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 news-pulsegit 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/news-pulse)<a href="https://agentmods.dev/skills/xbtlin/ai-berkshire/news-pulse"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/news-pulse/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/news-pulse"><img src="https://agentmods.dev/badge/skills/xbtlin/ai-berkshire/news-pulse.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 | $0.00066 | $0.03948 |
| Opus 5 | $0.00033 | $0.01974 |
| Sonnet 5 | $0.00013 | $0.00790 |
| Haiku 4.5 | $0.00007 | $0.00395 |
Grade A, and why
news-pulse 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 — 245 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/news-pulse.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.
公司新闻脉搏：股价异动快速归因团队
对 $ARGUMENTS 进行最近新闻侦察与异动归因。这不是深度投研，是情报快速响应——目标是 10 分钟内回答："这家公司最近发生了什么？股价异动的真因是什么？要不要重审投资论文？"
适用场景
- 持仓/关注股票股价大涨/大跌（一般触发线：单日 ±5%、一周 ±10%）
- 财报后股价异动，想快速搞清市场在反应什么
- 看到新闻标题，但不确定是噪音还是真信号
- 不适用：完整投研（用
/investment-team）、财报深读（用/earnings-review）、长期论文跟踪（用/thesis-tracker）
执行流程
第一步：确认参数与场景
向用户澄清以下信息（如未在 $ARGUMENTS 中提供）：
| 参数 | 说明 | 默认 |
|---|---|---|
| 公司名 | 中文/英文/股票代码均可 | 必填 |
| 时间窗口 | 侦察新闻的回溯天数 | 默认 14 天，财报季可缩到 7 天 |
| 股价异动 | 涨/跌幅度 + 时间，如"跌 12%/3 天" | 选填，有则用于聚焦归因 |
| 关注侧重 | 公司事件 / 监管 / 行业 / 情绪 | 默认四方平均 |
如果用户只说了公司名，先反问："最近多少天的新闻？有具体的股价异动要解释吗？"——不要默默假设。
第二步：信息可得性分级
参考 investment-team.md 的 A/B/C 评级，但维度不同：
| 等级 | 特征 | 侦察策略 |
|---|---|---|
| A 级（信息充裕） | 大盘股、媒体覆盖广、财报季 | 重点是降噪和归因——信息太多反而难找真因，每个 Agent 要有判断力，过滤掉"重复转述"的二手新闻 |
| B 级（信息适中） | 中小盘、覆盖一般 | 标准模式，每条关键事件附 1-2 个独立信源 |
| C 级（信息稀缺） | 港股小票、新上市、冷门 | 转入"扫盲模式"——可能找不到任何能解释异动的新闻，这个结论本身就有价值（可能是技术性/资金面而非基本面） |
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 · 245 lines · 66 tokens per session scan A 53d8c0301d5d
news-pulse is a skill published in the GitHub repository xbtlin/ai-berkshire (16,289 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 3,948 once invoked, about $0.0003 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.