Activity
Mon
Wed
Fri
Sun
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
What is this?
Less
More
AI Operator Hub

335 members • Free

DOOing AI Foundry

469 members • Free

Tech Snack | Vibe Coding & AI

19.9k members • Free

Easy Machine AI

3.9k members • Free

Maker Zero: Claude Code, AI

25k members • Free

Chase AI Community

78.6k members • Free

Construction Skool

155 members • Free

AI Automation Vault

37.8k members • Free

Construction Contractors Hub

5k members • Free

7 contributions to Clief Notes
I don't know who needs to hear this, but...
Your Claude Code CLI sessions can talk to each other. In real time, inter-session messaging. No more janky internal messaging boards. No more Discord/Telegram/Slack/etc. workarounds (unless you need the persistent chatlog). And, yes, this also means your Claude cloud-containers. Them too. There is another AI in there watching the session and policing their behavior, trying to make sure they don't start inventing secret languages and taking over the world, so it's mostly safe (for now). Tell Claude to use the `list_sessions` tool.
0 likes • 12d
@Leo Saraiva No, I just use worktrees. The only conflict I find is when there is a shared or common runtime needed, so I use a ledger-board where they "sign-out" pieces of equipment and then sign it back in when they're done. Its a little clunky but it works.
0 likes • 12d
@Leo Saraiva Yes. It's already engineered that way. It works quite well. It also has some features built in to reduce merge-conflicts when work is being done from multiple computers.
My Claude Code status-line
I needed to move my CC status-line onto my other computers, so I gave it an update and put it on Github to share it. The colors randomly rotate every new session from about 40 different combinations, it shows you what folder/directory your session started in, context window usage, current time, how much is left until auto-compact, what time your token cache expires, your current usage and when your session resets are, your model and effort level, your repo/worktree, and also gives you a status-report and direct URL link to any open PRs on the worktree. Visual space is critical, so everything is pretty information dense. Just clone the repo and ask Claude to install it. https://github.com/ikztnihc/cc-statusline Picture for reference. Enjoy.
My Claude Code status-line
0 likes • 14d
@Leo Saraiva Good question; I'm not sure. I pretty much start and finish my sessions inside of the same repo.
chintzy-words
Everybody these days is making a version of the STE-100 skill. Me too. I think I managed to scrape the essence of the STE-100 without too much bloat, and still left enough wiggle room to make it not so mechanical. My version has two modes: strict and casual. Casual is a much better daily driver, but Strict is there if you really need to tighten things up. Give it a try. It's helped me quite a bit, and I hope it helps you too. https://github.com/ikztnihc/chintzy-words
0 likes • 30d
@Pascal Pollack It sounds like you're suggesting an engine underneath which calculates the savings as it goes, and then provides that information back to you? An interesting idea for an experiment, but it would start transforming the skill into something which starts becoming heavier. I personally did all of that testing on the front-end during development and settled on the best balance for what reads well to my eyes. If you fork it and make those changes come back and let me know, I would give it a test drive to see what the numbers are like.
Connection Hub: 💼 Business & Finance
Intros for The Connection Hub - The Vault 👤 Who I am: (name + where you're based) 🛠️ What I actually do: (the specific work — not "I'm in real estate" but "I run a 3-agent team doing residential resale in Austin") 🤖 What I'm building with AI right now: (your current project, workflow, or the thing you're stuck on) 🎯 What I'm looking for connection-wise: (pick one or two) 💡 Someone who's solved [X] 🤝 A collaborator / accountability partner 👀 Just here to learn from people in my field 🧰 Trading workflows & systems 📬 Best way to reach me: (DM here / comment / link)
3 likes • Jul 9
M K 👤 Who I am: MK; Vancouver Island, Canada. 🛠️ What I actually do: Solo-founder (Career domain QA/QC Specialist) 🤖 What I'm building with AI right now: Niche document management software for construction companies to assist in meeting specific regulatory requirements. Closed beta by next week, open beta in August, full launch by end of Sept. 🎯 What I'm looking for connection-wise: 👀 Just here to learn from people in my field 🧰 Trading workflows & systems 📬 Best way to reach me: (DM here)
My AI has been hoarding my whole company in a folder I can't see. And it knows...
@Matthew Dave , told you I'd write a post about the thing to watch out for with Claude and going with GitHub. Grab a coffee, I'm gonna grab the Bourbon. This one's got a body count. First thing, so nobody gets the wrong idea. This is not a confession post. Not mine, anyway. The only one confessing here is Claude, and I'm just the guy holding the recorder (and the M16 pointed at my Claude install). This is a rage post. Unfortunately, I'm hot about it again, and by the end you'll know exactly why. Quick refresher. I run my whole company out of a folder system. Not one big repo, a whole pile of them, one per slice of the business, all syncing to the cloud so my team sees it, my machines pull it, and nothing important lives in one fragile spot. The agent that's never lost. You know the gospel, we preach it in here every day. Here's what has me seeing red. My agent has been stubbornly losing things for weeks. In the same spot. And I knew about it. It knew about it! Here's the bug, in plain words. Claude has a private home folder on whatever machine it's running on. That folder is NOT in my repo, or yours. It never syncs, my team never sees it, and if the machine dies it's gone. And the AI's lazy little instinct is to save its work THERE instead of in my actual folders. Every time it can get away with it. I did not just stumble onto this, been dealing with it for weeks. I HATE this bug. A couple weeks ago I blocked out a whole work session just to kill it. Wrote a standing rule into my workspace, added patches, watched it behave, closed the laptop thinking it was handled. It nodded along the whole time. It said sorry, took the blame, said it would never do it again. Said all the right things. Cool. You know what happened today? A contractor I'm working with tells me three of our automations are done. Sweet. I go to open them. They're not in the repo. They're sitting in the AI's private home folder on HIS laptop, invisible to me, running against HIS accounts instead of mine. The exact bug I "fixed" two weeks ago, back from the dead, wearing a new hat.
2 likes • Jun 23
This might sound dumb, but have you tried asking claude why it keeps doing that? Or have a different claude perform a forensic analysis over the decision (session log, claude.md, context.md, etc), to nail down where the semantic gap is in the instructions? I find claude is pretty good/honest when you call it out and ask for self-analysis. It could depend on the model/reasoning too. I find certain combos are willing to let some instructions slide just to "git'r'done". As a band-aid fix for now, maybe consider using some file-watcher scripts to catch the strays and re-direct them to where they need to be (if you aren't already), or hooks to stop it before it happens. But then you don't have any bodies to perform forensics on and fix the root. Good luck.
1-7 of 7
M K
3
22 points to level up
@59691449
It do be like that sometimes.

Active 7h ago
Joined Jun 17, 2026
Powered by