One of my favorite concepts from MetaHarness: benevolent prompt injection. “Maintaining context hygiene is half the problem. The process also has to deliver it at the moment an agent begins working. An agent opening ticket 3 on a payments spec does not start with a blank prompt. It starts with the architecture doc, the two decisions logged last week, the acceptance criteria that define done for that ticket, the fact that validation is currently clean, and the commands that let it verify its…