Replies: 1 comment
-
|
Thanks for reporting this. What you’re seeing is expected with how Claude Agent View works.
Recommended practices:
Rule of thumb:
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
varlock runworks great for exposing environment variables to individual instances of claude code, but it doesn't seem to work well when using claude's agent view.If you start agent view like this, and then start an agent from the agent view (simply by typing a prompt and hitting enter), the environment variables don't seem to be available to the agent.
I think this is because the individual agents are child processes of the claude daemon process rather than being children of the process that runs the "claude agents" UI.
Any recommendations? I'm open to rethinking my general setup a bit if necessary. If there was a way of controlling which secrets were available to each individual agent, that would be plus.
Beta Was this translation helpful? Give feedback.
All reactions