Live data from Hacker News

Breaking Claude Code Opus 5 Auto Mode

131–132 of 132 posts

Re: Breaking Claude Code Opus 5 Auto Mode

#131

Post by subarctic » Thu, Sep 03, 2026, 3:14 AM UTC

pram wrote: post #115

subarctic wrote: post #112

Earlier quoted context omitted.

For someone that's used to the convenience of leaving claude code running unattended in auto mode, how would you recommend I change my setup so that agents are sandboxed? Looking for something that's safer than unsandboxed auto mode but just as convenient, or at least very close to as convenient.

Claude Code has a built in sandbox for terminal commands which is very simple to enable, if nothing else: https://code.claude.com/docs/en/sandboxing

Thanks. I know about that sandbox but I'm asking about if I were to use another harness like pi instead

Re: Breaking Claude Code Opus 5 Auto Mode

#132

Post by Sattyamjjain » Sat, Sep 05, 2026, 4:45 PM UTC

subarctic wrote: post #112

kstenerud wrote: post #51

Just one of the many reasons why I run my agents sandboxed (and why I wrote agent sandboxing software). I once caught my Claude agent complaining that it couldn't connect to https://some-weird-domain.com because the network was down (I disable network in the sandbox when it doesn't need it, and broker the API connection). I asked why it was looking there and it told me I'd asked it to. I never found any evidence of p…

For someone that's used to the convenience of leaving claude code running unattended in auto mode, how would you recommend I change my setup so that agents are sandboxed? Looking for something that's safer than unsandboxed auto mode but just as convenient, or at least very close to as convenient.

[flagged]

Post reply on HN