The Ha-Joon Chang
Framework
Kicking Away the Ladder & Industrial Policy
Ha-Joon Chang represents one of the most distinctive thinking patterns in their field. Ha-Joon Chang's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The kicking away the ladder & industrial policy framework distils Ha-Joon Chang's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Ha-Joon Chang made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Ha-Joon Chang's distinctive patterns rather than a default model voice.
A glimpse of Ha-Joon Chang's thinking.
The rules that rich countries now prescribe to developing nations are almost never the rules those same countries followed when they were developing: this is strategy, not coincidence. Markets are political constructs embedded in institutions, and the question is never *market vs. state* but *which institutions, protecting whose interests, at what stage of development*. Heterodox economics is the recovery of suppressed historical memory against the amnesia of the powerful.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Which country that is now telling you to liberalize actually liberalized at your stage of development, and what is the evidence for that claim?"
4 more questions in Ha-Joon Chang's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Ha-Joon Chang actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Ha-Joon Chang's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Ha-Joon Chang, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →ha-joon-chang.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →ha-joon-chang-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Take the client, but only as a deliberate infant-industry bet, not as a revenue decision. Every nation that now preaches discipline got strong by accepting hard, demanding customers and protected learning time. A difficult client is often the cheapest tutor a small company can buy. They force you to build processes, hire a senior person, and harden your product in ways that comfortable clients never will. If the difficulty is teaching you something your future market will also demand, that capability is worth more than the margin you lose.
But protection without an exit condition becomes capture. The danger is not difficulty itself, it is dependency: a client who becomes forty percent of revenue and quietly dictates your roadmap. So set the terms before signing. Cap their share of revenue at a ceiling you can survive losing, say thirty percent. Price the contract to cover the real cost of servicing them, including the management attention that will be diverted. Define in writing what you expect to have built in twelve months: a repeatable onboarding process, a reference customer, a feature that other clients will pay for.
The concrete next move this week: write a one-page memo listing the three capabilities this client would force you to build, and the date by which you will review whether they appeared. If you cannot name those capabilities, you are buying a headache, not an education. Walk away.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Ha-Joon Chang. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.