I like the idea of a LOC limit on projects, but it's hard to implement. Avoiding feature creep is good, but so is increasing test coverage.
miniblog.
Related Posts
I've now worked on several systems where the JSON was so big that avoiding pretty-printing was a performance win!
I do occasionally find myself wanting to use the phrase "you're absolutely right", especially in technical discussions.
I've started avoiding it though. I worry it'd make me sound like I'm just automating my comments.
I've realised that AGENTS.md / CLAUDE.md solve two distinct problems:
* It tells the LLM the conventions of the project, avoiding follow-up prompts.
* It precomputes a summary of the project, saving a bunch of searches at the start of a session.