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 Travisun/Opptrix --skill lean-black-littermangit clone --depth 1 https://github.com/Travisun/OpptrixWrote 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/travisun/opptrix/lean-black-litterman)<a href="https://agentmods.dev/skills/travisun/opptrix/lean-black-litterman"><img src="https://agentmods.dev/badge/skills/travisun/opptrix/lean-black-litterman.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.01451 |
| Opus 5 | $0.00041 | $0.00726 |
| Sonnet 5 | $0.00016 | $0.00290 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
lean-black-litterman 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 5d 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
LEAN 黑利特曼
方法溯源 QuantConnect LEAN 社区算法/示例思路；本技能是平台工具编排的投研工作流，禁止假装跑完整 LEAN 引擎或输出 LEAN 回测曲线、订单日志冒充引擎结果。实际取数与计算仅限 Opptrix 工具（行情/财务/opptrix_run 沙盒等）。
能力声明（assumption-only）：无机构级先验/协方差服务；均衡收益、风险厌恶、观点矩阵与 τ 等须 ask_user 或显式假设。输出为教育/示意，禁止假装已跑卖方 BL 引擎或 LEAN 优化内核。完整度：assumption-only。
何时使用
用户要在 A股/场内 ETF 上用 Black-Litterman 把「均衡先验 + 主观观点」合成为后验预期收益/权重示意（LEAN 方法溯源，非美股原版照搬）。默认交付可预览网页。
边界：组合复盘用 @skill:portfolio-review；风险平价用 @skill:lean-risk-parity；均值方差用 @skill:lean-mean-variance。本技能不提供机构级协方差估计服务，完整度 assumption-only。
A股适配（默认）
- 默认市场 CN（A股 / 场内 ETF）。用户点名美股/港股再切换，并声明数据口径与微观结构差异。
- 默认先验/观点落在 CN 行业或宽基 ETF；观点来自用户或可得研究，标 assumption-only。
- 后验权重默认多头；融券受限禁止负权重自由做空。
- 不可硬适配或数据缺口时：首页横幅写清完整度（assumption-only 或更严）+ 必要时
ask_user。
分析架构（投研方法）
- 问题/假设：在显式观点与不确定度下，后验权重如何相对先验移动？
- 证据清单：资产清单、用户观点、（可选）历史收益协方差沙盒估计
- 多维交叉验证：观点强度 τ/Ω 敏感；有无观点时权重对比
- 结论与不确定：示意≠可执行优化器输出
- 微观/制度风险：涨跌停钝化、T+1、ST/停牌、融券受限（及相关会计口径差异）；不得按美股连续可成交或自由做空假设叙事
- 事实 | 假设 | 推断 分栏强制
数据维度
| 维度 | 取数方向 | 缺失时 |
|---|---|---|
| 资产与基准 | ask_user / 组合持仓 / portfolio_summary / 搜索 |
先确认 |
| 观点 P/Q/Ω | ask_user（必须） |
禁止静默编造「市场共识观点」 |
| 协方差示意 | opptrix_run（历史收益） |
用对角简化并标假设 |
| 交付 | list_web_vendor → create_web |
可跳过口头要点 |
| A股观点/先验 | CN 行业/ETF + 用户观点 | 无观点 → ask_user；assumption-only |
步骤
- 确认默认 CN：标的/宇宙为 A股或场内 ETF（用户点名其他市场再切换并声明差异）。应用涨跌停/T+1/融券受限等微观约束（见 A股适配）。
- 能力横幅：assumption-only；非 LEAN/卖方引擎
- 收集资产与观点：强度与置信必须显式
- 先验与后验示意：沙盒计算；敏感度表
- 分栏结论：禁止仓位建议措辞
- 交付网页（默认）：
create_web
网页报告建议目录
- 范围：默认 A股/场内 ETF + LEAN 溯源；assumption-only
- 资产、先验与观点表
- 后验预期/权重示意
- 敏感性（τ / 观点强度）
- 事实 / 假设 / 推断分栏
- 局限与不可执行声明
- A股适配与限制（默认 CN；微观结构/代理/完整度）
- 免责声明（无仓位建议）
禁止
- 荐股、目标价、仓位建议；编造未返回数字
- 假装卖方共识观点或机构 BL 引擎结果
- 把示意权重写成下单清单
- 禁止假装跑完整 LEAN 引擎或伪造 LEAN 日志/回测净值
- 禁止无交付就结束（默认须有 web 产物，除非用户明确只要口头要点）
- 禁止把美股成分/ETF 清单不经映射直接当 A股结果
- 禁止假设可自由融券做空
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.
- 5d ago First seen · 85 lines · 81 tokens per session scan A eb909c694460
lean-black-litterman is a skill published in the GitHub repository Travisun/Opptrix (230 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 1,451 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
national-team-position
A Chinese-language analysis tool that estimates changes in China’s government-backed ETF holdings by tracking ETF share counts and related index prices. ETFs are funds traded on stock exchanges, and the “national team” refers here to Central Huijin, a state investment company.
caijing-ipo-hk
A Chinese-language adviser for Hong Kong stock initial public offerings, or IPOs—the first sale of a company's shares to the public. It covers how to apply, how much to apply for, and risks such as the share price falling below the offering price.
caijing-fundamental
A finance research skill for writing a detailed, forward-looking analysis of a listed company’s business, financials, valuation, risks, and investment arguments. It covers companies listed in mainland China and Hong Kong.
rodya-caijing-studio
A toolkit for researching Chinese A-share and Hong Kong-listed companies and producing financial content. It includes separate workflows for company fundamentals, earnings, valuation, risks, industries, and IPO checks.
caijing-earnings
A finance research skill for reviewing listed companies’ earnings reports, or preparing for an upcoming report. It focuses on Chinese A- and Hong Kong-listed companies.
caijing-valuation
A Chinese-language adviser that assesses whether a stock's current valuation looks high or low. It adapts the comparison to the industry and examines historical and peer-company valuation ranges.