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 taxueseek/fund-investment-guide --skill invest-cligit clone --depth 1 https://github.com/taxueseek/fund-investment-guideWrote 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/taxueseek/fund-investment-guide/invest-cli)<a href="https://agentmods.dev/skills/taxueseek/fund-investment-guide/invest-cli"><img src="https://agentmods.dev/badge/skills/taxueseek/fund-investment-guide/invest-cli/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/taxueseek/fund-investment-guide/invest-cli"><img src="https://agentmods.dev/badge/skills/taxueseek/fund-investment-guide/invest-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 228 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 241 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00113 | $0.04327 |
| Opus 5.5 | $0.00045 | $0.01731 |
| Sonnet 5.5 | $0.00023 | $0.00865 |
| Haiku 4.5 | $0.00011 | $0.00433 |
Grade A, and why
invest-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
完整触发条件（原始 description）
投资分析 CLI — 数据获取 + 分析框架一体化，dual-mode 运行。 触发：「/cli」「/投资cli」「invest cli」「终端分析」「命令行分析」 或：「用cli分析」「终端查一下」「命令行看看」 命令入口：invest-cli（兜底脚本见下）
invest-cli — 投资分析 CLI
定位
现有 invest 系列 skill 只定义"怎么想"（分析框架），数据靠 web search。 invest-cli 补充"怎么取"（数据获取），把 CLI 脚本和分析框架串起来。
dual-mode：
- Skill 触发 → 调用 CLI 脚本（
--json）→ 用 invest 系列框架解读 → 输出完整分析报告 - 终端直接运行 → 输出表格快照
入口约定：优先 invest-cli 命令（PATH，wrapper 在 ~/.local/bin/）；PATH 无该命令时用 "$HOME/.local/bin/invest-cli" 兜底。不要绕过 wrapper 直接 python3 裸跑系统解释器——那样会丢掉 venv 里的 yfinance，美股路径静默降级到 Bitget rToken 报价。
路由逻辑
- 识别标的类型（股票/基金/美股/选股）
- 调用对应子命令，
--json获取结构化数据 - 将 JSON 数据传给 invest 系列分析框架
- 输出完整分析报告
子命令
stock — A股/港股分析
invest-cli stock <代码/名称> [--json]
- 数据源：同花顺金融数据服务优先（A 股官方 REST）；失败或港股回退东方财富
- 获取：实时行情 + PE/PB/PS/PCF + 近 5 年年报 + ROE/毛利率/现金流（港股仍走东财）
- 分析框架：对标 invest-stock 三关审查（懂不懂 / 好不好 / 贵不贵）
- 内置名称映射：茅台→600519、五粮液→000858、宁德时代→300750 等
fund — 基金分析
invest-cli fund <代码/名称> [--json]
- 数据源：同花顺金融数据服务优先；失败回退东方财富（intent deep fund 仍先盈米）
- 获取：净值/业绩/回撤/费率/经理/十大重仓
- 分析框架：对标 invest-fund 三关审查
- 内置名称映射：易方达蓝筹（精选）→005827、中欧医疗→003096 等。注意 110011 现为「易方达优质精选(QDII)」，旧文档把「易方达蓝筹」映射到 110011 是错的（源码注释里专门记过这次纠偏）
us — 美股分析
invest-cli us <代码> [--json]
- 数据源：yfinance 优先（估值/财务/评级）；缺失或失败时回退腾讯行情（真实美股行情，含 PE/PB/市值/52周/股息率/ROE），再退 Bitget rToken 报价（USDT，非官方价，只有成交价与 24h 区间）
- 获取：全量快照（yfinance）或行情口径快照（tencent）或行情-only（bitget，
quote_type=rtoken） - 分析框架：对标 invest-stock 美股四维度（ROE持续性/负债安全/FCF质量/经济护城河）；Bitget 回退仅有报价，无财务
quote — 免鉴权多标的实时行情（跨市场）
invest-cli quote <代码[,...]> [--json]
- 用途：只要行情的问题（「现在多少钱」「涨跌多少」「这几只对比一下」）
- 数据源：腾讯行情（零鉴权），一次 HTTP 请求可带任意多个标的，跨 A股/港股/美股/ETF/可转债
- 实测：单标的 ~130ms，6 标的混合 ~132ms；缓存 10s（比快照链的 60s 更严，行情语境下可忽略）
- 与
stock/fund/us的分工：那三条是深度快照（含基本面，冷取数 0.5s 起，美股 4s 量级），quote是纯行情。问基本面却用 quote 会缺 ROE/净利润；问行情却用 stock 会多付几倍等待
sec — 美股财报原文（SEC EDGAR，免费官方源）
invest-cli sec <代码> [--forms 10-K,10-Q,8-K] [--filings 5] [--json]
What ships with it
60 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.
- .gitignore 26 B
- data-sources.yaml 7.2 KB
- docs/ablation.md 4.3 KB
- docs/capability-gap.md 7.7 KB
- docs/data-sources.md 14 KB
- docs/复核报告_2026-09-22_hunt_check.md 8.9 KB
- docs/复核报告_2026-09-22_第五轮_独立验证.md 13 KB
- docs/审查报告_2026-09-21_第二轮.md 17 KB
- docs/性能与缺陷治理报告_2026-09-19.md 14 KB
- docs/性能与缺陷治理报告_2026-09-21.md 40 KB
- docs/性能与缺陷治理报告_2026-09-22_第五轮_腾讯源整合.md 28 KB
- docs/性能与缺陷治理报告_2026-09-22_第四轮.md 28 KB
- docs/第五轮状态交接_2026-09-22.md 5.5 KB
- docs/被吸收实现的审计与处置_2026-09-22.md 7.4 KB
- requirements.txt 385 B
- scripts/_common.py 13 KB runs code
- scripts/cmd_capabilities.py 8.9 KB runs code
- scripts/cmd_datasources.py 1.9 KB runs code
- scripts/cmd_fund.py 16 KB runs code
- scripts/cmd_info.py 1.4 KB runs code
- scripts/cmd_intent.py 14 KB runs code
- scripts/cmd_kline.py 4.8 KB runs code
- scripts/cmd_present.py 5.5 KB runs code
- scripts/cmd_quote.py 4.0 KB runs code
- scripts/cmd_screen.py 4.4 KB runs code
- scripts/cmd_sec.py 3.3 KB runs code
- scripts/cmd_stock.py 17 KB runs code
- scripts/cmd_ttskill.py 2.4 KB runs code
- scripts/cmd_us.py 28 KB runs code
- scripts/cmd_watchlist.py 6.0 KB runs code
- scripts/cmd_westock.py 2.2 KB runs code
- scripts/cmd_wind.py 1.1 KB runs code
- scripts/cmd_yingmi.py 1022 B runs code
- scripts/conftest.py 1.7 KB runs code
- scripts/invest_cli.py 14 KB runs code
- scripts/sources/__init__.py 1.8 KB runs code
- scripts/sources/argo.py 7.4 KB runs code
- scripts/sources/bitget.py 6.6 KB runs code
- scripts/sources/eastmoney.py 5.7 KB runs code
- scripts/sources/env.py 3.8 KB runs code
- scripts/sources/fred.py 10 KB runs code
- scripts/sources/hithink.py 32 KB runs code
- scripts/sources/registry.py 12 KB runs code
- scripts/sources/route.py 13 KB runs code
- scripts/sources/sec_edgar.py 12 KB runs code
- scripts/sources/tencent.py 49 KB runs code
- scripts/sources/ttskill.py 19 KB runs code
- scripts/sources/westock.py 18 KB runs code
- scripts/sources/wind.py 8.2 KB runs code
- scripts/sources/yfinance.py 1.3 KB runs code
- scripts/sources/yingmi.py 9.6 KB runs code
- scripts/tencent_samples.json 14 KB
- scripts/test_bitget.py 4.7 KB runs code
- scripts/test_capabilities.py 2.5 KB runs code
- scripts/test_claims.py 4.8 KB runs code
- scripts/test_cli_guards.py 24 KB runs code
- scripts/test_contract.py 4.6 KB runs code
- scripts/test_env.py 2.3 KB runs code
- scripts/test_fred.py 2.8 KB runs code
- scripts/test_hithink.py 16 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.
- 1mo ago Changed · +14 lines e19679d2c044
- 1mo ago Changed · +17 lines · +6 tokens per session 53061d979dbc
- 1mo ago Changed · +39 lines · +18 tokens per session 2640d1f64f0d
- 1mo ago First seen · 206 lines · 89 tokens per session scan A 6fad83317cde
invest-cli is a skill published in the GitHub repository taxueseek/fund-investment-guide (21 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 4,327 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
paymob-integration
Integrate and operate Paymob payments in Egypt, UAE, KSA, and Oman — checkout, Intention API, HMAC webhooks, SDKs, plugins, refunds, reconciliation, go-live, diagnostics, and support tickets.
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
investment-report-reader
Read and extract content from PDF investment reports — sell-side notes (GS/MS/JPM/UBS/Citi/BofA), 10-Ks, annual reports, fund factsheets, manager commentaries, and macro outlooks. Specialises in CHARTS, TABLES, and IMAGES that text-only extraction silently misses (most research charts are vector and invisible to…
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
earnings-analysis
Institutional-quality earnings analysis for public equities. Parses 10-Qs, earnings releases, and call transcripts into a 4-layer framework (Parse → Compare → Diagnose → Decide), runs a mechanical scoring engine that produces a composite verdict across beat quality, operational health, and management signals, and…