Set Your Editor to Autosave So Claude Sees Your Changes Instantly
Claude Code watches the filesystem. If your editor only saves on Cmd+S, there's a gap between when you type and when Claude can read your changes. That lag breaks the feedback loop.
In Zed, add this to your settings (Cmd+,):
{
"autosave": {
"after_delay": {
"milliseconds": 500
}
}
}
In VS Code, add this to settings.json:
{
"files.autoSave": "afterDelay",
"files.autoSaveDelay": 500
}
With your terminal on one half of the screen and your editor on the other, both looking at the same file, the result feels like collaborating on a shared document. You add a comment in the editor; Claude reads it within a second. Claude edits a function; your editor shows it instantly. Neither side is waiting on the other.
This is especially useful when you're guiding Claude through a task incrementally. You type a note or a constraint directly into the file, and Claude reacts to it on its next action without you needing to repeat yourself in the chat.
Half a second of latency is the difference between a loop and a lag.
Log in to leave a comment.
When Claude writes error messages, button labels, validation text, or onboarding flows, it defaults to generic developer-speak. Add a "Users" section to your CLAUDE.md describing who your actual users are — their technical level, industry jargon, and what they care about — so Claude writes copy that makes sense to THEM, not to developers.
Use the --agent flag with custom markdown files in .claude/agents/ to launch purpose-built Claude sessions with restricted tools and scoped system prompts.
Every project has traps — the billing module that silently fails if you forget to queue the job, the legacy table with column names that don't match the model, the config value that must be set before tests run. Document these gotchas in your CLAUDE.md so Claude avoids the same mistakes your team spent days debugging.