-
What agent skills are actually made of
1.9 million agent skills on GitHub. Only 12 in 100 come with any code attached, and when they do it is usually Python, whatever the skill is about.
-
A safety filter moved our benchmark by seven places
A provider content filter silently deleted 29.3% of one model's answers on our regex benchmark, and the blanked calls were not missing at random. Depending on how a harness handles them, the same model finishes 3rd, 10th or 4th out of 11. Running k=3 rather than a single sample is what caught it.
-
What language are agent skills written in?
3.8 million AI agent instruction files on GitHub, read by a model that speaks every language. So why are 85.3% of them in English, and what is changing?
-
a regex can pass its tests and still fail in use
A study of generated regular expressions, benchmark answer keys, and vulnerability screening across corpora. Passing tests is a limited guarantee; corpus differences do not establish what caused them.
-
Mollify, Agents, and Integration
why codebase intelligence for Python wants to be one integrated tool, and what changes now that the reader is a machine