apply-mental-models

apply-mental-models is a skill for Claude Code from impactbrussels/FounderOS. It costs 115 tokens per session (1,048 once invoked), scanned A, original, Apache-2.0.

A Founder OS skill that examines difficult founder decisions through selected mental models, or structured ways of looking at a problem. Founder OS is a library of guidance for people starting companies.

In plain words
What is it for?
Use it to frame a decision, distinguish reversible from hard-to-reverse choices, and stress-test options using two or three relevant lenses.
Why use it?
It exposes assumptions, risks, and blind spots that a quick decision based only on instinct may miss.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the founderos plugin — 23 skills, 3 agents shipped together

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.

agentmods
npx agentmods add skills/impactbrussels/founderos/apply-mental-models
Any agent
npx skills add impactbrussels/FounderOS --skill apply-mental-models
Clone the repo
git clone --depth 1 https://github.com/impactbrussels/FounderOS

Made for: Claude Code.

Or install founderos, the plugin that ships this one along with the rest of its 23 skills, 3 agents.

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 apply-mental-models

README.md
[![agentmods](https://agentmods.dev/badge/skills/impactbrussels/founderos/apply-mental-models.svg)](https://agentmods.dev/skills/impactbrussels/founderos/apply-mental-models)
Your own site
<a href="https://agentmods.dev/skills/impactbrussels/founderos/apply-mental-models"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/apply-mental-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,048 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00115 $0.01048
Opus 5 $0.00057 $0.00524
Sonnet 5 $0.00023 $0.00210
Haiku 4.5 $0.00012 $0.00105

Measured 5d ago against content hash 9b4ca586530a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

apply-mental-models 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 5d 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/apply-mental-models/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Mental Models

Founders make a hundred judgement calls with no playbook. The fastest way to think better isn't more data - it's running the decision through a few sharp lenses that each catch a different blind spot. This skill picks the right lenses for your decision and forces the thinking that gut alone skips. Proof before hype: a decision examined from three angles beats a confident first instinct.

The method

Built on the Founder OS scaffold. The full lens library - classic models (Munger, Taleb, Bezos, Thiel, Graham) and the author's frameworks (Proof Ladder, Trust Stack, Narrative-Evidence Gap, Five Killers, Operator's Creed) - is in references/mental-models.md.

Step 1 - Frame the decision

State it in one sentence, and classify it:

  • Reversible (two-way door)? Then bias to speed - don't over-think it.
  • Irreversible (one-way door)? Slow down; this is where lenses earn their keep.
  • What's the [CONSTRAINT] (runway, time) and what would make this decision wrong?

Step 2 - Pick 2-3 lenses that fit (not all of them)

Match the lens to the decision (see references for the full set and when to use each):

Decision type Lenses that earn their keep
Big bet / strategy Inversion · Power law · Contrarian question · Barbell
Launch / claim / messaging Proof Ladder · Copy Test · Narrative-Evidence Gap
Survival / runway The Five Killers · Antifragility · Via negativa
Build vs not Work-backwards / press-release test · Do things that don't scale
Trust / positioning Trust Stack · Comparison-Set Problem
Advice you've been given Skin in the game · Circle of competence

Step 3 - Run the decision through each lens

For each chosen lens, write the one sentence it produces. E.g. Inversion: "the surest way to kill this is X - so guard against X." Power law: "one of these five things matters most - it's Y."

Step 4 - Read the pattern

Read the full file on GitHub · 91 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. 5d ago First seen · 91 lines · 115 tokens per session scan A 9b4ca586530a

Subscribe to this mod's changes

apply-mental-models is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,048 once invoked, about $0.0006 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