tkjef

thanks! will be checking out your project as well. if someone is running 5+ agents for different features i recommend just stating them as different objectives of the claude session and just let claude code auto-spawn sub-agents that handle them.

it seems like ai providers are getting better at deciding when to make sub-agents on their own. but i'm actively exploring this and will hopefully have more to report back sooner than later. your approach is cool.

i have found that the agent cli tools running in the panes are more dialed in by having the local directory structure as context and the best streaming text interface to show ai output on. the chat panel is kind of a nice to have as it's familiar. you can highlight text on the terminal > right click > choose Fix This|Explain This and it's sent to the chat panel to dig into more.

it's also, helpful for asking tangential questions about the current claude session, while allowing it to keep running but not interfering with it.

Creator here, happy to answer questions. A quick demo of the auto-snap workflow: you type 'claude' or 'codex' in any pane, Yaw detects it, and splits — agent on the left, shell in the same directory on the right. When the agent exits, the split closes automatically. It sounds trivial but it removed a surprising amount of friction for me.

Love to hear others pain points around terminals!

yeah, the ai cli split-pane workflow really works for me. creds are encrypted via local keychain.

After burning out I thought through several business ideas, but ended up starting a fruit tree farm and getting a motorcycle. Having a blast!

Also, what a lot of consumers think is that it is basically free and it is not.

the range would be for more than one trip.

anecdotally i had a 2011 Nissan Leaf 1st year it came out. Was neat. I have not gone back to electric. I sold it for $800 with 90k miles on it.

I have been on the terraform side for 7 years-ish.

eksctl just really impressed me with its eks management, specifically managed node groups & cluster add-ons, over terraform.

that uses cloudformation under the hood. so i gave it a try, and it’s awesome. combine with github actions and you have your IAC automation.

nice web interface for others to check stacks status, events for debugging and associated resources that were created.

oh, ever destroy some legacy complex (or not that complex) aws shit in terraform? it’s not going to be smooth. site to site connections, network interfaces, subnets, peering connections, associated resources… oh, my.

so far cloudformation has been good at destroying, but i haven’t tested that with massive legacy infra yet.

but i am happily converted tf>cf.

and will happily use both alongside each other as needed.

i did say violently breaking the law is American.

and i did also say it was complicated and nuanced so please do not ignore that detail of my comment.

i’m glad to hear life is good, and to hear you’re humble enough to acknowledge it could be better. it could be better over here, too. are we doing it right or are you? i have no idea. :)

we’re probably both doing things right and wrong. should it even be solved? are we just living a Memento (great movie) like existence where we’re keeping ourselves busy and at war because if we all got along we would over-populate the planet and destroy earth?

what if our ignorant violent human behavior is actually an environmental mitigation technique?

very reasonable observation. :)

i can tell you being physically strong comes with it violence and is at the fabric of being an American. so i’d say the issue is complicated and nuanced as is most.

breaking the law (through violence) is also American. we stand up for what we believe in. even if it means breaking the law and going against our government. this is America.

the fact that you have better outcomes for crime is great. how’s your investment system? how’s your sports teams? how’s your military? how’s your stock market? how’s your currency?

i agree with everything you say. i just think the first step is what i’m laying out.

gotta show them we’re not afraid to play their game and win it as well.

we should be able to play any game, any time. But based on that direct the game to be of higher moral ground.

editing this comment as apparently we’ve reached our thread comment limit.

yes, bargaining from a position of power. that would allow to direct it to a more suitable place. banding together with individuals of power to produce combined power. you say it’s impossible and then say exactly how we’re going to do it. :)

i hope you know this has been a very enjoyable conversation for me.