mental-model-fusion-skill

mental-model-fusion-skill is a skill for Claude Code, Codex from peterfei/forge-skill. It costs 92 tokens per session (4,893 once invoked), scanned A, original, MIT.

A structured way to examine a problem using connected ideas from several fields, such as psychology, economics, physics, and biology. It is based on Charlie Munger’s “latticework” of mental models.

In plain words
What is it for?
Use it to analyse complex decisions, check for narrow thinking, compare cross-disciplinary perspectives, and improve your reasoning about difficult problems.
Why use it?
It helps prevent relying on one familiar way of thinking for every problem. Comparing several models can reveal assumptions and useful perspectives that one field alone may miss.

Skill for Claude CodeCodex

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

Good fit Use it to analyse complex decisions, check for narrow thinking, compare cross-disciplinary perspectives, and improve your reasoning about difficult problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/peterfei/forge-skill/mental-model-fusion-skill
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 peterfei/forge-skill --skill mental-model-fusion-skill
Clone the repo
git clone --depth 1 https://github.com/peterfei/forge-skill

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 mental-model-fusion-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/peterfei/forge-skill/mental-model-fusion-skill/github.svg)](https://agentmods.dev/skills/peterfei/forge-skill/mental-model-fusion-skill)
Your own site
<a href="https://agentmods.dev/skills/peterfei/forge-skill/mental-model-fusion-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/mental-model-fusion-skill/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 mental-model-fusion-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/peterfei/forge-skill/mental-model-fusion-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/mental-model-fusion-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,893 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 $0.00092 $0.04893
Opus 5 $0.00046 $0.02447
Sonnet 5 $0.00018 $0.00979
Haiku 4.5 $0.00009 $0.00489

Measured 9d ago against content hash 427b75953181, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mental-model-fusion-skill 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.

methods/mental-model-fusion-skill/SKILL.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

心智模型融合(Mental Model Fusion)思维工具

"拥有一个心智模型,你会变成那个锤子眼中的一切都是钉子的人。但如果你拥有100个心智模型,你就能以更客观的方式看待现实。" —— Charlie Munger


激活条件与触发词

直接使用触发词

  • 「用心智模型分析...」
  • 「多学科思维视角」
  • 「帮我检查是否存在锤人综合征」
  • 「用 latticework 分析」
  • 「跨学科」「mental models」

诊断推荐触发词

  • 「想提升决策质量」
  • 「感觉思路固化」
  • 「需要不同学科视角」
  • 「分析复杂问题」

方法框架概览

心智模型融合是一套将来自不同学科的核心心智模型相互连接、形成网状结构的认知方法论。其核心是避免依赖单一模型导致的"锤人综合征",通过调用多个相关模型进行交叉验证,获得任何单一学科无法提供的洞察力。Charlie Munger 将此方法称为"Latticework"(网格),强调"对多学科知识的掌握是获得真正智慧的钥匙"。


核心原理

原理1:心智网格理论(Latticework of Mental Models)

一句话定义: 将来自不同学科的80-90个核心心智模型相互连接形成网状结构,而非孤立存储,以应对生活中90%的情况。

跨域证据1: [投资哲学] Charlie Munger 在1994年USC演讲《A Lesson on Elementary Worldly Wisdom》中系统阐述了心智网格理论。Munger认为:"你必须拥有所有主要学科的核心模型,并将它们连接成网格。当你拥有了这个网格,你就能够自动地调用正确的模型。"他强调这是Berkshire Hathaway投资决策的核心方法论。

跨域证据2: [认知科学] Philip Johnson-Laird在1983年开创性著作《Mental Models》中奠定了心智模型的认知科学基础。Farnam Street研究表明,心智模型是对某事如何运作的简化解释,当多个模型相互连接时,能够产生涌现式的认知能力。

应用方式: (1) 系统性学习各学科的基础原理(心理学、经济学、物理学、生物学等);(2) 主动寻找不同模型之间的关联点;(3) 在决策时同时调用多个相关模型进行交叉验证。

局限: 需要大量时间和精力投入;容易陷入"收集模型"而非"应用模型"的陷阱;深度理解多学科基础几乎是不可能的任务。

原理2:能力圈原理(Circle of Competence)

一句话定义: 只在真正具备知识和优势的领域内运作,清晰认知知识边界,并诚实地承认边界之外的无知。

跨域证据1: [投资实践] Charlie Munger在1995年Berkshire Hathaway年会上明确指出能力圈是"第一号心智模型"。他解释道:"我们只在能力圈内运作,在这个圈子里,我们比其他人有优势。"Berkshire通过只购买完全理解的企业建立了投资帝国。

跨域证据2: [商业智慧] IBM创始人Tom Watson Sr.的名言:"我不是天才,但我在某些方面很聪明……我坚守那个边界。"这一理念被广泛应用于商业决策、职业规划和个人发展中。

应用方式: (1) 明确列出自己真正理解的行业/领域;(2) 对能力圈外的机会保持克制;(3) 通过持续学习有节制地扩大能力圈;(4) 定期审视边界是否随时间变化。

局限: 能力圈可能随时间变化而缩小或扩大;过度自信导致误判边界;可能被误用为"舒适区"的借口。

原理3:洛拉帕卢扎效应(Lollapalooza Effects)

一句话定义: 多种因素、偏差或倾向在同一方向上共同作用时,产生远超各因素简单叠加的极端结果(1+1=11)。

跨域证据1: [认知心理学] Charlie Munger整合了认知心理学和行为经济学的见解,指出当多个心理偏差(如奖励机制、社会认同、权威效应)在同一方向上叠加时,会产生极端效果。他称之为"Lollapalooza效应",这在可口可乐投资决策中发挥了关键作用。

跨域证据2: [社会科学] CMQ Investing的研究指出,大的效应通常来自大量因素组合而非单一因素。在社交媒体成瘾、金融危机等复杂现象中,都能观察到洛拉帕卢扎效应的作用。

应用方式: (1) 寻找多个正向因素叠加的机会;(2) 警惕多个负向因素同时出现的风险;(3) 理解复杂系统中多因素互动的非线性效应;(4) 在产品设计中利用多种心理学原理创造正向效应。

局限: 难以预测所有参与因素;反向洛拉帕卢扎效应同样危险;过度简化可能忽略关键因素。

Read the full file on GitHub · 307 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 · 307 lines · 92 tokens per session scan A 427b75953181

Subscribe to this mod's changes

mental-model-fusion-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 4,893 once invoked, about $0.0005 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

opencli-usage

Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".

jackwener/OpenCLI · 74 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

opencli-browser-sitemap

Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…

jackwener/OpenCLI · 64 tokens

crit-story

Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.

tomasz-tomczyk/crit · 47 tokens

gpt-vis

A chart-generation tool that recommends visual formats for data and produces either chart settings or runnable code. It uses GPT-Vis, a library for rendering data visualisations.

antvis/chart-visualization-skills · 63 tokens

antv-x6-editor

A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.

antvis/chart-visualization-skills · 253 tokens