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.
Borrowing it
Nothing to install: this file belongs to xbtlin/ai-berkshire. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xbtlin/ai-berkshire/main/AGENTS.mdgit 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/instructions/xbtlin/ai-berkshire/agents-md)<a href="https://agentmods.dev/instructions/xbtlin/ai-berkshire/agents-md"><img src="https://agentmods.dev/badge/instructions/xbtlin/ai-berkshire/agents-md/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/instructions/xbtlin/ai-berkshire/agents-md"><img src="https://agentmods.dev/badge/instructions/xbtlin/ai-berkshire/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00791 | $0.00791 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
ai-berkshire AGENTS.md 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Berkshire Codex Guide
This repository contains investment research workflows, reports, and shared validation tools. Keep compatibility with both Claude Code and Codex users.
Project Layout
skills/*.md: Claude Code slash-command source files.codex-skills/*/SKILL.md: Codex skill packages. Most are generated fromskills/*.md; Codex-only hand-written packages are allowed when clearly marked and no same-namedskills/*.mdsource exists.codex-prompts/*.md: generated Codex custom prompts for slash-command style entry points. These are a compatibility layer; skills remain preferred.tools/*.py: shared financial validation and data tools used by both systems.reports/: research outputs. Do not rewrite unrelated reports while changing tooling or skills.scripts/sync-codex-skills.py: regenerates Codex skills fromskills/*.md.scripts/install-codex-skills.sh/scripts/install-codex-skills.bat: installs Codex skills locally.scripts/install-codex-prompts.sh/scripts/install-codex-prompts.bat: installs generated Codex slash prompts locally.scripts/install-claude-commands.sh/scripts/install-claude-commands.bat: installs Claude Code commands locally.
Compatibility Rules
- Treat
skills/*.mdas the canonical workflow source. - After changing any file in
skills/, run:python3 scripts/sync-codex-skills.py - If slash prompt compatibility is needed, also run:
python3 scripts/sync-codex-prompts.py - Do not manually edit generated
codex-skills/*/SKILL.mdunless also updating the corresponding source inskills/. - For Codex-only hand-written packages under
codex-skills/, keep them clearly marked as Codex-only and do not create a same-namedskills/*.mdfile unless intentionally adopting the workflow for Claude Code too. - Keep tool paths compatible with the documented checkout path:
~/ai-berkshire/tools/... - Keep
CLAUDE.mdfor Claude Code behavior and thisAGENTS.mdfor Codex behavior.
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.
- 9d ago First seen · 70 lines · 791 tokens per session scan A d3d75821ad83
ai-berkshire AGENTS.md is an instructions file published in the GitHub repository xbtlin/ai-berkshire (16,258 stars, last pushed yesterday), licensed MIT. It adds 791 tokens to every session, about $0.0040 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.