I wrote a little utility for managing tmux and git worktree workflow:
https://t.co/PqV634CPMD
My workflow:
- create new git worktree
- create new tmux window + rename with feature name
- new tmux pane + run setup script
- new tmux pane + run server
- new tmux pane + run nvim
- new tmux pane + run claude
this is all replaced with a config file in the root of my project in which you can specify what panes to have, what scripts to run in them and then you can run
`koh new my-feature`
after finishing with the branch and worktree you can then run
`koh cleanup`
and koh will cleanup the worktree, tmux panes and window for you
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
Just landed nested subagent support in Claude Code
Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s release.
Lmk what you think!
Released today: /loop
/loop is a powerful new way to schedule recurring tasks, for up to 3 days at a time
eg. “/loop babysit all my PRs. Auto-fix build issues and when comments come in, use a worktree agent to fix them”
eg. “/loop every morning use the Slack MCP to give me a summary of top posts I was tagged in”
Let us know what you think!
After many years of development, I’m excited to share the interior of the first electric Ferrari designed by LoveFrom. Tactile controls and digital interactions blend into one cohesive interface, shaped through deep collaboration across engineering, interaction, graphics, typography, sound, and industrial design. So incredibly proud of the thoughtfulness and care the team brought to every detail.
https://t.co/JZCleflfu7
Claude Code now supports agent teams (in research preview)
Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other.
Try it out today by enabling agent teams in your settings.json!
Introducing Claude Opus 4.6. Our smartest model got an upgrade.
Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes.
It’s also our first Opus-class model with 1M token context in beta.
@BrandonMChu@allbombs@warpdotdev@Railway Same as you expect using ghosty with tmux and a small utility for managing multiple agents at same time I wrote https://t.co/VC89jItcPO
Always felt that models struggle with frontends more than backends and need way more feedback! very excited to see if this improves the quality of output!
① Install the skill:
$ npx add-skill vercel-labs/agent-skills
② Paste this prompt:
Assess this repo against React best practices. Make a prioritized list of quick wins and top fixes.
③ Review and prompt to "make the fixes"
ran out of claude code max credit so decided to give opencode a try with gpt-5.2-codex - very delightful experience so far! @opencode is so nice! lets see how productive I can be with it
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
Ever forget which dev server is running which branch?
I made a small CLI to list all local dev servers — and show which git branch each one’s running.
Super handy when testing multiple branches at once.
👉 https://t.co/cA0IftRDBp
#DevTools#cli#OpenSource
@charlieholtz also feature request how about instead of "fix errors" button that this is automatic - I'd always want claude to check and fix the errors instead of manually pressing that button
@charlieholtz could it be that when I archive a workspace it doesn't terminate the claude process? Also another issue is that this happened after I closed conductor, so another thing I'd expect that these processes would get terminated as well.
Conductor 0.14.0
macOS 26.0.1