Tag: claude-code
All the articles with the tag "claude-code".
-
Functional Scars: Turning Repeated AI Agent Mistakes Into Runtime Controls
Functional scars turn a correction your AI coding agent keeps forgetting into a check that runs at the moment of the action. Why it exists, how it works, three measured cases.
-
It never opened the file I handed it
I built a hook that hands my agent the name of the right note before it answers. Then I judged all 1,234 firings blind. The name was right two times in three. The file got opened one time in four.
-
Every audit deleted the audit before it
A monthly job reduced three months of outcome labels to unknown, every time it ran. The row survived, the totals moved, and the only witness was a backup the job itself had just written.
-
You can't measure a memory hook by the times it spoke
I tagged sixty hook activations, concluded retrieval was fine, and wrote down a verdict. Then I measured the prompts where the hook said nothing at all, and the number flipped.