agentic engineering scorecard→agentic engineering scorecard→practice - custom linting rules that inject in-repo documentation as context→custom linting rule→linting rule

linting rule
linting rule

Backlinks

custom linting rule

^ custom linting rule

see in context
video - harness engineering from OpenAI - 2026-04

At 13:00 he talks about adding linting rules that catch specific issues. For example, on every request, it should always have a retry and a timeout

Another static analysis check that he suggests is forcing all of the files to be less than 350 lines because model attention is scarce. Feels like the types of constraints you would add with Rubocop

see in context

At 34:45 they sort of pushed towards something like microservices and used linting rules to ensure that the services were actually being used. He says that it's great if you can just look into one directory to be able to make most of the changes that you need to make in order to do what you need to do.

see in context

At 38:30 One purpose of the practice - context right in the repo is that it serves as a centralized way to prompt inject the model for any of the sort of the structured failure modes (like linting rule or static analysis violations)

At 38:50 he had them bucket their feedback into the persona that they were operating as for example, front end engineer.

see in context