DEV Community

hyuga profile picture

hyuga

Small, zero-dependency tools that check what an agent claims against what is actually there. Currently finding out how much of my own tooling was describing itself rather than measuring itself.

My linter kept warning the people who did it right. Three times, in the same direction

My linter kept warning the people who did it right. Three times, in the same direction

Comments
5 min read

Want to connect with hyuga?

Create an account to connect with hyuga. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
That amazing skill you shared only runs on your machine. I built a linter for it — then found I was 85% wrong

That amazing skill you shared only runs on your machine. I built a linter for it — then found I was 85% wrong

Comments 12
4 min read
Don't trust "Done." — forcing AI agents to re-fetch reality before they report completion

Don't trust "Done." — forcing AI agents to re-fetch reality before they report completion

Comments 4
7 min read
I attacked my own npm package before launching it. It let the proposer approve their own writes

I attacked my own npm package before launching it. It let the proposer approve their own writes

1
Comments
6 min read
Your agent can write to your database. Which layer is actually stopping it?

Your agent can write to your database. Which layer is actually stopping it?

Comments
11 min read
The card said one column. The apply wrote two.

The card said one column. The apply wrote two.

Comments
7 min read
loading...