verbose, default, quiet. what do you think?
why do we need a specific tool/command when the PM agent can just write a file in a temporary directory now (thanks to #92)? what if we have 100 git servers, do we have to add 100 commands?
When forking a session, the forked session should inherit the permissions of the parent (since its a fork).
have you verify this? does opencode works this way?
I think rather than letting the agent to decide what kind of behavior it should do, we should prompt it in pm agent markdown as the prior context to the agent.
maybe we have "verbosity"…
if we merged #92 or #93, does this PR is still necessary?
can you test if its working? if its working, can you add unit tests to confirm that in the next release we can still have this working? also, is it makes sense to add this permission setting…
does it work? can you confirm by creating unit tests? if its confirmed, we can add the unit test as well to our kugetsu skill folder. also can we document it as well in the SKILL.md? basically in…
we also need this updated at SKILL.md as well so agent can pick it up that we have env command to manage env rather than injecting them manually on each command
my question is, is it needed to have a separate file for environment rather than utilizing config file?
can we utilize config file or does using a separate config file is a must?
also is it possible to have the config file being written during kugetsu init? especially if the file exist during init, we can --force to overwrite it
please remove this line GIT_SERVERS["git.fbrns.co"]="https://git.fbrns.co"
wow I like the idea of per-session command. but I think we can make it simpler by per agent command, what do you think? for example we can have config that used by all agents. but if its…
in the kugetsu server command, is there no modify and delete command? I think during init, we should prompt to user if they want to add new server or left as default one (github). no server…