> Permission rules are old hat. Everyone should be using auto mode instead. It is safer and also does not require manually maintaining finicky allow/deny lists. Auto mode is enabled by default and is included for free in all plans.

More and more it seems we are being prescribed a particular way to use Claude Code: move fast, break things, do not look at the edits, etc. Basically, Claude Code is designed for vibe-coding.

I hate this, and I suspect a lot of devs do too. I use the TUI, and believe it or not, I like to review every edit or change before Claude makes it. I used to allow auto mode and don't ask again sometimes in the past, but now almost never do. The number of incredibly nonsensical things I catch Claude trying to do sometime just reinforced my commitment to this way of working.

So now this idea that permissions are old hat and auto mode is the way to go rubs me the wrong way, very much. And here are a litany of other ways Claude Code TUI is making it hard for me to work:

1. Scroll-back glitches, too numerous to enumerate. Suffice it to say I rely on it a lot, to refer back to something the agent said before, to review the general progression of the session, etc, etc. And it barely works now: missing/overwritten conversation text, messages that have inexplicably disappeared; even sometimes the agent own last response is garbled or hidden or overwritten by some previous message that keeps floating on top.

2. I use iTerm2 on macOS, and frequently use split panes. Whenever change the width of a pane, Claude Code messes up the conversation text so that is often unreadable, and nothing I do will restore it.

3. As other sibling comments have noted, the current preference of Claude to use incomprehensible scripts for editing files is off-putting and a hindrance to being in control of my work. I have resorted to using the permissions setting to ban it from using Go, Perl, Python, and sed (for in pace editing), etc, to cope with this.

4. Even basic text editing is messed up in Claude Code TUI. I used to be able to navigate around lines effectively by using up/down keys; this was removed, which has significantly impacted by work. I cannot disable copying on selection, which I don;t want, because if I disable it, the copying does not work at all, etc

At this point, due to all the impediments Claude Code places to my style of working, the only reasonable conclusion I can reach is: I am supposed to be vibe coding, letting the agents loose to vomit out massive amounts of slop. But if vibe coding of the Claude Code TUI itself is producing such garbage, why should anyone be convinced that it is a good thing?

I will never let Claude Code loose to do its thing; I will not surrender my control to it, no matter how much many times I hear I no longer need to look at code.

Claude Code's "Don't Ask Again" exposes passwords in 1,122 public GitHub files