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 quality-screengit 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/quality-screen)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/quality-screen"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/quality-screen/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/quality-screen"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/quality-screen.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 | $0.00032 | $0.02486 |
| Opus 5 | $0.00016 | $0.01243 |
| Sonnet 5 | $0.00006 | $0.00497 |
| Haiku 4.5 | $0.00003 | $0.00249 |
Grade A, and why
quality-screen 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 11d 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 — 184 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/quality-screen.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.
去劣筛选：7条指标快速排除非一流公司
对 $ARGUMENTS 执行去劣指标筛选，快速排除不符合一流公司标准的标的。
支持输入格式：
| 输入方式 | 示例 | 说明 |
|---|---|---|
| 个股 | 腾讯, 美团, 英伟达 |
逐家筛选 |
| 行业 | 中国啤酒行业 全球云计算 港股运动品牌 |
先搜索该行业主要上市公司（10-20家），再逐家筛选 |
| 市场/指数 | 恒生指数成分股 沪深300 纳斯达克100 |
拉取成分股列表，逐家筛选 |
| 主题 | 中国高股息50强 全球AI算力链 |
先搜索主题相关公司，再逐家筛选 |
行业/市场/主题模式下，输出额外包含：通过率统计、行业内排名、板块对比总结。
设计原则
- 目标：不错杀任何一流好公司，但能排除确定的非一流公司
- 逻辑：7条硬指标 + 2条豁免规则，宁可漏网不可误杀
- 适用范围：所有上市公司（银行/保险不适用第3条利息覆盖倍数）
7条去劣指标
| # | 指标 | 排除条件 | 衡量的是什么 |
|---|---|---|---|
| 1 | 10年平均ROE | < 8% | 资本效率——股东的钱能不能跑赢机会成本 |
| 2 | 5年累计自由现金流 | 为负 | 真金白银——利润是不是"纸面富贵" |
| 3 | 利息覆盖倍数（EBIT/利息） | < 2倍 | 偿债安全——还利息的能力 |
| 4 | 长期毛利率 | < 15% | 定价权——产品/服务有没有差异化 |
| 5 | 经营现金流 / 净利润（5年均值） | < 0.7 | 利润质量——赚到的利润能不能收回现金 |
| 6 | 长期净利率 | < 5% | 抗风险能力——收入波动时利润是否归零 |
| 7 | 5年总股本膨胀 | > 20%（非并购原因） | 股东利益——管理层是否在稀释你的权益 |
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.
- 11d ago First seen · 184 lines · 32 tokens per session scan A ea302e077cbf
quality-screen is a skill published in the GitHub repository xbtlin/ai-berkshire (16,273 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 2,486 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.