For about two weeks last year, roughly one in five runs of my audit pipeline died on the same line:...
Structured Security Findings From a 7B Model: The Schema That Stopped Breaking
Related
Coding agents: Your skill bodies are fine, your descriptions are broken
Hi friends This is a follow-up to my post about structuring CLAUDE.md, skills and agents. A comment...
One Repo Became Three — Quietly, Then Publicl
One Repo Became Three — Quietly, Then Publicly ai #docker #security #mcp ...
I stopped installing opaque AI agents and started copying their source
A practical test for reusable agents: copy the definition into your project, inspect every permission boundary, and accept that updates become your responsibility.