You can run a capable AI model on the laptop you already own — no account, no subscription, no usage meter, and no data leaving your machine. Here’s how to install Ollama, pick a model that fits your memory, use agent mode, and point Claude Code at a local model without losing your skills and connectors.
Claude can now run its own sessions. Dispatch takes an outcome you text from your phone, splits it into tasks, and runs each as its own session on your computer. Here’s what Dispatch, cross-session messaging and agent teams each do, and how to pick the right one.
Your work is almost certainly fine — Claude finishes the task before it stops you. What actually happens when you hit the limit, what to do in the next five minutes, and the three changes that make the next one a non-event.
Your CLAUDE.md gets stale as models improve — rules you wrote to babysit an older model are now just noise. Here’s a copy-paste prompt that audits it against Anthropic’s current docs and hands back a tighter file, nothing overwritten until you approve it.
Most resume guides hand you a prompt and call it a workflow. Claude Code works from files on your machine, so your brag sheet, style rubric, and rules persist — and the tenth application takes a fraction of the time the first one did.
Codex vs Claude Code, from someone who uses both daily. Which fits your work, why the choice is lower-stakes than you think, and the one metric that decides.
This is a small project and guide to create a local Wiki-style set of files guided by Claude Code.