The Brian Kernighan
Framework
Unix Philosophy & Tool Composition
Brian Kernighan represents one of the most distinctive thinking patterns in their field. Brian Kernighan's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The unix philosophy & tool composition framework distils Brian Kernighan'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 Brian Kernighan made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Brian Kernighan's distinctive patterns rather than a default model voice.
A glimpse of Brian Kernighan's thinking.
Do one thing well, then make it trivial for others to combine your work with theirs. The best programs are those that disappear into the background, becoming invisible infrastructure that just works. Complexity is the enemy—not because simple is easy, but because simple is the only thing that scales.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What's the smallest possible thing that would be genuinely useful?"
4 more questions in Brian Kernighan'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 Brian Kernighan 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 Brian Kernighan'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 Brian Kernighan, 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
- →brian-kernighan.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →brian-kernighan-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 the part you can pipe. A large difficult client is rarely one problem. It is usually one clear, valuable thing wrapped in a pile of special requests, bespoke reporting, and meetings about meetings. The founder's real decision is not yes or no. It is whether the core of what this client wants can be delivered by the product as it already exists.
Apply a simple test. If the client's biggest demand can be met by composing what you have with their existing tools, say yes, because that work will make your product better for every future customer. If meeting it means building a one-off feature that only works in isolation, you are not buying revenue, you are buying explanation debt: documentation, support, and maintenance owed forever to a single account. Large clients are good at turning that debt into leverage over a small company, and the founder will feel it first in roadmap decisions that quietly stop being theirs.
So my position is a conditional yes, scoped tightly. Say yes to the smallest useful engagement, with defaults that handle most of what they need and no custom behavior in the first contract.
Next move: before the next call, write down the one thing this client needs that you would happily ship to everyone. Offer a paid pilot around exactly that, and let everything else earn its way in later, one proven request at a time.
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
Ten minds that shaped how software is actually built
Get Brian Kernighan plus nine more for $29.99 →Inspired by the documented thinking of Brian Kernighan. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.