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 investment-teamgit 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/investment-team)<a href="https://agentmods.dev/skills/travisun/opptrix/investment-team"><img src="https://agentmods.dev/badge/skills/travisun/opptrix/investment-team/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/travisun/opptrix/investment-team"><img src="https://agentmods.dev/badge/skills/travisun/opptrix/investment-team.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00090 | $0.01673 |
| Opus 5 | $0.00045 | $0.00837 |
| Sonnet 5 | $0.00018 | $0.00335 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
investment-team 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 6d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
四角色并行投研团队
对用户指定标的做真正并行的四大师投研，再由 Team Lead（父 Agent）综合。署名：Opptrix · AI Berkshire 分析。
何时使用 / 边界
| 使用 | 不要用本技能 |
|---|---|
| 需要四角色独立成稿再交叉验证 | 单人七模块深度研究 → @skill:investment-research |
| 重要标的首次/重大重做，愿付并行成本 | 多空辩论研讨团 → @skill:multi-role-research-council（勿合并） |
未上市六侦察 → @skill:private-company-research |
|
财报专属团队 → @skill:earnings-team |
研究质量（硬性）
同契约：四大师、强制结论档位、镜子测试、A/B/C、快速否决、事实/观点分栏、get_current_time、禁止训练知识冒充联网结果。
并行纪律：禁止「一个 prompt 切四段」冒充对抗；四角色必须各自 run_subagent 独立取证成稿。
团队结构
| 角色 | 视角 | 职责 |
|---|---|---|
| Team Lead（父） | 综合 | 统筹、交叉验证、scorecard、定稿、create_web |
| business-analyst | 段永平 | 生意本质、护城河、用户价值 |
| financial-analyst | 巴菲特 | 财务质量、估值、安全边际（须跑 rigor） |
| industry-researcher | 芒格 | 行业格局、竞争、失败路径 |
| risk-assessor | 李录 | 风险、管理层、长期确定性 |
详细 brief：get_agent_skill_file(..., path="references/role-briefs.md")。
取数
与 @skill:investment-research 相同工具栈。财务角色须 workspace_write 后 opptrix_run：
python scripts/run_rigor_json.py --input data.json --output result.json
python scripts/scorecard.py --input evidence.json --output scorecard.json
脚本不联网。第二源由 Agent 用公告/资讯/http_fetch 写入后再 cross-validate。
并行编排（对齐 multi-role-research-council）
S0 — 范围与预检
- 确认标的；多候选
ask_user。get_current_time。评定 A/B/C，写入 checklist。 update_research_checklist加载references/checklist.json。- 取数可达性预检：父 Agent 先试一次
get_instrument_snapshot（或等价工具）。若失败 → 停止启动子 Agent，醒目标注并询问用户是否继续（继续则整份报告顶栏标注降级，data_mode=proxy/insufficient）。后台子任务无法向用户弹权限确认时，父必须先保证工具可用。
S1 — 四角色并行（硬性）
在同一轮对四角色各调用一次 run_subagent（可 background）：
role/instructions：按role-briefs.md；注入标的、A/B/C、数据截止。- 子 Agent 自行取数；父不代写结论数字。
- 联网/取数失败禁止伪装：子报告顶部必须醒目标注「未能刷新数据，置信度降级」，并如实告知 Team Lead；Lead 可中止研究。
四路终态后：get_subagent 收结果 → 立即 reclaim_subagent → checklist 勾选。禁止堆积未回收会话；子 Agent 禁止再 run_subagent。
S2 — 交叉验证与综合
- 比对四稿关键数字冲突；财务稿须含 rigor 输出摘要。
- 找共识与矛盾（矛盾优先分析）。
- 镜子测试 + 快速否决；
scorecard.py输出档位。 - 强制结论：通过 / 有条件通过 / 不通过 / 灰色地带。
What ships with it
10 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.
- references/checklist.json 648 B
- references/role-briefs.md 1.2 KB
- scripts/financial_rigor.py 20 KB runs code
- scripts/fixtures/sample_cross_validate_full.json 534 B
- scripts/fixtures/sample_scorecard_full.json 605 B
- scripts/fixtures/sample_scorecard_insufficient.json 148 B
- scripts/fixtures/sample_verify_market_cap.json 309 B
- scripts/report_audit.py 22 KB runs code
- scripts/run_rigor_json.py 13 KB runs code
- scripts/scorecard.py 7.8 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.
- 6d ago First seen · 118 lines · 90 tokens per session scan A 3cbeb44a4aae
investment-team is a skill published in the GitHub repository Travisun/Opptrix (231 stars, last pushed 3d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,673 once invoked, about $0.0005 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-industry
A finance research skill for mapping an industry or investment theme from its drivers through its suppliers, customers, and representative companies. It is about the wider sector, not ranking individual stocks.