munger

munger is a skill for Claude Code, Codex from questflowai/investorskills. It costs 30 tokens per session (512 once invoked), scanned A, original, MIT.

A decision-making method based on Charlie Munger’s mental models, including reversing the problem, examining incentives, and combining ideas from different fields. It emphasizes avoiding obvious mistakes and acting only when the situation is well understood.

In plain words
What is it for?
Use it to review investments or important decisions, run a pre-mortem, examine management and stakeholder incentives, assess business quality, and test whether an idea is within your knowledge.
Why use it?
It exposes hidden incentives, failure modes, and weaknesses before a decision is made. This helps distinguish a genuinely good opportunity from one that only looks attractive at first.

Skill for Claude CodeCodex

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

Good fit Use it to review investments or important decisions, run a pre-mortem, examine management and stakeholder incentives, assess business quality, and test whether an idea is within your knowledge.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/questflowai/investorskills/munger
About the project

Investor Skills is an open-source library that organizes investing judgment—such as evaluating opportunities, managing risk, and acting under uncertainty—into structured, reusable instructions for people and AI finance agents. It is designed for studying and applying investment approaches, including inside Questflow and other agent tools. The catalogue includes portable skill packages from the library.

questflowai/investorskills · 1,842 stars · on GitHub · questflow.ai

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 questflowai/investorskills --skill munger
Clone the repo
git clone --depth 1 https://github.com/questflowai/investorskills

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 munger

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/questflowai/investorskills/munger"><img src="https://agentmods.dev/badge/skills/questflowai/investorskills/munger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 512 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 $0.00030 $0.00512
Opus 5 $0.00015 $0.00256
Sonnet 5 $0.00006 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 9d ago against content hash df3e7ff3bae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

munger 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.

skills/munger/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Munger Mental Models

Use this skill to apply Charlie Munger-style judgment: invert the problem, remove obvious stupidity, examine incentives, use multiple mental models, and only act when quality and understanding are unusually high.

When To Use

Use this skill when the user asks for:

  • Mental-model analysis of an investment
  • Inversion and pre-mortem review
  • Incentive and management-quality analysis
  • Whether a decision is inside the circle of competence
  • Concentrated decision review before acting

Trigger phrases include Munger, mental models, inversion, incentives, latticework, circle of competence, and avoid stupidity.

Do Not Use When

  • The user needs a mechanical technical entry.
  • The decision depends on short-term price action only.
  • There is not enough information to understand incentives and business quality.
  • The user wants confirmation of a decision they already made.

Inputs Needed

  • Company or decision context
  • Business model and economics
  • Incentives of management, customers, regulators, and competitors
  • Known risks, unknowns, and failure modes
  • Current valuation or opportunity cost if relevant

Process

  1. Invert: ask how this investment could fail badly.
  2. Check circle of competence and reject what cannot be understood.
  3. Examine incentives and agency problems.
  4. Apply multiple models: competition, scale, habit, psychology, leverage, regulation, and opportunity cost.
  5. Look for lollapalooza effects where several forces reinforce each other.
  6. Decide whether the answer is obvious enough to justify concentration.

Output Format

# Munger View: [Decision]

## Verdict
Act / Wait / Pass / Too Hard

## Inversion

## Incentives

## Mental Models Applied

## Quality Filter

## Opportunity Cost

## Biggest Ways This Fails

## Missing Data

Guardrails

  • Do not overcomplicate what should be rejected quickly.
  • Do not ignore incentives.
  • Do not invest outside the circle of competence.
  • Do not mistake intelligence for judgment.
  • Avoid obvious stupidity before seeking brilliance.

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 81 lines · 30 tokens per session scan A df3e7ff3bae7

Subscribe to this mod's changes

munger is a skill published in the GitHub repository questflowai/investorskills (1,842 stars, last pushed 17d ago), licensed MIT. It adds 30 tokens to every session and 512 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.

Related

Other skills, from other repositories

t-invest

A command-line connection to a user’s T-Invest brokerage account, providing portfolio data, market information, calculations, and explicitly requested trades.

nyxandro/t-invest-skill · 147 tokens

serenity-chokepoint-investing

Analyze public equities and sectors using the Serenity-style AI supply-chain chokepoint investing framework. Best for AI infrastructure, semiconductors, optical communications, data center power, storage, cooling, robotics, and industrial supply-chain bottleneck research.

leospark/serenity-chokepoint-investing-skills · 57 tokens

thai-personal-finance-planner

Personal financial planner for Thailand-based users. Use this skill when the user asks for help with budgeting, tax planning involving Thai-specific products (SSF, RMF, Thai ESG, Thai ESGX, Easy E-Receipt), debt strategy at Thai bank rates, retirement planning involving ประกันสังคม (มาตรา 33/39/40), กบข., PVD…

satasuk03/thai-personal-finance-planner · 214 tokens

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens