I feel like claude.md is like Asimov's laws of robotics. Whatever you write there ends up eventually messing up everything.
My agent.md to improve LLM-assisted code quality
31–40 of 200 posts
Re: My agent.md to improve LLM-assisted code quality
#32A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters. Then this one really is a pattern that creates a lot of churn: - Add a small, to the point, comment to explain what the block does and why . Use examples when possible. Propose ASCII drawin…
Re: My agent.md to improve LLM-assisted code quality
#33A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters. Then this one really is a pattern that creates a lot of churn: - Add a small, to the point, comment to explain what the block does and why . Use examples when possible. Propose ASCII drawin…
My biggest pet peeve with agents is when people beg their (non-deterministic) agents to do something that a lint rule could've accomplished
Which is kind of cool if you’re unaware enough to know to do it yourself.
Oh, and find. Agents use find a lot.
Re: My agent.md to improve LLM-assisted code quality
#34I've been seeing the same thing with models like GPT5.6 and Opus4.8 in GH Cop CLI. They still introduce magic numbers, and in Scala they often put an entire 10-line Spark expression inside an if condition instead of extracting it into a meaningfully named value to keep "if" readable. I wonder when common sense instructions will be baked into the models.
Re: My agent.md to improve LLM-assisted code quality
#35Earlier quoted context omitted.
I would never tell an agent to write "what does the code do" comments. Their default comments are already way too fluffy.
I added to the memory, system prompts, and the prompt itself and every soa model still litters code with the most inane useless crap. I will then get code to review from a coworker using fable/opus. It has more lines of comments then code. Maybe I am some god tier code reader (i am not) but i dont think i have ever found a comment in code to be useful in my day job. That isnt true, i once came across // submit to the…
“”” After you give up on trying to refactor this code, increment the following line accordingly. HOURS_WASTED_HERE=26 “””
Re: My agent.md to improve LLM-assisted code quality
#36A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters. Then this one really is a pattern that creates a lot of churn: - Add a small, to the point, comment to explain what the block does and why . Use examples when possible. Propose ASCII drawin…
With the mechanical routes, we get checks, failures, and so much more. A bit wild to me.
Make an agent operate within defined constraints and yell at it when it doesn’t.
Re: My agent.md to improve LLM-assisted code quality
#37Since we are sharing our AGENTS.md, I thought I'd share my own, because most of the time, this is pretty much all you need for LLMs to write good code, everything else can be added per project: ---- *Convergence rule* Every substantial task must end in exactly one of three states: A. Success The intended capability works in the real path and the real motivating case materially improves. B. Meaningful progression The…
Re: My agent.md to improve LLM-assisted code quality
#38A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters. Then this one really is a pattern that creates a lot of churn: - Add a small, to the point, comment to explain what the block does and why . Use examples when possible. Propose ASCII drawin…
Re: My agent.md to improve LLM-assisted code quality
#39A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters. Then this one really is a pattern that creates a lot of churn: - Add a small, to the point, comment to explain what the block does and why . Use examples when possible. Propose ASCII drawin…
LLMs are very bad at ASCII drawings.
https://medium.com/data-science/why-llms-suck-at-ascii-art-a...
Re: My agent.md to improve LLM-assisted code quality
#40A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters. Then this one really is a pattern that creates a lot of churn: - Add a small, to the point, comment to explain what the block does and why . Use examples when possible. Propose ASCII drawin…