That’s a strong opinion for a mild inconvenience that’s trivially solved with a symlink

Its indicative of a pattern of behavior where they want to upsell you into their ecosystem and keep you there.

They don't even allow alternative harnesses on their subscription model. (But they do allow a agent-sdk that can pretend to be a generic compatible endpoint the alternative harnesses can use).

If you like your stuff overengineered, gated, and over-priced then by all means.

Its not even wrong from Anthropic because it's the path to most profit.

I'll take the opinion of people who have strong opinions about mild inconveniences.

Between my goals and Anthropic's bottom line, i want my goal to win out without needless inconveniences.

These arguments have nothing to do with Claude supporting or not supporting AGENTS.md.

> Its indicative of a pattern of behavior

If you think I'm wrong, and these arguments have nothing to do with it, just tell us what explains Claude not supporting AGENTS.md.

Was it such a grand engineering challenge? Too many 'legacy' projects relying on both AGENTS.md/CLAUDE.md and that has recently changed?

I've made clear my belief on the reason behind it - branding decisions outweighing utility.

Add something to the thread by sharing your version of a 'more likely' decision process that led to the choice to only now support it.

not that i agree, but this is what an anthropic engineer said about this:

> Our reasoning for this was that we don't think that model families are interchangeable and the system prompt can have a big impact on performance.

https://x.com/trq212/status/2092302273099796842

Bad take. You should feel bad.

This kind of comment doesn't belong on hacker news.

I think the problem is deeper. I mean, calling it claude.md in the first place is weird, and not adopting agents.md causes the ecosystem to fracture.

Sometimes, Anthropic has pushed standards (MCP, Skills), and that is great, but other times they have explicitly built incompatibilities. With the Plug-in marketplaces, it is quite similar.

We have a CLAUDE.md file whose only content is "please read .agents/agents.md"

Wouldn't symlinking it be faster and use fewer tokens?

I did that but not necessarily.

When prompted to write to it, it will always try to write into the Claude.md and error out with that approach.. It eventually figures it out, but it's a ymmv situation I think

It also works more reliably. I've tested this quite a bit. Instructions in files referenced via CLAUDE.md are more likely to fall out of context or to be ignored. Raw project level CLAUDE.md instructions are the second most durable available as far as I know. I used to have a "well organized" hierarchy of rules and instructions. Collapsing all of that into CLAUDE.md + skills made things far more predictable and "as instructed".

Maybe I'm not up to speed but i deleted claude.md while testing weird opus 5 behaviors, it came back saying nothing was used in claude.md but rather storing context in memories.md in some .claude/projectname/memories folder in my user profile....

How is agents.md and different? Just a standard for other models? Is claude the lower standard now?

Everyone does. But I think you're missing the point. It's effectively a billboard in the root of your repo.

Sent from my iPhone.

it's been a standard practice on open source projects, right? CLAUDE.md only have one sentence "read ./AGENTS.md", lol.

Imo it is a sign they got beaten by astra. Competition drives it. I didn't try astra pro, but even the regular beats fable 5, not to talk about opus

If you don't use Claude anymore, why do you care?

Because I care about products, their communities, and how company’s treat customers.

I was quite annoyed with Claude earlier this year when I had to maintain duplicate files or rely on symlinks.

Seemed like a waste of time simply because Anthropic didn’t want to take the “L” and accept that AGENTS.md was the new standard.

IMO, this kind of product decision making is why so many products either suck, or they’re are good but not great … and users have zero loyalty.

I find it super annoying this building lock in instead of loyalty approach to product seems to be standard practice these days.

Because other people do, and those people previously would have CLAUDE.md files in their repos and not AGENTS.md files. When you have to work with them and their repos, you were forced to deal with the difference.

Isn't "deal with the difference" just renaming the file?

symlink CLAUDE.md to AGENTS.md

> Qwen3.8 30B

404

You’re right. Just checked LM Studio. It’s actually 3.8 27B. Got it confused with the 30B coder model that I’m playing with, too.