AI Berkshire is a collection of Claude Code and Codex skills that structures investment research around the methods of four value-investing thinkers and uses multiple agents for adversarial analysis. It is intended for investors who want a disciplined process for researching companies and making valuation-based decisions.
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 xbtlin/ai-berkshire --skill management-deep-divegit clone --depth 1 https://github.com/xbtlin/ai-berkshireWrote 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/xbtlin/ai-berkshire/management-deep-dive)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/management-deep-dive"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/management-deep-dive/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/xbtlin/ai-berkshire/management-deep-dive"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/management-deep-dive.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 | $0.00034 | $0.03399 |
| Opus 5 | $0.00017 | $0.01699 |
| Sonnet 5 | $0.00007 | $0.00680 |
| Haiku 4.5 | $0.00003 | $0.00340 |
Grade A, and why
management-deep-dive 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 12d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex adapter note
This skill is generated from skills/management-deep-dive.md so Claude Code and Codex users share one canonical workflow.
- Treat
$ARGUMENTSas the user's request in the current Codex thread. - When the source mentions Claude-only surfaces such as Task, Agent, WebSearch, Bash, Read, or Write, use the closest Codex capability available in this session: subagents when available, web search when needed, shell commands for local tools, and normal file edits for workspace files.
- Use shared project tools from
tools/in this repository. Prefer running commands from the repository root with paths likepython3 tools/financial_rigor.py ...; if the current thread starts outside the repo, locate the actual checkout path first instead of assuming a fixed home-directory path. - Before starting research, run the
datecommand to confirm today's date; treat it as the baseline for "latest" data and state the data cutoff date in the report header. Never assume the current date from training data. - Preserve the research quality rules from
AGENTS.md: cross-check financial data, use exact arithmetic tools for valuation/math, and clearly label uncertainty and source gaps.
管理层纵深研究：买股票就是买人
对 $ARGUMENTS 进行管理层深度研究。
支持输入格式：公司名 或 人名 公司名，例如：美团、王兴 美团、黄仁勋 英伟达
"买股票就是买人。找到你信任的人，然后长期持有。" —— 段永平
"评估管理层，要看他们在没人看着的时候做什么。" —— 巴菲特
设计理念
大多数投资分析对管理层的评估停留在表面：履历、持股比例、薪酬。但巴菲特花大量时间和管理层吃饭聊天，李录说他投资的本质是投人，段永平说买股票就是买人。
本Skill是 /investment-research 第五步管理层评估的深化版。当标准投资研究中管理层评分不确定（★★★或以下）、或管理层是核心投资逻辑时，使用本Skill做纵深研究。
AI无法和管理层吃饭，但可以通过公开信息做到：
- 追踪管理层的话与做是否一致（承诺vs兑现）
- 分析每一笔重大资本配置决策的回报
- 从困难时期的决策中推断品格
- 通过员工/商家/客户的反馈侧面验证
执行流程
第一步：识别关键管理层并启动并行数据收集
使用 WebSearch 确认以下关键人物：
| 角色 | 姓名 | 任期 | 背景 | 持股/期权 |
|---|---|---|---|---|
| CEO/董事长 | ||||
| CFO | ||||
| 创始人（如不在位） | ||||
| 实际控制人（如不同于CEO） | ||||
| 其他关键高管 |
注意：区分"谁在做决策"和"谁的名字在头衔上"。有些公司创始人虽然卸任但仍是灵魂人物（如黄峥之于拼多多）。
确认关键人物后，使用 Task 工具启动多个后台 Agent 并行收集以下数据：
- Agent 1：CEO公开发言与预测记录（股东信、电话会、采访、社交媒体）
- Agent 2：资本配置决策记录（并购、回购、分红、新业务投资）
- Agent 3：治理结构与薪酬（股权结构、关联交易、高管薪酬）
- Agent 4：侧面验证信息（员工评价、客户反馈、行业口碑）
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.
- 12d ago First seen · 298 lines · 34 tokens per session scan A 77cd31f1fa81
management-deep-dive is a skill published in the GitHub repository xbtlin/ai-berkshire (16,273 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 3,399 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
hyperliquid
Hyperliquid market data, account history, trade review.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
omni-budget
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
polymarket
Query Polymarket: markets, prices, orderbooks, history.