https://www.speakcode.ai/blog Field notes from running AI coding agents in production: Claude Code workflows, multi-agent orchestration patterns, and what actually ships. Mon, 14 Sep 2026 06:19:04 GMT https://www.speakcode.ai/blog/claude-code-vs-cowork https://www.speakcode.ai/blog/claude-code-vs-cowork Fri, 14 Aug 2026 00:00:00 GMT A coding agent, a knowledge-work agent from the same company, and a self-hosted assistant. Why comparing their feature lists is the wrong move, and what actually decides it. https://www.speakcode.ai/blog/claude-code-subscription https://www.speakcode.ai/blog/claude-code-subscription Wed, 12 Aug 2026 00:00:00 GMT Official pricing answers what a plan costs, not what happens when you run four agents. Why burn scales linearly, where tokens actually go, and the levers that genuinely help. https://www.speakcode.ai/blog/claude-md-agents-md https://www.speakcode.ai/blog/claude-md-agents-md Mon, 10 Aug 2026 00:00:00 GMT Claude Code does not read AGENTS.md — one import line fixes that. Then: where instruction files load from, why splitting into imports saves no context, and what belongs in a hook instead. https://www.speakcode.ai/blog/claude-code-security https://www.speakcode.ai/blog/claude-code-security Sat, 08 Aug 2026 00:00:00 GMT Permission rules constrain what Claude decides; the sandbox constrains what the OS allows. Why that gap matters, what yolo mode still refuses, and where the real risk sits. https://www.speakcode.ai/blog/claude-code-auto-mode https://www.speakcode.ai/blog/claude-code-auto-mode Thu, 06 Aug 2026 00:00:00 GMT Auto mode is a classifier, not a yes-to-everything switch. The three mechanisms called loops, what survives unattended, and the rules from running 42 of them. https://www.speakcode.ai/blog/claude-code-plugins https://www.speakcode.ai/blog/claude-code-plugins Tue, 04 Aug 2026 00:00:00 GMT A plugin is not a different thing from a skill — it is a shareable, versioned wrapper around one. What can go inside, how the two marketplaces differ, and why to read hooks.json first. https://www.speakcode.ai/blog/claude-code-web https://www.speakcode.ai/blog/claude-code-web Sun, 02 Aug 2026 00:00:00 GMT The DIY answer is now mostly the wrong answer. What ships first-party, the three cases where self-hosting still wins, and why echo prediction over a network is a dead end. https://www.speakcode.ai/blog/claude-code-agent-teams https://www.speakcode.ai/blog/claude-code-agent-teams Fri, 31 Jul 2026 00:00:00 GMT Two agents in one checkout will destroy each other's work within the hour. The worktree layout, the claim field, and the merge gate that stop it — with the exact commands. https://www.speakcode.ai/blog/claude-code-desktop-app https://www.speakcode.ai/blog/claude-code-desktop-app Wed, 29 Jul 2026 00:00:00 GMT There is now an official Claude Code desktop app, and it does most of what people installed third-party GUIs for. The five surfaces, what each is best at, and the three gaps that survive. https://www.speakcode.ai/blog/claude-code-skills https://www.speakcode.ai/blog/claude-code-skills Mon, 27 Jul 2026 00:00:00 GMT A skill is a playbook with a trigger attached, and the trigger is one sentence of frontmatter. What that means in practice, and the rule we use to decide when a procedure earns its own file. https://www.speakcode.ai/blog/claude-code-tutorial https://www.speakcode.ai/blog/claude-code-tutorial Sat, 18 Jul 2026 00:00:00 GMT Most Claude Code tutorials stop at the install command. The step that changes outcomes is the 20 minutes you spend on CLAUDE.md and permission modes before the first real task — here's the full path to a multi-file change that lands. https://www.speakcode.ai/blog/claude-code-workflow https://www.speakcode.ai/blog/claude-code-workflow Sat, 18 Jul 2026 00:00:00 GMT We run 42 autonomous Claude Code loops that each open one small, verified PR per tick. The lesson: workflow structure, not prompt quality, is what ships code — small increments, worktree isolation per task, and a merge gate that curls the real page. https://www.speakcode.ai/blog/codex-vs-claude-code https://www.speakcode.ai/blog/codex-vs-claude-code Sat, 18 Jul 2026 00:00:00 GMT We run Claude Code and Codex side by side every day: Claude Code drives multi-file agentic work through its CLAUDE.md/hooks/skills ecosystem, and Codex adversarially reviews every diff before merge. The honest verdict isn't either/or — it's orchestration.