Claude Code Auto Mode Not Working: Check the Real Mode First
Claude Code auto mode not working? Cycle Shift+Tab once: if auto is in the cycle, a defaultMode line wins; if not, the text beside it names the cause.
Claude Code auto mode not working? Cycle Shift+Tab once: if auto is in the cycle, a defaultMode line wins; if not, the text beside it names the cause.
Ollama on 100% CPU after an Ubuntu update? A driver mismatch: new NVIDIA packages, old module still loaded. Reboot, check ollama ps, then hold the driver.
If Claude Code ignores CLAUDE.md, check what loaded: every loaded rule held 45 of 45 in our runs; misses were subfolder rules and uncalled skills.
Local LLM hardware: a 14B fits a 16GB card at 32K, a 30B MoE coder at 32K takes 24GB, and 70B at 32K needs a 96GB Mac, because context uses memory.
If a skill shows in /skills but Claude ignores it, the description likely isn’t why: in 45 runs, misses came only from requests that never named the job.
1Password for Claude fills logins on a Mac after you approve each one. What it needs, how it asks at every login, and what to try when it stops connecting.
Send coding-agent tasks to a cheap model like GPT-6 Luna only when you can check the result fast, and route the rest by what a wrong change would break.
Pro 500 vs Pro 200 for Codex after the October 30 cut: what each plan gives, how Ultrafast burns 8x usage, and why I moved back to Pro 200.
Before Claude Code runs unattended overnight, I keep push keys and real .env files out of its reach. Then I don’t trust “success”: 38 blocked runs said it.
Let an AI agent read your email and draft replies, but approve each send and payment yourself and leave off the one setting that removes that stop.