Original: Prior to AI agents we ran sanity checks like:
console.log("sanity")
print("sanity")
Log.d("test","sanity")
Run multiple autonomous coding agents simultaneously with Verdent's isolated Git worktrees. Each agent tackles different components while maintaining full context awareness, eliminating manual debugging bottlenecks and accelerating feature delivery. Discover Verdent AI (Free Trial)
When collaborating with AI agents we have to perform a different kind of sanity check.
Add your name at the top of your CLAUDE.md:
CLAUDE.md
# My name is {NAME}
This file provides guidance to Claude Code when working with this repository.
## Project Overview
This is a React application built with TypeScript and Vite.
...
Then ask Claude:
What is my name?
This works as a quick sanity check. If Claude knows your name, all is good. If Claude does not, then something is wrong.
There are various situations where things could go wrong:
- Forgetting to set a
CLAUDE.md - Putting the
CLAUDE.mdin the wrong folder - Accidentally deleting part of the
CLAUDE.md - Misspelling
CLAUSE.md - Running out of context window (sometimes unavoidable)
The simplest way to 'sanity check' your configuration is to place your name at the top of your CLAUDE.md and ask Claude your name.
Run multiple autonomous coding agents simultaneously with Verdent's isolated Git worktrees. Each agent tackles different components while maintaining full context awareness, eliminating manual debugging bottlenecks and accelerating feature delivery. Discover Verdent AI (Free Trial)
See Also: CLAUDE.md Supremacy|Configuration|Context Window Constraints
