01Links
Claude Code
Put your agent inside the repo, where it can read the plan, run the skills and check its work.
Keep command-line contexts side by side in Warp, so your agent work has a place to run.
Why I keep it
I do my command-line work in Warp because it lets me keep several contexts going side by side. I run the Claude Code CLI or the OpenCode CLI there, so I can work with agents across those contexts.
Warp has basically replaced my IDE, so the terminal is where I go to work on code. I open it with Caps Lock + W through Raycast and Hyperkey, so getting there is part of the same setup I use to switch between apps.
01Links
Put your agent inside the repo, where it can read the plan, run the skills and check its work.
02Links
Give the writing to the model I prefer for copy, while Claude checks every claim against its source.
03Links
Keep separate jobs open across Claude accounts, with Notch showing which account has room to work.
04Links
Speak the job, the look and the stack in one brief, so your agent gets the context together.
05Links
Give apps and tools their own shortcuts, so you can switch contexts from the keyboard.
06Links
Turn Caps Lock into all four modifiers, so new shortcuts don’t clash with app defaults.
I’ll send you one build log a week: what I added to the library and what I shipped with it. You can unsubscribe any time.