Thin Harness, Fat Skills

Steve Yegge says people using AI coding agents are "10x to 100x as productive as engineers using Cursor and chat today, and roughly 1000x as productive as Googlers were back in 2005." That's a real number. I've seen it. I've lived it. But when people hear it, they reach for the wrong explanation. Better models. Smarter Claude. More parameters. 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. The harness is the product On March 31, 2026, Anthropic accidentally shipped the entire source code for Claude Code to the npm registry. 512,000 lines. I read it. It confirmed everything I'd been teaching at YC: the secret isn't the model. It's the thing wrapping the model. Live repo context. Prompt caching. Purpose-built tools. Context bloat minimization. Structured session memory. Parallel sub-agents. None of that makes the model smarter. All of it gives the model the right context, at the right time, without drowning it in noise. That wrapper is called the harness. And the question every AI builder should be asking is: what goes in the harness, and what stays out? The answer has a specific shape. I call it thin harness, fat skills. Five definitions The bottleneck is never the model's intelligence. Models already know how to reason, synthesize, and write code. They fail because they don't understand your data — your schema, your conventions, the particular shape of your problem. Five definitions fix this. 1. Skill files A skill file is a reusable markdown document that teaches the model how to do something. Not what to do — the user supplies that. The skill supplies the process. Here's the key insight most people miss: a skill file works like a method call. It takes parameters. You invoke it with different arguments. The same procedure produces radically different capabilities depending on what you pass in. Consider a skill called /investigate. It has seven steps: scope the dataset, build a timeline, diarize every document, synthesize, argue both sides, cite sources. It takes three parameters: TARGET, QUESTION, and DATASET. Point it at a safety scientist and 2.1 million discovery emails, and you get a medical research analyst determining whether a whistleblower was silenced. Point it at a shell company and FEC filings, and you get a forensic investigator tracing coordinated campaign donations. Same skill. Same seven steps. Same markdown file. The skill describes a process of judgment. The invocation supplies the world. This is not prompt engineering. This is software design, using markdown as the programming language and human judgment as the runtime. Markdown is, in fact, a more perfect encapsulation of capability than rigid source code, because it describes process, judgment, and context in the language the model already thinks in. 2. The harness The harness is the program that runs the LLM. It does four things: runs the model in a loop, reads and writes your files, manages context, and enforces safety. That's it. That's the "thin." The anti-pattern is a fat harness with thin skills. You've seen it: 40+ tool definitions eating half the context window. God-tools with 2-to-5-second MCP round-trips. REST API wrappers that turn every endpoint into a separate tool. Three times the tokens, three times the latency, three times the failure rate. What you want instead is purpose-built tooling that's fast and narrow. A Playwright CLI that does each browser operation in 100 milliseconds, not a Chrome MCP that takes 15 seconds for screenshot-find-click-wait-read. That's 75x faster. Software doesn't have to be precious anymore. Build exactly what you need, and nothing else. 3. Resolvers A resolver is a routing table for context. When task type X appears, load document Y first. Skills tell the model how. Resolvers tell it what to load and when. A developer changes a prompt. Without the resolver, they ship it. With the resolver, the model reads docs/EVALS.md first — which says: run the eval suite, compare scores, if accuracy drops more than 2%, revert and investigate. The developer didn't know the eval suite existed. The resolver loaded the right context at the right moment. Claude Code has a built-in resolver. Every skill has a description field, and the model matches user intent to skill descriptions automatically. You never have to remember that /ship exists. The description is the resolver. A confession: my CLAUDE.md was 20,000 lines. Every quirk, every pattern, every lesson I'd ever encountered. Completely ridiculous. The model's attention degraded. Claude Code literally told me to cut it back. The fix was about 200 lines — just pointers to documents. The resolver loads the right one when it matters. Twenty thousand lines of knowledge, accessible on demand, without polluting the context window. 4. Latent vs. deterministic Every step in your system is one or the other, and confusing them is the most common mistake in agent design.