alphagbm-buffett-analysis

alphagbm-buffett-analysis is a skill for Claude Code, Codex from AlphaGBM/skills. It costs 180 tokens per session (1,724 once invoked), scanned A, original, MIT.

A stock scorecard based on four Warren Buffett-style questions: business quality, durable advantage, management, and valuation.

In plain words
What is it for?
It helps assess a ticker using company fundamentals, profitability, dividends, valuation measures, and comparison with the 10-year Treasury yield.
Why use it?
It turns several financial checks into a single weighted view that indicates whether a stock may be worth holding, watching, or avoiding.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit It helps assess a ticker using company fundamentals, profitability, dividends, valuation measures, and comparison with the 10-year Treasury yield.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alphagbm/skills/alphagbm-buffett-analysis
About the project

AlphaGBM Skills is a collection of AI-agent skills for researching options and other financial markets with sourced market data, including measures such as implied volatility, Greeks, skew, and trading flow. Traders use it with coding agents such as Claude Code, Cursor, and Windsurf to analyze instruments and research ideas using the project's data and scoring methods. The catalogue entries are the skills that bring these capabilities into agent workflows.

AlphaGBM/skills · 2,240 stars · on GitHub · alphagbm.com

Install

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.

Any agent
npx skills add AlphaGBM/skills --skill alphagbm-buffett-analysis
Clone the repo
git clone --depth 1 https://github.com/AlphaGBM/skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for alphagbm-buffett-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphagbm/skills/alphagbm-buffett-analysis/github.svg)](https://agentmods.dev/skills/alphagbm/skills/alphagbm-buffett-analysis)
Your own site
<a href="https://agentmods.dev/skills/alphagbm/skills/alphagbm-buffett-analysis"><img src="https://agentmods.dev/badge/skills/alphagbm/skills/alphagbm-buffett-analysis/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.

agentmods 80×15 button for alphagbm-buffett-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/alphagbm/skills/alphagbm-buffett-analysis"><img src="https://agentmods.dev/badge/skills/alphagbm/skills/alphagbm-buffett-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00180 $0.01724
Opus 5 $0.00090 $0.00862
Sonnet 5 $0.00036 $0.00345
Haiku 4.5 $0.00018 $0.00172

Measured 9d ago against content hash f2ace7af2911, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

alphagbm-buffett-analysis 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/alphagbm-buffett-analysis/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlphaGBM Buffett Analysis

The 4 lenses Buffett himself says he applies, computed from yfinance fundamentals and returned as a single-number verdict plus reasoning for each lens.

The 4 Lenses

  1. Business (20% weight) — circle of competence. Simple sectors (consumer staples, utilities, industrials) score high. Complex sectors (tech, healthcare, financials) score lower unless mega-cap like AAPL.
  2. Moat (30% weight) — durable advantage. Gross margin > 40%, ROE > 20%, profit margin > 15%, and market cap > $100B each contribute to the moat score.
  3. Management (15% weight) — capital allocation proxy via dividend continuity
    • payout ratio (15-60% is ideal balance) + 5yr avg div yield.
  4. Valuation (35% weight) — fair price check. PE < 15 → +20, PEG < 1 → +15, FCF yield > 10Y treasury + 2pp → +20. PE > 40 or PEG > 2.5 → deductions.

Overall Verdict

  • ≥ 75 → HOLDABLE (color green) — meets Buffett standards, long-term hold
  • 55-74 → WATCHABLE (color amber) — wait for better price or clearer evidence
  • < 55 → AVOID (color red) — fails Buffett's standards

Why This Is a Separate Skill

The generic alphagbm-stock-analysis runs a G=B+M style/momentum score. Buffett's framework is different — it weights moat + valuation much more heavily than momentum, and penalizes complex businesses regardless of growth. This skill codifies Buffett's rules, not AlphaGBM's house rules.

How to Use

Input:

  • ticker (required) — US stock symbol

Output:

  • scorecard.business: {score, sector, industry, verdict_zh, verdict_en}
  • scorecard.moat: {score, gross_margin, roe, profit_margin, market_cap_b, reasons_zh, reasons_en}
  • scorecard.management: {score, dividend_rate, payout_ratio, reasons_zh, reasons_en}
  • scorecard.valuation: {score, pe, forward_pe, peg, pb, fcf_yield_pct, ten_year_treasury, reasons_zh, reasons_en}
  • scorecard.overall: {score, verdict, verdict_zh, verdict_en, color}

Example Queries

Read the full file on GitHub · 152 lines

Changes

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.

  1. 9d ago First seen · 152 lines · 180 tokens per session scan A f2ace7af2911

Subscribe to this mod's changes

alphagbm-buffett-analysis is a skill published in the GitHub repository AlphaGBM/skills (2,240 stars, last pushed 2mo ago), licensed MIT. It adds 180 tokens to every session and 1,724 once invoked, about $0.0009 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.

Related

Other skills, from other repositories