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 bottleneck-huntergit 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/bottleneck-hunter)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/bottleneck-hunter"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/bottleneck-hunter/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/bottleneck-hunter"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/bottleneck-hunter.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 | $0.00041 | $0.06145 |
| Opus 5 | $0.00020 | $0.03073 |
| Sonnet 5 | $0.00008 | $0.01229 |
| Haiku 4.5 | $0.00004 | $0.00615 |
Grade A, and why
bottleneck-hunter 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 — 492 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/bottleneck-hunter.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.
供应链瓶颈猎手：AI驱动的全球产业链瓶颈套利
对 $ARGUMENTS 超级趋势执行供应链瓶颈扫描与套利机会挖掘。
核心理念
不问"AI推荐什么股票"，问"如果这个趋势继续扩张，哪一环会先不够用？"
传统投研盯龙头、盯已知赛道。这个系统反过来：从物理供应链的咽喉位置出发，找那些没人注意但一旦断货整个行业都得停下来等的公司。
超额收益来源：第一层瓶颈（GPU、HBM、电力）已被充分定价。真正的alpha在第二层、第三层——光模块、激光器、InP衬底、SOI晶圆、外延设备、晶圆级测试、IC载板、特殊玻纤等。
第一步：超级趋势确认
1.1 趋势筛选标准
不在小风口里找幻觉，只追符合以下全部条件的超级趋势：
| 标准 | 要求 | 验证方法 |
|---|---|---|
| 持续性 | 至少3-5年确定性增长 | 搜索行业预测、资本开支计划 |
| 物理性 | 需要实际硬件/材料/设备建设 | 区分"软件升级"和"物理扩建" |
| 规模性 | 全球资本开支>500亿美元/年 | 搜索头部玩家capex指引 |
| 加速性 | 需求增速>供给扩产速度 | 对比需求增长率vs产能扩张计划 |
1.2 当前跟踪的超级趋势清单
每次运行时更新，初始清单：
- AI基础设施建设 — 数据中心、GPU集群、网络互联、电力
- 能源转型 — 核电重启、电网升级、储能
- 国防现代化 — 西方军费上升周期、供应链重构
- 半导体再工业化 — 美欧日补贴建厂、设备/材料瓶颈
- 太空经济 — 卫星互联网、发射频次激增
如果用户指定了具体趋势（如"AI基础设施"），只聚焦该趋势。
1.3 趋势验证输出
趋势名称：
核心驱动力：（一句话）
已发生的验证事件（至少3个）：
1. [日期] [事件] [来源]
2.
3.
资本开支规模：全球约 $XX 亿/年，增速 YY%
供需缺口判断：需求增速 > 供给扩产速度？是/否/不确定
趋势确认：✅ 可追踪 / ❌ 证据不足，暂不追踪
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 · 492 lines · 41 tokens per session scan A 84435e484856
bottleneck-hunter is a skill published in the GitHub repository xbtlin/ai-berkshire (16,273 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 6,145 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.