factor | For computing forward/backward adjusted prices |
stock_basic |
Stock list | ts_code, name, industry, area, list_date, act_name |
trade_cal |
Trading calendar | cal_date, is_open, pretrade_date |
Financial Statements
| Mode | Description | Key Fields |
|---|---|---|
income |
Income statement | revenue, total_revenue, n_income, basic_eps, ebit, ebitda |
balancesheet |
Balance sheet | total_assets, total_liab, total_hldr_eqy, inventories |
cashflow |
Cash flow | n_cashflow_act, n_cashflow_inv_act, free_cashflow |
fina_indicator |
Financial ratios | ROE, ROA, grossprofit_margin, netprofit_margin, current_ratio, debt_to_assets, netprofit_yoy |
What ships with it
2 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.
- 2mo ago First seen · 130 lines · 109 tokens per session scan A db8cb77351ed
tushare-data is a skill published in the GitHub repository Haochenhust/ch-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 1,593 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
tushare-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tushare-dataHaochenhust/ch-skills | Skill | 9 | 3mo ago | MIT | A | 109 | Claude Code |
| rugpull-detectorDjordjeMojsilovic/Djordjes-Claude-Setup | Skill | 4 | 3mo ago | none | A | 205 | Claude Code, Codex |
| ma-playbookalirezarezvani/claude-skills | Skill | 29k | yesterday | MIT | A | 29 | Claude Code |
| fiscalisteromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 320 | Claude Code, Codex |
| comptableromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 153 | Claude Code, Codex |
| syndicromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 204 | Claude Code, Codex |
| prompt-masternidhinjs/prompt-master | Skill | 16k | 15d ago | MIT | B | 78 | Claude Code, Codex |