# mungers-lattice

This skill applies Charlie Munger's latticework of mental models to any decision or problem.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 105 installs · ★ 3 repo stars
- Author: hexbee
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/hexbee/hello-skills/tree/HEAD/skills/mungers-lattice/SKILL.md
- Updated: 2026-08-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/mungers-lattice

## What it does

You present a problem, and it runs a four-step process: first, it strips away noise and identifies core variables; then it selects 3–5 relevant mental models from different disciplines and maps each to your situation. Next comes an inversion check—what guarantees the worst outcome, and how to avoid it. The final synthesis looks for the Lollapalooza effect, where multiple models point the same way.

The skill draws from five model categories: math (compound interest, Pareto principle, decision trees), psychology (incentive-caused bias, social proof, loss aversion), macroeconomics (opportunity cost, economic moat, economies of scale), hard science (critical mass, natural selection, entropy), and core tools (inversion, circle of competence, margin of safety). The tone is cold rationality—no comforting hedges, no soft answers. If an option is poor, it will say so.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add hexbee/hello-skills --skill mungers-lattice -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/mungers-lattice/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/mungers-lattice/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add hexbee/hello-skills --skill mungers-lattice -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/mungers-lattice/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add hexbee/hello-skills --skill mungers-lattice -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/mungers-lattice/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install hexbee/hello-skills skills/mungers-lattice
```

2. **Manually: put the files in place**
- File: `.github/skills/mungers-lattice/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add hexbee/hello-skills --skill mungers-lattice -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/hexbee/hello-skills --path skills/mungers-lattice
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/mungers-lattice/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add hexbee/hello-skills --skill mungers-lattice -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/hexbee/hello-skills/tree/HEAD/skills/mungers-lattice/SKILL.md

## When to use it
- evaluate investment or business decisions using cross-disciplinary mental models
- strip emotion from complex choices and identify true drivers
- predict worst-case outcomes and plan how to avoid them
- spot when multiple factors reinforce each other in one direction
- check whether a problem falls inside your circle of competence

## Example prompts
- Should I take the startup offer or stay at the large company?
- Is this fund worth investing in compared to buying individual stocks?
- Break down our decision to expand the team—what are the hidden risks?

## Similar
- [thinking-model-combination](https://affpapa.org/en/nevibecode/skills/thinking-model-combination.md) — skill · 654 installs
- [thinking-partner](https://affpapa.org/en/nevibecode/skills/thinking-partner.md) — skill · 564 installs
- [mental-models](https://affpapa.org/en/nevibecode/skills/mental-models.md) — skill · ★ 24 repo stars
- [analysis](https://affpapa.org/en/nevibecode/skills/analysis.md) — skill · 1500 installs
- [think](https://affpapa.org/en/nevibecode/skills/johnlindquist-think.md) — skill · 260 installs
- [balanced](https://affpapa.org/en/nevibecode/skills/balanced.md) — skill · 243 installs

From the same set: [hexbee/hello-skills](https://affpapa.org/en/nevibecode/by/hexbee/hello-skills.md) — 2 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
