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

AGENTS.md – Open format for guiding coding agents

agents.md

Post reply on HN
Print view View original

291–300 of 398 posts

Re: AGENTS.md – Open format for guiding coding agents

#291

Post by stillsut »

I'm rolling my own like this [0]:

.agdocs/

├── specs/ # Task specification files

├── conf/ # Configuration files

├── guides/ # Development guides for agents

└── swap/ # Temporary files (gitignored)

Every markdown file in guides/ gets copied to any agent (aider, claude, gemini) I kick-off.

I gitignore this .agdocs directory by default. I find this useful because otherwise you get into _please commit or stash your changes_ when trying to switch branches.

But I also run an rsync script before each release to copy the .agdocs to a git tracked mirrored directory [1].

[0]: https://github.com/sutt/agro/blob/master/README.md#layout

[1]: https://github.com/sutt/vidstr/tree/master/.public-agdocs/gu...

Re: AGENTS.md – Open format for guiding coding agents

#292

Post by adidoit »

Fundamentally, AI still remains completions.

Agents, tools etc. all cover up the fact that it's completions

Still a remarkable, extraordinary technology. But the nomenclature distracts from how it works.

AGENTS.md is a great way to give context to get better completions.

Re: AGENTS.md – Open format for guiding coding agents

#294

Post by zulban »

witx wrote: post #290

This is a sad timeline. "AI is going to replace engineers.. but first please fill this human-readable markdown file to help it understand your code". What a bunch of morons, that's just called documentation. Instead of using AI where it can actually have positive impact on human lives like medicine, biology, et al. we're wasting huge amounts of resources and generating tons of pollution to teach it to program and ste…

> that's just called documentation.

Ironically you sound very optimistic about AI capabilities here. This implies that an AI is just as capable as a human because all they need to contribute is what a human needs to contribute.

Alternatively if you think AI is useless trash then clearly they need more than a human readme to do anything?

Re: AGENTS.md – Open format for guiding coding agents

#295

Post by mmaunder »

Not having support for importing files makes this dead on arrival. It means you can’t have a local file with local environment details.

There’s an issue open about this in the repo already. I mean if you’re going to copy the CLAUDE.md concept, don’t leave out one of the most useful parts.

Re: AGENTS.md – Open format for guiding coding agents

#297

Post by oehpr »

zimbatm wrote: post #289
CharlesW wrote: post #36

This should've been an .agents¹ with an index.md. For tiny, throwaway projects, a monolithic .md file is fine. A folder allows more complex projects to use "just enough hierarchy" to provide structure, with index.md as the entry point. Along with top-level universal guidance, it can include an organization guide (easily maintained with the help of LLMs). index.md ├── auth.md ├── performance.md ├── code_quality ├── da…

This should have been CONTRIBUTING.md all along. The content of the AGENTS.md is the same as what humans are looking for when contributing to a project.

The most effective argument I have for getting other developers to comment their code is "The agent will read it and it will give better suggestions".

Truly perverse, but it works.

I agree with you... but the reality is that there's a wide contingent of people that are not capable of understanding "people don't know the same things as me". So they need some other reason.

Re: AGENTS.md – Open format for guiding coding agents

#298

Post by ecb_penguin »

pmg101 wrote: post #173
ecb_penguin wrote: post #74

Earlier quoted context omitted.

> So the solution to using AI so you don't have to code, is to try to write some kind of pseudocode in AGENT.md and hope the AI does a bit better? Umm, no. Where did you get that idea? The purpose of the agent.md file is to give it instructions. Nothing about no-code AI said there would be no instructions...

I'm old enough to remember when computer code was called "instructions". Eg, the 6502 instruction set. https://www.masswerk.at/6502/6502_instruction_set.html History doesn't repeat but it rhymes!

They are still called instruction sets.

> History doesn't repeat but it rhymes!

The only similarity is the word

Re: AGENTS.md – Open format for guiding coding agents

#299

Post by jcmontx »

adidoit wrote: post #292

Fundamentally, AI still remains completions. Agents, tools etc. all cover up the fact that it's completions Still a remarkable, extraordinary technology. But the nomenclature distracts from how it works. AGENTS.md is a great way to give context to get better completions.

"Computing is just 1s, 0s and logic gates"

Re: AGENTS.md – Open format for guiding coding agents

#300

Post by esafak »

oehpr wrote: post #297
zimbatm wrote: post #289

Earlier quoted context omitted.

This should have been CONTRIBUTING.md all along. The content of the AGENTS.md is the same as what humans are looking for when contributing to a project.

The most effective argument I have for getting other developers to comment their code is "The agent will read it and it will give better suggestions". Truly perverse, but it works. I agree with you... but the reality is that there's a wide contingent of people that are not capable of understanding "people don't know the same things as me". So they need some other reason.

They understand it just fine; they are acting selfishly, because it does not benefit them. Helping the coding agent does.
Post reply on HN