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 thesis-trackergit 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/thesis-tracker)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/thesis-tracker"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/thesis-tracker/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/thesis-tracker"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/thesis-tracker.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 | $0.00030 | $0.02686 |
| Opus 5 | $0.00015 | $0.01343 |
| Sonnet 5 | $0.00006 | $0.00537 |
| Haiku 4.5 | $0.00003 | $0.00269 |
Grade A, and why
thesis-tracker 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 — 226 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/thesis-tracker.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.
投资论文追踪：买入后的纪律系统
对 $ARGUMENTS 执行投资论文追踪检查。
支持输入格式：
公司名— 首次使用时建立投资论文，后续使用时追踪检查公司名 建立论文— 强制重新建立投资论文公司名 季度检查— 基于最新财报进行论文检查
"买入只是开始。真正的工作是持有期间的持续跟踪。" —— 李录
"当事实改变时，我就改变想法。你呢？" —— 凯恩斯
设计理念
大多数投资者的流程是：研究 → 买入 → 祈祷。缺少买入后的系统化跟踪，导致：
- 该卖的时候舍不得卖（"再等等，会涨回来的"）
- 不该卖的时候恐慌卖出（"跌了20%，是不是我错了"）
- 忘记了当初为什么买的（"我买这个是因为什么来着？"）
巴菲特和李录的做法是：买入前就写下卖出条件。然后每个季度检查论文是否完整。
执行流程
第一步：判断操作模式
检查是否已存在该公司的投资论文文件（reports/{公司名}-thesis.md）：
- 如果不存在 → 进入建立论文模式
- 如果存在 → 进入追踪检查模式
- 如果找不到但用户表示已有 → 询问文件路径
模式A：建立投资论文
A0：数据收集
使用 WebSearch 获取当前股价、估值指标（PE/PB/股息率）、最新财报核心数据，用于填写估值锚点。如果已有该公司的 /investment-research 或 /investment-team 报告，优先从中读取。
使用 tools/financial_rigor.py verify-valuation 校验估值数据。
A1：核心论文（必须用200字以内写清楚）
投资论文必须回答以下5个问题，每个问题一句话：
我以 ___元 买入 ___公司，因为：
1. 这门生意的本质是___，我理解它的赚钱方式
2. 它的护城河是___，而且在变宽/稳定
3. 管理层___，值得信赖的原因是___
4. 当前价格相当于内在价值的___折，安全边际来自___
5. 即使我错了，下行风险可控，因为___
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 · 226 lines · 30 tokens per session scan A 08b70c839788
thesis-tracker is a skill published in the GitHub repository xbtlin/ai-berkshire (16,273 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 2,686 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.