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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xbtlin/ai-berkshirenpx agentmods add skills/xbtlin/ai-berkshire/industry-researchWrote 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/industry-research)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/industry-research"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/industry-research/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/industry-research"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/industry-research.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 | $0.00036 | $0.03097 |
| Opus 5 | $0.00018 | $0.01548 |
| Sonnet 5 | $0.00007 | $0.00619 |
| Haiku 4.5 | $0.00004 | $0.00310 |
Grade A, and why
industry-research 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 — 284 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/industry-research.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.
行业投资研究：产业链全景扫描 + 四大师个股分析框架
对 $ARGUMENTS 行业进行系统化产业链投资研究。
研究目标
从一个投资主题/逻辑链出发，完成：
- 验证投资逻辑链的每一个环节
- 绘制完整产业链全景图
- 扫描全球所有上市公司（A股/港股/美股/国际）
- 对每个细分环节的头部公司执行四大师框架分析
- 输出行业级投资组合配置建议
第一步：投资逻辑链构建与验证
1.1 画出逻辑链
用箭头链路表达从"底层趋势"到"受益标的"的因果关系，例如：
底层趋势 A
→ 导致需求 B
→ 创造瓶颈/刚需 C
→ 受益产业链 D
1.2 逐环节验证
对逻辑链的每个箭头提出质疑并寻找证据：
| 环节 | 核心假设 | 验证方式 | 数据来源 |
|---|---|---|---|
| A→B | 搜索行业数据/预测 | ||
| B→C | 搜索供需分析 | ||
| C→D | 搜索实际案例/签约 |
1.3 寻找"已发生的验证事件"
列出支撑该逻辑链的已签约/已落地的真实商业事件（而非预测），例如大公司的采购协议、政策文件、行业报告等。
第二步：产业链全景图绘制
2.1 绘制产业链结构
将行业拆解为上游→中游→下游→辅助环节，例如：
上游：原材料/资源开采 → 材料加工/提纯
中游：核心设备制造 → 系统集成/工程建设 → 新技术研发
下游：运营/服务 → 终端客户
辅助：检测/认证 → 维护服务 → 金融工具（ETF/信托）
2.2 识别每个环节的"生意特征"
对每个环节标注：
| 环节 | 商业模式 | 毛利率区间 | 竞争格局 | 壁垒类型 | 周期性 |
|---|---|---|---|---|---|
| 卖资源/卖设备/卖服务/收租 | 垄断/寡头/充分竞争 | 资源/牌照/技术/规模 | 强/中/弱 |
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 · 284 lines · 36 tokens per session scan A 39bca0b2dc0f
industry-research is a skill published in the GitHub repository xbtlin/ai-berkshire (16,289 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 3,097 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.