https://falcao.org/tags/developer-tools/Recent content in Developer-Tools on Danilo Falcão da SilvaHugoen-usSun, 19 Jul 2026 11:22:41 -0300https://falcao.org/posts/herdr-adds-agent-state-tmux-never-had/Sun, 19 Jul 2026 11:22:41 -0300https://falcao.org/posts/herdr-adds-agent-state-tmux-never-had/<p>I moved to tmux about fifteen years ago and <a href="https://falcao.org/posts/tmux-vs-gnu-screen/">I have not looked back</a>. I have also spent a fair number of words arguing that <a href="https://falcao.org/posts/the-problem-with-changing-tools-too-often/">changing tools too often</a> is a tax most teams pay without noticing, and that the question worth asking about any new tool is narrow and unglamorous: what <em>class of operational pain</em> does it delete, and is that worth relearning how things fail?</p> <p>So when a new terminal multiplexer shows up with 18,000 stars and a launch post, my first instinct is suspicion. The multiplexer problem has been solved since 1987. Prettier panes are not a reason.</p>https://falcao.org/posts/opencode-v2-no-longer-plan-b/Sun, 19 Jul 2026 10:10:50 -0300https://falcao.org/posts/opencode-v2-no-longer-plan-b/<p>In May I wrote that Claude Code was my daily driver and <a href="https://falcao.org/posts/claude-code-opencode-cursor/">OpenCode was my Plan B</a>. That label aged quickly.</p> <p>I meant it as a compliment. Plan B is the tool you&rsquo;re glad you installed — the one you fall back to during an outage or a client engagement that won&rsquo;t approve the supply chain. But Plan B also means <em>second choice</em>, and I listed three specific reasons it was second: a less-polished agent loop, a weaker subagent and verification story, and a smaller skills and integration ecosystem. Those were fair criticisms in May. The OpenCode 2.0 beta addresses all three head-on.</p>