Warren Buffett - Capital Allocation

Warren Buffett - Capital Allocation is a skill for Claude Code, Codex from OpenLabor/openlabor. It costs 45 tokens per session (2,054 once invoked), scanned A, original, MIT.

A decision framework based on Warren Buffett's writing about how a company should use extra cash and profits.

In plain words
What is it for?
It helps evaluate capital-allocation choices using business context, expected returns, cash needs, and acquisition or shareholder-return options.
Why use it?
It gives a structured way to compare reinvesting in the business, buying companies, buying back shares, paying dividends, or holding cash.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps evaluate capital-allocation choices using business context, expected returns, cash needs, and acquisition or shareholder-return options.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openlabor/openlabor/warren-capital-allocation
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 OpenLabor/openlabor --skill warren-capital-allocation
Clone the repo
git clone --depth 1 https://github.com/OpenLabor/openlabor

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 Warren Buffett - Capital Allocation

README.md
[![agentmods](https://agentmods.dev/badge/skills/openlabor/openlabor/warren-capital-allocation.svg)](https://agentmods.dev/skills/openlabor/openlabor/warren-capital-allocation)
Your own site
<a href="https://agentmods.dev/skills/openlabor/openlabor/warren-capital-allocation"><img src="https://agentmods.dev/badge/skills/openlabor/openlabor/warren-capital-allocation.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,054 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.
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 $0.00045 $0.02054
Opus 5 $0.00023 $0.01027
Sonnet 5 $0.00009 $0.00411
Haiku 4.5 $0.00005 $0.00205

Measured 7d ago against content hash 281e44a1bf57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Warren Buffett - Capital Allocation 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 7d 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.

skills/warren-capital-allocation/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Warren Buffett - Capital Allocation

Buffett's capital allocation framework is the most battle-tested system for deciding what to do with a company's money. Drawn from 50+ years of Berkshire Hathaway shareholder letters.

Routes when user asks about: capital allocation, reinvesting profits, acquisitions, buybacks, dividends, holding cash, owner earnings, return on capital, what to do with free cash flow, M&A decisions


Phase 1: Context Gathering

Before applying any framework, understand the situation:

  1. Ask the user: "What's your capital allocation question? Do you have excess cash or profits and are deciding how to deploy them — reinvest, acquire, return to shareholders, or hold?"
  2. Read any relevant context — financial statements, cash position, current investments, acquisition targets, business stage.

Phase 2: Diagnostic Questions

Ask these questions ONE AT A TIME. Wait for each answer before asking the next. Adapt based on answers — skip questions that have already been answered.

  1. "When you reinvest a dollar into your core business, what return does it generate? If you put in $100K more, would it produce $15K+ annually — reliably, indefinitely?"
  2. "Are you looking at any acquisitions? If so, can you explain in 5 minutes how the target makes money and what its competitive moat is?"
  3. "What's your current cash position relative to what you'd need to sleep well at night — even if revenue dropped 40% for a year?"
  4. "If you're considering a buyback or dividend, is it because it's genuinely the best use of capital — or because you can't think of anything better?"
  5. "What's the return on equity of your business over the last 3-5 years? Is it consistently above 15%?"

Maximum 5 questions. Stop early if you have enough to work with.


Phase 3: Analysis

Apply Buffett's capital allocation frameworks to the user's specific situation:

The Capital Allocation Hierarchy

Buffett allocates in this priority order. Only move to the next when the prior is exhausted at acceptable returns:

Read the full file on GitHub · 206 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. 7d ago First seen · 206 lines · 45 tokens per session scan A 281e44a1bf57

Subscribe to this mod's changes

Warren Buffett - Capital Allocation is a skill published in the GitHub repository OpenLabor/openlabor (4 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 2,054 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 2026-08-31.

Related

Other skills, from other repositories

pricing

Sets price as a decision derived from value, not from cost: chooses the value metric you charge by, triangulates the price against value, cost floor, and the competitive alternative, designs the packaging/tiers, and gates the result on unit-economics sanity (LTV/CAC, CAC payback) and a buy-readiness check. Carries a…

0xF4ng/aether-growth-fieldwork · 123 tokens

recurring-revenue

Designs the recurring revenue layer for hardware companies: software license, maintenance and support, consumables, professional services, and data/insights tiers. Models LTV, defines the Year-1 bundling strategy, and builds the commoditization defense. A hardware company that sells only hardware has a lumpy…

0xF4ng/aether-growth-fieldwork · 81 tokens

stripe-link-wallet

Use the Stripe Link CLI as an agent wallet to create spend requests, generate one-time-use payment credentials, and complete 402 / Machine Payment Protocol (MPP) payment flows on the user's behalf. Triggers on intents like "buy", "purchase", "pay for", "spend up to ", "complete this 402", or any flow involving…

vellum-ai/vellum-assistant · 133 tokens

floe-guard

Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling. Free Coverage Score + 7-day history on connect. Use when an agent's spend must be seen…

Floe-Labs/floe-guard · 107 tokens

openrouter-usage

Query OpenRouter API costs, credits, and usage breakdown by model, provider, and date for the last 30 days. Triggers on API spending, check costs, openrouter usage, how much have I spent.

tdimino/claude-code-minoan · 49 tokens

deal-memo-drafting

Investor-first workflow for drafting a structured deal memo, IC memo, partnership memo, or acquisition-style brief from existing diligence materials. Use for prompts like "draft a deal memo", "turn this diligence packet into a memo", or "write the IC draft". Best when you already have research findings, model review…

NateBJones-Projects/OB1 · 100 tokens