https://yashsachdeva.com/tags/claude-code/ Recent content in Claude Code on Tech Blog Hugo -- gohugo.io en © 2026 Yash Sachdeva Sun, 26 Apr 2026 23:30:00 +0530 https://yashsachdeva.com/posts/dissecting-the-claude-code-harness-part-2-extensibility-scale/ Sun, 26 Apr 2026 23:30:00 +0530 https://yashsachdeva.com/posts/dissecting-the-claude-code-harness-part-2-extensibility-scale/ <h2 class="relative group">1. Sub-Agents — Scaling Beyond a Single Loop <div id="1-sub-agents--scaling-beyond-a-single-loop" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#1-sub-agents--scaling-beyond-a-single-loop" aria-label="Anchor">#</a> </span> </h2> <p>The single-threaded agentic loop is simple and predictable, but it cannot parallelize work. Claude Code addresses this with <strong>sub-agents</strong> — child agent instances that run their own isolated loops.</p> https://yashsachdeva.com/posts/dissecting-the-claude-code-harness-part-1-the-execution-engine/ Fri, 24 Apr 2026 23:30:00 +0530 https://yashsachdeva.com/posts/dissecting-the-claude-code-harness-part-1-the-execution-engine/ <h2 class="relative group">Introduction <div id="introduction" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#introduction" aria-label="Anchor">#</a> </span> </h2> <p>Claude Code is Anthropic&rsquo;s terminal-based AI coding agent. On the surface it looks like a CLI that &ldquo;just talks to Claude,&rdquo; but under the hood it is a stateful software layer that sits between a stateless language model and your local development environment. The model provides the reasoning; the harness provides the hands, eyes, and workspace.</p>