The 2x people and the 100x people run the same models. The gap is architecture around the model, not intelligence inside it — better context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → at the right moment, not more parameters.
A thin agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → does exactly four things: run the model in a loop, read and write your files, manage context, and enforce safety. Anything else you were about to put in it belongs in a agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → instead.
The fat-harness cost is concrete: 40+ tool definitions eating half the context window and multi-second MCP round-trips add up to roughly three times the tokens, three times the latency, and three times the failure rate.
Narrow beats general in tooling. A purpose-built Playwright CLI at ~100ms per browser operation replaces a Chrome MCP that needs ~15 seconds for screenshot-find-click-wait-read — about 75x, for software cheap enough to build for one job.
The author's CLAUDE.md hit 20,000 lines and the model's attention degraded until Claude Code told him to cut it. The fix was ~200 lines of pointers, with the resolver pulling the right document in only when it matters.
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
Why it matters
The framework much of the current AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → discourse is downstream of: keep the harness lightweight, push capability into composable skills, claim 10–100x. Read the original before the takes about it — this is the source.
Key quotes
“The 2x people and the 100x people are using the same models. The difference isn't intelligence. It's architecture — and it fits on an index card.”
“On March 31, 2026, Anthropic accidentally shipped the entire source code for Claude Code to the npm registry. 512,000 lines.”
“This is not prompt engineering. This is software design, using markdown as the programming language and human judgment as the runtime.”
“A confession: my CLAUDE.md was 20,000 lines. Every quirk, every pattern, every lesson I'd ever encountered. Completely ridiculous.”
