How Claude Code’s Safe Mode Finds What Broke Your Config
Claude Code’s new –safe-mode flag (v2.1.169) boots with all your customizations off, so you can isolate which setting broke things.
First-person Claude Code tips, prompts, memory patterns from daily use.
Claude Code’s new –safe-mode flag (v2.1.169) boots with all your customizations off, so you can isolate which setting broke things.
Claude Code 2.1.152 added /reload-skills, which rescans your skill directory without killing the session. For anyone editing skill files daily, it ends the restart-and-rebuild-context loop.
I retype similar prompts almost daily. Claude Code’s Ctrl+R reverse search lets you fuzzy-find and rerun any past prompt — here’s my honest take after a few days.
I edit my Claude Code skills several times a day. /reload-skills lets me rescan the skill directory mid-session, so I no longer lose my context to a restart.
Claude Code now snapshots your code before every change. When a refactor goes sideways, two presses of Esc restore every touched file — no git stash, no command to memorize.
I was running five Claude Code sessions and burning out bouncing between tabs to hit Enter. The new /goal command made that disappear in one line.
I ran Claude Code for a year with zero plugins. Now I have five and use all of them daily — here’s what each does, when it fires, and the before/after.
Rename, archive, edit, and share link — four ChatGPT sidebar features that quietly decide how organized your conversations stay.
After using both daily for over a year: Claude for writing and code, ChatGPT for everyday chat. Here’s how to pick the right one in five minutes.
Pin a frequent task as a natural-language instruction and Claude reproduces the same procedure every time. With the skill-creator plugin, you can generate the skill itself from a single prompt.