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 deep-company-seriesgit 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/deep-company-series)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/deep-company-series"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/deep-company-series/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/deep-company-series"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/deep-company-series.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- 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 | $0.00038 | $0.04890 |
| Opus 5 | $0.00019 | $0.02445 |
| Sonnet 5 | $0.00008 | $0.00978 |
| Haiku 4.5 | $0.00004 | $0.00489 |
Grade A, and why
deep-company-series 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 13d 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 — 261 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/deep-company-series.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.
看懂XX公司（深度公司系列）：3-8 篇长文拆一家公司
为 $ARGUMENTS 撰写一个《看懂XX》深度长文系列（3-8 篇，按公司复杂度定，见"篇数适配"），发布在公众号/视频号等公开渠道。核心 IP 不是"会写"，而是"会改"——99% 的财经文章在违反本 skill 的事实核查标准。
参考样本：reports/腾讯/《看懂腾讯》/
一、触发场景
用户希望为一家公司做"教科书级别"的深度研究，并以系列长文形式公开发布。区别于一篇研报：
- 3-8 篇（复杂公司 8 篇约 12 万字，简单公司 3 篇约 3 万字），从认知重置到决策框架完整闭环
- 每篇独立成文（适合单篇分享），但贯穿一套估值/管理层/价格判断
- 写给"愿意花 90 分钟读懂一家公司"的读者，不是写给券商客户
不适合用本 skill 的场景：单篇研报、季报点评、行业研究——那些用 /investment-research、/earnings-review、/industry-research。
二、系列篇目模板
篇数适配公司复杂度（先定篇数，再定篇目）
篇数不固定为 8。 8 篇是腾讯这种"多业务 + 万亿投资组合 + 20 年管理层故事"的公司才撑得起的容量。写之前先问：这家公司有几个能用"一个尖锐问题"独立成文的主轴？有几个写几篇。
| 复杂度 | 特征 | 篇数 | 例子 |
|---|---|---|---|
| 高 | 多条业务线各自成生意 + 隐藏资产/投资组合 + 管理层史料丰富 | 7-8 篇 | 腾讯 |
| 中 | 2-3 条业务线 + 一个重大时代变量 | 4-6 篇 | — |
| 低 | 主业清晰、核心问题少而集中 | 3 篇 | 快手 |
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.
- 13d ago First seen · 261 lines · 38 tokens per session scan A e98f1c19023f
deep-company-series is a skill published in the GitHub repository xbtlin/ai-berkshire (16,289 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 4,890 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
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
build-ui-components-and-systems
A guide for building reusable UI components and design systems: shared visual rules, component interfaces, behavior, accessibility requirements, documentation, packaging, and version management. A design system is a maintained set of parts and rules that multiple screens or products can share.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…