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.
git clone --depth 1 https://github.com/Veblin/invest-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/plugins/veblin/invest-skills/gemini-extension)<a href="https://agentmods.dev/plugins/veblin/invest-skills/gemini-extension"><img src="https://agentmods.dev/badge/plugins/veblin/invest-skills/gemini-extension/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/plugins/veblin/invest-skills/gemini-extension"><img src="https://agentmods.dev/badge/plugins/veblin/invest-skills/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
invest-skills 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.
What it actually says
{
"name": "invest-skills",
"version": "0.3.2",
"description": "A股多因子投研助手 — 九模块研究备忘录,带数据引用的 Markdown 报告。研究工具,非决策工具。",
"settings": [
{
"name": "Extension Directory",
"description": "Extension installation directory (auto-set by Gemini CLI)",
"envVar": "GEMINI_EXTENSION_DIR",
"sensitive": false
},
{
"name": "Tushare Token",
"description": "Tushare Pro API Token(可选,注册即得 120 积分)— https://tushare.pro",
"envVar": "TUSHARE_TOKEN",
"sensitive": true
},
{
"name": "FRED API Key",
"description": "FRED 美联储宏观经济数据 API Key(可选,免费注册)— https://fred.stlouisfed.org/docs/api/api_key.html",
"envVar": "FRED_API_KEY",
"sensitive": true
},
{
"name": "Tavily Search API Key",
"description": "Tavily AI 搜索 API Key(可选,免费 1000次/月)— https://tavily.com",
"envVar": "TAVILY_API_KEY",
"sensitive": true
},
{
"name": "Longbridge App Key",
"description": "Longbridge OpenAPI App Key(可选,港股/美股兜底)— https://open.longbridge.com",
"envVar": "LONGBRIDGE_APP_KEY",
"sensitive": true
},
{
"name": "Longbridge App Secret",
"description": "Longbridge OpenAPI App Secret(可选)— https://open.longbridge.com",
"envVar": "LONGBRIDGE_APP_SECRET",
"sensitive": true
},
{
"name": "Longbridge Access Token",
"description": "Longbridge OpenAPI Access Token(可选)— https://open.longbridge.com",
"envVar": "LONGBRIDGE_ACCESS_TOKEN",
"sensitive": true
},
{
"name": "Finnhub API Key",
"description": "Finnhub API Key(可选,美股数据,免费 60次/分钟)— https://finnhub.io",
"envVar": "FINNHUB_API_KEY",
"sensitive": true
},
{
"name": "AlphaVantage API Key",
"description": "AlphaVantage API Key(可选,美股数据,免费 25次/天)— https://www.alphavantage.co",
"envVar": "ALPHAVANTAGE_API_KEY",
"sensitive": true
}
]
}
What ships with it
29 files beside gemini-extension.json 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.
- scripts/archive/backfill_futures_daily.py 1.8 KB runs code
- scripts/archive/backfill_market_daily.py 2.6 KB runs code
- scripts/archive/backtest_calendar.py 8.3 KB runs code
- scripts/archive/backtest_futures.py 15 KB runs code
- scripts/archive/backtest_h1.py 9.6 KB runs code
- scripts/archive/backtest_h2.py 8.3 KB runs code
- scripts/archive/backtest_h3.py 4.6 KB runs code
- scripts/archive/backtest_h4.py 13 KB runs code
- scripts/archive/backtest_h6.py 11 KB runs code
- scripts/archive/protect-main-branch.sh 4.5 KB runs code
- scripts/archive/README.md 1.5 KB
- scripts/archive/scenario_baselines.py 6.6 KB runs code
- scripts/archive/tmp_4050_band.py 3.3 KB runs code
- scripts/archive/tmp_wave_analysis.py 6.3 KB runs code
- scripts/archive/tmp_wave_analysis2.py 4.9 KB runs code
- scripts/build_skillhub_packages.py 68 KB runs code
- scripts/build_wb_package.sh 2.8 KB runs code
- scripts/bump-version.sh 1.2 KB runs code
- scripts/link-skills.sh 3.0 KB runs code
- scripts/research/entry_check.py 14 KB runs code
- scripts/setup_workbuddy_windows.ps1 7.5 KB runs code
- scripts/skillhub-dist/.github/workflows/skillhub-publish.yml 2.6 KB
- scripts/skillhub-dist/.gitignore 89 B
- scripts/skillhub-dist/README.md 3.3 KB
- scripts/smoke_interfaces.py 6.7 KB runs code
- scripts/sync_version.py 20 KB runs code
- scripts/wb_bundle/bootstrap.sh 3.1 KB runs code
- scripts/wb_bundle/README-安装.md 3.5 KB
- scripts/wb_bundle/SKILL.md 3.7 KB
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 Changed 2ea31a8a4bf9
- 21d ago Changed eadb7164df09
- 1mo ago Changed · -6 lines a27839b17099
- 1mo ago First seen · 68 lines scan A b14e41237317
invest-skills is a plugin published in the GitHub repository Veblin/invest-skills (17 stars, last pushed 13d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
a-share-mainline-os
A Chinese stock-market review tool that summarizes the day’s market conditions, the strength of a tracked investment theme, and possible breaches of your own holding rules.
xvary-stock-research
Institutional-style stock snapshots in Claude Code: /analyze, /score, /compare from public EDGAR + market data.
sp-global
Query S&P Capital IQ financials, prices, and transcripts.
liquilens
Find covered financial institutions, review public asset-quality disclosures, and inspect RBI supervisory evidence with source dates and coverage limits. LiquiLens helps analysts prepare institution review questions while preserving missing or non-comparable evidence. It does not access private accounts, replace…
property
UK property investment plugin for Claude Code. Real Land Registry comparable sales, Rightmove listings, EPC ratings, and rental data. Full analysis, deal screening, BUY/WATCH/PASS verdicts, and investment summaries for UK residential property.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.