31–40 of 48 posts
Is there an easy way to do something similar for Claude Code? I'm growing tired of babysitting it to make sure it doesn't do anything bad. Late adopter. Started last night. Stayed up four hours past my normal bedtime because I couldn't stop. (Ended up "building" a fancy .MOD player for DOS in Turbo C.) Needed the Max 5x plan after two hours. (The 'Pro' plan should be renamed 'Sampler', made one-time and free with CC…
Is there an easy way to do something similar for Claude Code? I'm growing tired of babysitting it to make sure it doesn't do anything bad. Late adopter. Started last night. Stayed up four hours past my normal bedtime because I couldn't stop. (Ended up "building" a fancy .MOD player for DOS in Turbo C.) Needed the Max 5x plan after two hours. (The 'Pro' plan should be renamed 'Sampler', made one-time and free with CC…
Isn't the easy way just a development VM? As in: Install your OS of choice in a virtual machine, e.g. even hosted on your main machine. Install the AI coding tool in the virtual machine. Set up a shared folder between host+guest OS. Only let the VM access files that are "safe" for it to access. Its own repo, in its own folder. If you want to give the AI tool and VM internet access and tool access, just limit what it…
A fun fact about apple containers[2], it's more isolated than docker containers as in it doesn't share the VM across all containers.
How about the windows App ?
How about the windows App ?
Is that even a sandbox? I thought it was just a wrapper around an (old) existing tool that has been infinitely rebranded. Their old "remote desktop" program and some web listing capabilities to launch it in "rootless" mode.
https://simonwillison.net/2026/Jan/12/claude-cowork/
That’s the point of this gist, and the related blog post.
Also, it’s a bit of a stretch to call Claude Code, which isn’t even a year old…old.
Earlier quoted context omitted.
I mean, it depends on what you're doing but I force claude to always commit code every time it finishes a todo. It never seems to stop doing that, so I run it in dangerous mode on Zed. I get to review the code after the fact anyway.
The risk isn’t that it makes weird commits; it’s that it may decide to clean up stuff and delete more than desired. - https://github.com/anthropics/claude-code/issues/4331 - https://github.com/anthropics/claude-code/issues/7787 - https://news.ycombinator.com/item?id=46268222
Is there an easy way to do something similar for Claude Code? I'm growing tired of babysitting it to make sure it doesn't do anything bad. Late adopter. Started last night. Stayed up four hours past my normal bedtime because I couldn't stop. (Ended up "building" a fancy .MOD player for DOS in Turbo C.) Needed the Max 5x plan after two hours. (The 'Pro' plan should be renamed 'Sampler', made one-time and free with CC…
Isn't the easy way just a development VM? As in: Install your OS of choice in a virtual machine, e.g. even hosted on your main machine. Install the AI coding tool in the virtual machine. Set up a shared folder between host+guest OS. Only let the VM access files that are "safe" for it to access. Its own repo, in its own folder. If you want to give the AI tool and VM internet access and tool access, just limit what it…
SandVault [0]: Run AI agents isolated in a sandboxed macOS user account
ClodPod [1]: Run AI agents isolated inside an OSX virtual machine
Earlier quoted context omitted.
The risk isn’t that it makes weird commits; it’s that it may decide to clean up stuff and delete more than desired. - https://github.com/anthropics/claude-code/issues/4331 - https://github.com/anthropics/claude-code/issues/7787 - https://news.ycombinator.com/item?id=46268222
You can roll back commits
Is there an easy way to do something similar for Claude Code? I'm growing tired of babysitting it to make sure it doesn't do anything bad. Late adopter. Started last night. Stayed up four hours past my normal bedtime because I couldn't stop. (Ended up "building" a fancy .MOD player for DOS in Turbo C.) Needed the Max 5x plan after two hours. (The 'Pro' plan should be renamed 'Sampler', made one-time and free with CC…
`yolobox run claude` launches Claude Code with --dangerously-skip-permissions mode inside of a container with a good set of default tools included.
Earlier quoted context omitted.
Is that even a sandbox? I thought it was just a wrapper around an (old) existing tool that has been infinitely rebranded. Their old "remote desktop" program and some web listing capabilities to launch it in "rootless" mode.
Yes, there is a sandbox. https://simonwillison.net/2026/Jan/12/claude-cowork/ That’s the point of this gist, and the related blog post. Also, it’s a bit of a stretch to call Claude Code, which isn’t even a year old… old .
Earlier quoted context omitted.
Isn't the easy way just a development VM? As in: Install your OS of choice in a virtual machine, e.g. even hosted on your main machine. Install the AI coding tool in the virtual machine. Set up a shared folder between host+guest OS. Only let the VM access files that are "safe" for it to access. Its own repo, in its own folder. If you want to give the AI tool and VM internet access and tool access, just limit what it…
Here are my open-source (MIT) solutions for Mac development: SandVault [0]: Run AI agents isolated in a sandboxed macOS user account ClodPod [1]: Run AI agents isolated inside an OSX virtual machine 0: https://github.com/webcoyote/sandvault 1: https://github.com/webcoyote/clodpod