Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My agent.md to improve LLM-assisted code quality

fabiensanglard.net

Post reply on HN
Print view View original

21–30 of 200 posts

Re: My agent.md to improve LLM-assisted code quality

#21

Post by formerly_proven »

anygivnthursday wrote: post #13
FooBarWidget wrote: post #11

Earlier quoted context omitted.

No, why should I have to remember to @ in every prompt? Or ask contributors to remember. It just makes it easier to make human mistakes. I have better things to do than micromanagement. There is huge value in auto-included context.

The GP wrote @ it from the agents.md file, not from the prompt. Their point was that instead of writing "how to contribute" instructions for agents, you could explain that in the CONTRIBUTING.md and link it from your agents file, so both humans and agents read it from one place.

Symlinks exist, but it's kind of ridiculous all harnesses just ignore CONTRIBUTING, HACKING and friends.

Re: My agent.md to improve LLM-assisted code quality

#22

Post by dan_ggggg »

bellowsgulch wrote: post #9

I've read a few of these over the years, and none of them seem to be useful. I have three sentences in my custom instructions, and those are basically all useless, too. Even my second one, "Avoid decorative or section-header comments. Never use `----` or `====` as comment separators. Comments should explain only non-obvious behavior, rationale, constraints, or implementation details." seems to be ignored by models re…

[flagged]

Re: My agent.md to improve LLM-assisted code quality

#23

Post by rustystump »

getnormality wrote: post #4
OptionOfT wrote: post #3

A 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…

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 dark lord

Above the function that sent a payment to PayPal for processing. It made me laugh so I let it be.

Re: My agent.md to improve LLM-assisted code quality

#24

Post by mattjoyce »

oumua_don17 wrote: post #6

Just this one line in AGENTS.md has given better results to reduce if not eliminate verbosity and grandeur. **Always use ASD-STE100 Simplified Technical English Disclaimer: I saw this listed in some other HN post that I can' locate right away.

This will produce quite verbose prose. STE100 is good for specs and explanations but it works best with a glossary or terms. will burn tokens.

Re: My agent.md to improve LLM-assisted code quality

#27

Post by maccard »

YuechenLi wrote: post #12

Since 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…

How often would you say step C happens and the agent stops when it can’t proceed?

Re: My agent.md to improve LLM-assisted code quality

#28

Post by latchkey »

this was what i was doing 3-4 months ago. i just have AI write/update my agents.md file now as i find problems. i also have ai keep a set of design documentation that it can update as it goes too. oh and he should try omp+codex/xhigh, he will probably be less annoyed.

Re: My agent.md to improve LLM-assisted code quality

#30

Post by culi »

OptionOfT wrote: post #3

A 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
Post reply on HN