Sort replies: Relevant Recent Liked
Replying to @ryancarson
running this pattern too. one addition: having the agent write to memory files mid-session not just end of day catches more context before it gets lost
3
1
108
51,675
Good call
14
38,212
Replying to @ryancarson
Could you have this run a copy of your setup on a virtual Mac via something like Scaleway instead of keeping your own machinec’awake’
1
2
7,196
Replying to @ryancarson
it's good to have you back on here :)
1
1
6,328
Replying to @ryancarson
When do you review the code?
1
1
6,807
in the morning with @greptile
1
1
8
6,516
Replying to @ryancarson
Can this work for any agents or just Claude code?
1
2
11,533
Any agents
2
9,448
Replying to @ryancarson
@ryancarson how are you using compound engineering with amp given that it relies heavily on custom agents and amp doesn't have custom agents as far as I know?
1
1
7,909
I just use the skill
1
1
6,142
Replying to @ryancarson
Just adapted it to my @openclaw, thanks for the idea!
1
1
977
Replying to @ryancarson
Can I do this with Claude code?
1
1,511
Maybe read the article
1
8
1,395
Replying to @ryancarson
But do I need the server rack unit as pictured
1
9,871
Replying to @ryancarson
x.com/acolombiadev/status/20… This is exactly the kind of setup that made me write about the maintenance problem. You’ve got an agent shipping features every night. AGENTS.md files growing. PRs stacking up. But here’s the question I keep coming back to: who’s watching the repo health while all this code lands? Docs drifting from code. Test coverage gaps. Dependencies going stale. CI pipelines getting slower. The stuff that doesn’t break immediately but compounds in the wrong direction. @GitHub Next built something called Peli’s Agent Factory for this exact gap. Over 100 maintenance workflows: triage agents, CI diagnostics, doc drift detection, security monitors. Agents that maintain what your building agents ship.
4
10
3,363
Replying to @ryancarson
How to best manage out of tokens?
1
3
1,629
Replying to @ryancarson
Ryan like you energy

ALT Clapping Leonardo Dicaprio GIF

2
847
Replying to @ryancarson

ALT waynes world GIF

2
778
Replying to @ryancarson
I find that my biggest blocker is not choosing what to work on (which this post does a great job in tackling), but how to merge the work into main. Even with CI passes, the agent don’t always adhere to patterns, write tests, or add proof that it works. Any advice on that front?
1
2
3,308
Replying to @ryancarson
@samtemaki this seems interesting, please email it to Gandalf and tell him to consider it and report back to me.
1
163
Replying to @ryancarson
👏👏
1,096
Hey @ryancarson, thank you for sharing your workflow in Claude Code. Followed your article and set it up successfully on Windows. I successfully ran with clauee the planning parr of your script and it returned a plan in the terminal. But when I try to run the implementation patt in PowerShell I get this error message: EBADF: bad file descriptor error on history.jsonl.lock. How can I fix it? Btw, I'm using my Max subscription and not API calls.
1,700
Replying to @ryancarson
thanks for the tip, i think a lot of people will find this useful
1,102
Replying to @ryancarson
Thank you Ryan very useful
154
Replying to @ryancarson
Passive agents can’t fix flawed logic. Being present > just automating Followed you, would be awesome if you returned it @ryancarson
571
Replying to @ryancarson
Sleeping agents won’t fix broken thinking. Presence > automation. Just followed you would really appreciate a follow back. @ryancarson
1,017
Replying to @ryancarson
bold of you to assume that i sleep
3
1,164
Replying to @ryancarson
@agrimsingh favorite hobby
617