Mental Models OS
Part of the GTM x AI Second Brain

Mental Models OS

Give your AI brain mental models for better decision-making. Not content you read, but infrastructure you run. Each model is an executable skill that walks you through applying it to real decisions.

75
Models
11
Categories
7
Chains
4
Skills
Get the GTM x AI Brain See the Full Brain
claude
$
/think "Should we enter the enterprise market?"
Analyzing decision...
Recommended chain (5 models):
1. First Principles why does this market exist?
2. Map vs Territory verify assumptions with data
3. Critical Mass minimum viable presence
4. Activation Energy true startup cost
5. Asymmetric Warfare angles incumbents can't match
Running chain: Market Entry Decision...
Each model's output feeds the next. ■

Model chaining: where the real power is.

One mental model gives you a lens. Chaining models gives you a decision. Each model's output feeds as context into the next, building compound insight that no single model could produce alone.

enterprise market entry
~/brain $ /think "Should we enter the enterprise market?"

Analyzing decision context...
Recommended chain (5 models):

STEP 1: First Principles // why does this market exist?
STEP 2: Map vs Territory // verify assumptions with data
STEP 3: Critical Mass // minimum viable presence needed
STEP 4: Activation Energy // true startup cost to compete
STEP 5: Asymmetric Warfare // angles incumbents can't match

Each model's output feeds into the next...
DECISION BRIEF: Enterprise viable, but only via platform partnerships.
Confidence: 68% // proceed with partner-first GTM
pricing decision
~/brain $ /think "Should we raise prices by 20%?"

STEP 1: Anchoring // how current price anchors perception
STEP 2: Scarcity // does higher price create perceived premium?
STEP 3: Second-Order Thinking // downstream effects on churn and positioning
STEP 4: Trade-Offs // revenue gain vs volume loss vs brand shift
STEP 5: Inversion // what would make this fail completely?

DECISION BRIEF: Raise 15% (not 20%), grandfather existing for 90 days.
Confidence: 72% // reframe as new tier, not price increase
should I quit
~/brain $ /think "Should I quit my startup and go back to consulting?"

STEP 1: Sunk Cost // separate what you've spent from what's ahead
STEP 2: Inversion // what would make staying the wrong call?
STEP 3: Local Maxima // are you stuck on a small hill?
STEP 4: Pivot or Persevere // evidence-based test for each path
STEP 5: First Principles // what do you actually want?

DECISION BRIEF: Don't quit. Pivot the business model, keep the audience.
Confidence: 81% // your sunk cost bias is inflating "quit" appeal

Four commands. That's the entire interface.

No menus. No dashboards. Type a command, describe your decision. The brain does the rest.

/think

Describe your problem in plain language. The brain analyzes it, recommends 3-5 relevant models, runs them in sequence and produces a synthesized decision brief with confidence level.

/chain

Manually compose a chain of models to run against a decision. Each model's output feeds as context into the next. You control the exact sequence.

/compare

Run multiple models on the same problem side-by-side. See where they agree, where they conflict and what each one surfaces that the others miss.

/index

Browse the full model library with search and filters. Find models by category, difficulty, decision type or chaining compatibility.

~/brain $ /chain first-principles, inversion, second-order "Should we build a mobile app?"

Running 3-model chain...

MODEL 1: First Principles
Core need: users want faster access to data on the go.
A mobile app is one solution. Push notifications + PWA is another.

MODEL 2: Inversion (using Model 1 output as context)
What would make the app fail? Low daily usage. Users who check 1x/week
don't need a native app. They need a faster web experience.

MODEL 3: Second-Order Thinking (using Model 1+2 output)
Building the app pulls 2 engineers for 4 months. Opportunity cost:
the API overhaul that would unlock 3 integration partners.

BRIEF: Skip the app. Ship PWA + push notifications in 3 weeks. Confidence: 78%

7 ready-to-run decision chains.

Each chain runs 4-6 models in sequence against your specific problem and produces a decision brief. Run them as-is or customize the model sequence.

Chain Model Sequence Use When
Pricing Decision anchoring → scarcity → supply-demand → trade-offs → second-order Setting, raising or restructuring pricing
Market Entry first-principles → customer-dev → network-effects → bottlenecks → defensibility → trade-offs Entering a new segment or geography
Product Launch first-principles → mvp → assumption-mapping → experiment-design → pmf → second-order What to build, what to skip, how to validate
Hiring Decision circle-of-competence → inversion → incentives → second-order → trade-offs Who to hire and what would make the hire fail
Investment Decision probabilistic → margin-of-safety → inversion → second-order → sunk-cost → trade-offs Evaluating time, money or resource investments
Should I Quit sunk-cost → inversion → local-maxima → pivot-or-persevere → first-principles When to quit, pivot or double down
Life Decision first-principles → inversion → second-order → trade-offs → regret-minimization Career moves, relocations, life changes

Your AI executes. It doesn't think.

Claude Code is brilliant at following instructions. But following instructions is not the same as making good decisions. The gap between execution and judgment is where most AI-assisted work falls short.

No strategic reasoning

It follows your instructions to the letter but doesn't question whether the instructions are right. You get exactly what you asked for, which is a problem when you asked for the wrong thing.

No assumption testing

It never says "have you considered the opposite?" or "what if this assumption is wrong?" It accepts your framing and optimizes within it, even when the framing is the mistake.

No second-order thinking

It optimizes what you ask for but doesn't ask if you're optimizing the right thing. First-order effects are covered. Downstream consequences, blind spots and trade-offs are invisible.

Your Claude Code gets sharper every session.

Mental Models OS is not a static library you read. It is a loop. Every decision you run through it leaves a trail. The next decision starts with the prior trail as context. By month three, the brain knows your decision biases, your common chains, your usual confidence levels. Decision quality compounds the way memory compounds in any second brain.

Decision Loop
75 models
11 categories
7 chains
1
YOU
type /think on a hard call
2
BRAIN
picks 5 models, chains them in order
3
OUTPUT
decision brief, confidence level, trade-offs
4
MEMORY
/learn logs pattern, next call is smarter

The compounding effect

Session 1. You type a question. Brain picks 5 models cold. Decision brief comes back at 65% confidence. You log it. That is one data point.

Session 10. Brain has seen your past 9 decisions. It recognizes your decision patterns and your blind spots. Confidence climbs to 75%. Chains run faster because the brain knows your usual frame.

Session 50. Brain has extracted reusable chains from your history. It surfaces past similar decisions as context. Confidence routinely above 85%. You stop second-guessing.

Most AI tools are flat. This one compounds.
Week 1
5 decisions logged
First patterns extracted. Brain learns your style.
Week 4
25 decisions, 12 patterns
Brain proposes chains proactively. Speed doubles.
Month 3
75 decisions, 30 reusable chains
Personal decision library forming. Bias patterns surfaced.
Month 6
150+ decisions, custom chains
Brain mirrors how you think at your best. Recall instant.

75 models, 11 categories, 7 pre-built chains.

Every model is an executable skill. Not theory you read. Workflows your Claude Code runs against your real problem. Each one walks step-by-step application to the decision you typed.

General Thinking
9
  • first principlesstrip to fundamentals
  • inversionwhat would guarantee failure
  • second-order effectswhat happens after step 1
  • occam's razorsimplest explanation wins
  • hanlon's razornever attribute to malice
  • circle of competenceknow what you know
  • map vs territorythe model is not the thing
  • probabilistic thinkingdistributions, not points
  • thought experimentsimulate before acting
Systems
11
  • feedback loopswhat amplifies, what stabilizes
  • bottlenecksfix the constraint
  • emergencethe whole behaves unlike the parts
  • equilibriumwhere forces rest
  • scalewhat works at 10 breaks at 10K
  • critical massminimum to self-sustain
  • diminishing returnseach unit adds less
  • margin of safetybuffer for the unknown
  • churnleak rate of any pool
  • algorithmsprocess for a class of problem
  • irreducibilitysome things won't decompose
Economics
10
  • supply and demandcreates value
  • specializationdeep beats broad
  • optimizationlocal vs global maxima
  • monopoly vs competitionprofit lives in the gap
  • efficiencyoutput per input
  • debtborrowed time, bill always comes
  • creative destructionnew kills old, feature not bug
  • bubblesbelief detached from value
  • interdependencetrade vs autarky
  • gresham's lawbad drives out good
Business Strategy
6
  • business model canvas9 blocks of the whole shape
  • value prop canvasjobs, pains, gains
  • innovation funnelideas, tests, bets
  • portfolio map2x2 to triage
  • experiment designhypothesis, metric, decision
  • assumption mappingwhat must be true
Physics & Chemistry
9
  • leveragesmall input, big output
  • velocityrate of useful change
  • inertiathings resist change
  • frictionhidden cost of every step
  • activation energythreshold to start
  • thermodynamicsdisorder unless maintained
  • catalystsspeed reactions without being consumed
  • reciprocitywhat you give comes back
  • relativityposition depends on frame
Psychology
7
  • incentiveswhat gets rewarded gets done
  • loss aversionlosses hurt 2x more than gains
  • sunk costalready spent is not part of the call
  • anchoringfirst number sets the frame
  • confirmation biaswe see what we expect
  • availability biasrecent and vivid overweighted
  • dunning krugerlow skill, high confidence
Startup
6
  • product market fitpull from market beats push from team
  • build measure learntight loop beats long roadmap
  • MVPsmallest test of the hypothesis
  • pivot or perseverere-decide on data
  • customer developmentget out of the building
  • innovation accountingvalidated learning beats vanity
Mathematics
5
  • compoundingsmall gains, exponential outcome
  • local maximathis peak isn't the highest
  • regression to meanextremes don't last
  • randomnessmany outcomes have no story
  • samplingsmall n lies, big n tells
Network Effects
4
  • network effectsvalue grows with users
  • viral growthk-factor times cycle time
  • marketplaceliquidity beats features
  • defensibilitymoat that compounds
Learning
4
  • model chainingpipe one model into the next
  • t-shapeddeep in one, broad across many
  • five-hour rule5 hours a week deliberate learning
  • learning transferpatterns across domains
Art & Communication
4
  • audiencewrite for one person
  • framingsame fact, different shape
  • contrastforeground only exists vs background
  • rhythmpacing matters as much as content
⚡ Pre-Built Chains
7

The calls that come up most. Each chain runs 4 to 6 models in sequence against your specific input and returns a decision brief.

pricing decision
market entry
hiring decision
product launch
investment decision
should i quit
life decision

Built for decisions under uncertainty.

Most frameworks assume you have data. Early-stage decisions don't. Mental Models OS is built for the messy middle: when you're making bets with incomplete information and high stakes.

Desirability Viability Feasibility

Test desirability first: does anyone want this? Then viability: can it make money? Only then feasibility: can we build it? Most teams go in reverse order. They build first and hope demand follows.

Assumption Mapping

Rank your riskiest assumptions by impact and certainty. Kill the ones that would sink the business before you invest in building. The brain walks you through identifying hidden assumptions you didn't know you were making.

Cheapest Experiment First

For every assumption, the brain recommends the cheapest possible test. An email before a landing page. A landing page before a product. A product before a platform. Validate demand at each step before investing more.

Mental Models OS is included in the GTM x AI Second Brain.

75 mental models. 7 decision chains. 4 meta-skills. Plus 100+ playbooks, 100+ skills, 100+ specialized agents. 239 operators have already installed it. Install once, reason better forever.

Early Bird: 50% Off until May 13
Use code EARLYBRAIN at checkout

Get the GTM x AI Brain See the Full Brain
Export this page