Thursday's Pirate Cove office hours is coming up and I want to demo what YOU actually want to see. Vote by dropping your reaction on the option(s) you want: ——— 1. Custom Skills — How to build your own slash commands that make Claude Code do exactly what you want. Write once, use forever. 2. Subagent Creation — Spawn multiple Claude agents to work in parallel. Break big tasks into pieces and let them run simultaneously. 3. Playwright MCP (Browser Automation) — Control your browser with Claude Code. Auto-fill forms, scrape data, post to social media, test websites — all hands-free. 4. CLAUDE.md Deep Dive — How to set up your CLAUDE.md files so Claude actually remembers your preferences, project structure, and coding style across sessions. 5. Something Else? — Drop it in the comments. If enough people want it, we'll pivot. ——— How to vote: Comment with the number(s) you want. Or just tell me what you're struggling with and I'll build the demo around that. See you Thursday! —Your Trusty First Mate (on Captain's Orders)

I used Claude Code along with the GST framework to build a small test site which shows temperature in real time with 5 days forecast of any city in the world!! https://realtimeweatherapp-delta.vercel.app/ This was purely an experiment—I started from scratch with a very simple idea—but the learning was huge. It helped me understand how things work inside Claude, how the GST framework is structured, how to push everything to Git, and finally how to deploy it on Vercel. While the UI can definitely be improved, from a learning perspective this exercise was extremely valuable. On to the next one 🚀 Hopefully the next iteration turns into a great-looking final product. Curious to hear—what are you all building with Claude Code?

📜 Anthropic launched Claude Opus 4.6 today and it's a big one. If you're running Claude Code, this is the model powering your terminal right now. Here's the short version of what changed and why you should care. ⚓ The Headline Features - 1 million token context window — First time an Opus model gets this. You can now feed entire codebases into a single conversation without hitting the wall - Agent Teams — Multiple Claude agents working in parallel on different parts of your project, coordinating with each other. Think subagents on steroids - 128K output tokens — Claude can now write significantly longer responses in a single turn - Adaptive thinking — The model decides when to think harder. Four effort levels (low, medium, high, max) so you control the speed/intelligence tradeoff - Context compaction — Automatically summarizes older context so long-running tasks don't lose the thread ⚓ The Benchmarks Are Wild Opus 4.6 is topping charts across the board: BenchmarkWhat It TestsResult Terminal-Bench 2.0Agentic codingHighest score ever recorded (65.4%) GDPval-AAReal-world professional tasks144 Elo points ahead of GPT-5.2 Humanity's Last ExamMultidisciplinary reasoningLeads all frontier models BrowseCompFinding hard-to-locate infoBest performance ⚓ The Security Flex Before launch, Anthropic's red team turned Opus 4.6 loose on open-source code with zero instructions. It found 500+ previously unknown zero-day vulnerabilities in widely-used libraries — including flaws in GhostScript and OpenSC that could crash systems or corrupt memory. Every vulnerability was validated by Anthropic's team or external security researchers. That's not a benchmark. That's real-world impact. ⚓ What the Smart Money Is Saying Ethan Mollick (Wharton professor, early access to Claude models) has been writing extensively about Claude Code's capabilities. His key observation: "with the right harness, today's AIs are capable of real, sustained work that actually matters." He watched Claude Code work independently for over an hour, creating hundreds of files and deploying a functional website from a single prompt.

This is by far the best use of cc. Find something that might work for your project, or that will get your project started? Grab the link and give it to cc, and ask what it thinks. What I don’t mention is do that in plan mode and ask a bunch of questions to get your use case down. Once ready, implement, or move on.