Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code Cheat Sheet

cc.storyfox.cz

Post reply on HN
Print view View original

151–160 of 215 posts

Re: Claude Code Cheat Sheet

#151

Post by dangoodmanUT »

joegibbs wrote: post #92
dangoodmanUT wrote: post #22

I think this is the argument for UIs - it should be self-explanatory since it's singificantly simpler than an IDE

I used to think UIs would be better for agents, but I changed my mind: UIs suit traditional software very well because there are only X actions that can be performed - it makes sense that if you have an image converter that can take X, Y and Z formats and convert them to A, B and C then you should have a UI that limits what the user can do, preventing them from making mistakes and making it obvious what's possible. B…

The terminal is a pretty bad place to have free form input if you need a separate key bind to paste an image than to paste text…

Re: Claude Code Cheat Sheet

#152

Post by theshrike79 »

AugustoCAS wrote: post #110

Are 'project rules' a thing? > .claude/rules/ .md Project rules > ~/.claude/rules/ .md User rules or is it just a way to organise files to be imported from other prompts?

Yes, they're even documented on the official site: https://code.claude.com/docs/en/memory#organize-rules-with-c...

Re: Claude Code Cheat Sheet

#153

Post by theshrike79 »

kstenerud wrote: post #115
kqr wrote: post #113

Earlier quoted context omitted.

I keep hearing that, and I have yet to go there. I find the permission checks are helpful – they keep me in the loop which helps me intervene when the LLM is wasting time on pointless searches, or going about the implementation wrong. What am I missing?

The problem comes when it starts asking you hundreds of times "May I run sed -e blah blah blah". After the 10th time you just start hitting enter without really looking, and then the whole reason for permissions is undermined. What works is a workflow where it operates in a contained environment where it can't do any damage outside, it makes any changes it likes without permission (you can watch its reasoning flow if…

You can allow specific commands, you do know that?

I run a generic Claude on my ~/projects/ directory and Claude logs every now and then and ask it what commands I commonly have to keep manually accepting in different projects and ask it to add them to the user-level settings.json.

Works like a charm (except when Opus 4.6 started being "efficient" and combined multiple commands to a single line, triggering a safety check in the harness).

Re: Claude Code Cheat Sheet

#154

Post by theshrike79 »

kstenerud wrote: post #125
kqr wrote: post #119

Earlier quoted context omitted.

> starts asking you hundreds of times "May I run sed -e blah blah blah". In my experience, that is already a sign that it's no longer trying to do the right thing. Maybe it depends on usage patterns.

I've found that any time I have Claude refactor some code, it reaches for sed as its tool of choice. And then the builtin "sandbox" makes it ask for permission for each and every sed command, because any sed command could potentially be damaging. Same goes for the little scripts it whips up to speed up code analysis and debugging. And then there's the annoyance of coming back to an agent after 15 mins, only to discov…

Try adding LSP support using the anthropic skills that should make it a bit more efficient.

Re: Claude Code Cheat Sheet

#155

Post by nl »

throwaw12 wrote: post #150
embedding-shape wrote: post #145

Earlier quoted context omitted.

Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.

sorry, have you used Claude Code or are you a bot? "--dangerously-skip-permissions" - is a flag, irrelevant to LLM

How to tell if someone has never used Claude Code...

Re: Claude Code Cheat Sheet

#156

Post by rdevilla »

throwaw12 wrote: post #150
embedding-shape wrote: post #145

Earlier quoted context omitted.

Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.

sorry, have you used Claude Code or are you a bot? "--dangerously-skip-permissions" - is a flag, irrelevant to LLM

[flagged]

Re: Claude Code Cheat Sheet

#157

Post by unholiness »

throwaw12 wrote: post #150
embedding-shape wrote: post #145

Earlier quoted context omitted.

Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.

sorry, have you used Claude Code or are you a bot? "--dangerously-skip-permissions" - is a flag, irrelevant to LLM

The relevance is that Claude made this cheat sheet.

Re: Claude Code Cheat Sheet

#158

Post by nl »

consumer451 wrote: post #137
jerrygoyal wrote: post #70

I recently switched from the CC terminal to the CC VS Code extension, and I like it better.

It seems like it’s chronically behind though. One example, last I checked /btw only worked via CLI.

I agree it is behind - but usually only a few days.

I'm a big fan of the VS Code add-in. Despite the current narrative that IDEs are dead, I find the ability to look at multiple things at once is works much better in some kind of.. GUI editing tool.. than just using a terminal.

Re: Claude Code Cheat Sheet

#159

Post by ticulatedspline »

throwaw12 wrote: post #150
embedding-shape wrote: post #145

Earlier quoted context omitted.

Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.

sorry, have you used Claude Code or are you a bot? "--dangerously-skip-permissions" - is a flag, irrelevant to LLM

Author stated they used Claude to compose the document. I believe they were alluding to the idea that Claude's own safety alignment prevented it from documenting the flag because it's called dangerous.

Re: Claude Code Cheat Sheet

#160

Post by embedding-shape »

throwaw12 wrote: post #150
embedding-shape wrote: post #145

Earlier quoted context omitted.

Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.

sorry, have you used Claude Code or are you a bot? "--dangerously-skip-permissions" - is a flag, irrelevant to LLM

Yes, use it every day :) And very much a human, AFAIK.

My point is that if you ask "Hey Claude, please write out all common and useful command line arguments into a commands.html file", the LLM that actually does that work, might ignore anything that says "dangerous" or gives that indication, because the LLM doesn't think potentially dangerous commands could be "common" and/or "useful". Hope my point makes sense now.

Post reply on HN