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.
Borrowing it
Nothing to install: this file belongs to xbtlin/ai-berkshire. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xbtlin/ai-berkshire/main/CLAUDE.mdgit 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/instructions/xbtlin/ai-berkshire/claude-md)<a href="https://agentmods.dev/instructions/xbtlin/ai-berkshire/claude-md"><img src="https://agentmods.dev/badge/instructions/xbtlin/ai-berkshire/claude-md/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/instructions/xbtlin/ai-berkshire/claude-md"><img src="https://agentmods.dev/badge/instructions/xbtlin/ai-berkshire/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01799 | $0.01799 |
| Opus 5 | $0.00899 | $0.00899 |
| Sonnet 5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
ai-berkshire CLAUDE.md 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 3d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Berkshire — 项目指令
项目概述
基于 Claude Code 的价值投资研究 Skill 合集。四大师框架：巴菲特、芒格、段永平、李录。 GitHub: xbtlin/ai-berkshire
项目结构
skills/ — 投研 Skill 定义（.md），复制到 ~/.claude/commands/ 使用
tools/ — 辅助工具（financial_rigor.py 精确计算、twstock_data.py 台股FinMind取数）
reports/ — 投资研究报告输出
assets/ — 图片等静态资源
报告目录结构
所有报告按公司名建文件夹，公司相关的所有报告放在对应文件夹内：
reports/
├── AI产业研究/ — AI产业链全景研究（置顶）
│ ├── AI五层蛋糕-产业全景研究-20260605.md
│ └── AI五层蛋糕-公众号-20260605.md
├── 腾讯/ — 腾讯所有研究报告
│ ├── 腾讯-research-20260408.md
│ ├── 腾讯-earnings-2025Q4.md
│ ├── 腾讯-management-20260409.md
│ └── 腾讯-thesis.md
├── 拼多多/ — 拼多多所有研究报告
├── 泡泡玛特/ — 泡泡玛特所有研究报告
├── 核电-industry-20260409.md — 行业报告放根目录
├── AI算力-funnel-20260509.md — 漏斗筛选报告放根目录
├── AI-轮动判断-20260509.md — 主题级综合判断报告放根目录
├── portfolio-latest.md — 组合报告放根目录
└── 多公司对比-checklist-20260408.md — 多公司报告放根目录
报告命名规范
| Skill | 文件命名格式 | 示例 |
|---|---|---|
| /investment-team | {公司名}/ 目录内含4个视角+最终报告 |
reports/拼多多/最终报告.md |
| /investment-research | {公司名}-research-{YYYYMMDD}.md |
reports/腾讯/腾讯-research-20260408.md |
| /investment-checklist | {公司名}-checklist-{YYYYMMDD}.md |
reports/腾讯/腾讯-checklist-20260408.md |
| /industry-research | {行业名}-industry-{YYYYMMDD}.md（根目录） |
reports/核电-industry-20260409.md |
| /industry-funnel | {行业名}-funnel-{YYYYMMDD}.md（根目录） |
reports/AI算力-funnel-20260509.md |
| /private-company-research | {公司名}-private-{YYYYMMDD}.md |
reports/字节跳动/字节跳动-private-20260408.md |
| /earnings-review | {公司名}-earnings-{期间}.md |
reports/腾讯/腾讯-earnings-2025Q4.md |
| /earnings-team | {公司名}/ 目录内含4个大师视角+研究底稿+公众号文章+读者评审 |
reports/腾讯/腾讯-earnings-2025Q4.md（公众号定稿） |
| /thesis-tracker | {公司名}-thesis.md（长期维护） |
reports/腾讯/腾讯-thesis.md |
| /portfolio-review | portfolio-latest.md（根目录，持续更新） |
reports/portfolio-latest.md |
| /management-deep-dive | {公司名}-management-{YYYYMMDD}.md |
reports/腾讯/腾讯-management-20260409.md |
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.
- 3d ago Changed · +11 lines · +199 tokens per session 197d07f02360
- 10d ago First seen · 113 lines · 1,600 tokens per session scan A caf69557c004
ai-berkshire CLAUDE.md is an instructions file published in the GitHub repository xbtlin/ai-berkshire (16,258 stars, last pushed 2d ago), licensed MIT. It adds 1,799 tokens to every session, about $0.0090 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.