The fact that it took this long to add such a basic feature is a disgrace. I’m not even remotely satisfied. Bailed on Claude ages ago. Rolling Codex, Gemini, and Qwen3.8 30B. The only way I’m going back to Anthropic is if they drop and Culture Series mind.

I switched to oh-my-py and never looked back. I guess having an incentive to maximize (expensive) token usage, and LLMs degrading with higher context, isn't aligned with a user's best interest.

Oh-my-py unlocks max capabilities at the smartest token usage, and you can change AI company and providers while still getting things done. Roles, advisor, and the ability to use Chinese models on international providers with no training and ZDR behind OpenRouter are very powerful. You can have providers and model companies competing on price, intelligence, and speed for something that's useful but with less and less moat as model progress plateaus.

I now use GLM 5.3 for slow/planning, GLM 5.3 Flash as the default task-vision model, and DeepSeek Flash 4.1 as the advisor. Providers are ordered by cheapest at the minimum TPS I want for that model. I use it not only for coding but also as a personal assistant. I can ask it things and it gets them done automatically, like opening an issue on a repo, then having another agent ship the code, run the tests, and update master after having changed the app to autoupdate on cut release.

I can also ask it to do groceries. I use Bitwarden machine secrets and a limited virtual card connected to my phone.Something else that's very powerful is asking it to launch parallel agents to do things you know don't overlap too much.

The amount of agency we're gifted with is crazy, you can now move hundreds of hours of work with one hour of input using an open-source harness and open-weight models. I can't wait for more competitors in the chip space, and to be able to buy models etched on silicon for even higher agency, speed, and independence.

I recently had Claude Fable set up a new project for me and I pointed it at some existing projects to use as a guide on how I like to structure things. It created, unprompted, an AGENTS.md file and a CLAUDE.md symlink to AGENTS.md

I didn't even have that symlink in any other project - it just did it. I think it saw that one of the projects I already had was set up by Codex and that project had an AGENTS.md so perhaps it inferred that I was using both Claude and Codex, so it was politely covering both? Or maybe a recent change made this behavior default?

I was surprised and I hope they continue to seek standards.

Don’t get too excited, Claude code still won’t detect skills on .agents/skills.

Remember they didn't do this because they wanted to help community, they did it because community was angry and they were losing users to other harnesses.

Doesn't look like Anthropic care about dev community

Once I asked, puckishly, Claude Code to “follow the instructions in this directory” when there was only an AGENTS.md there.

In the manner of someone finding a dead mouse and holding it up for examination CC said it could find no instructions but perhaps it should check this AGENTS.md file.

CC is such a bloated POS by this point that only full on AGI could have implemented this feature. Congrats guys. Maybe with Super Intelligence they will be able to make it actually respect the instructions in there too.

Claude Code wraps both the AGENTS.md and CLAUDE.md in a system-reminder with this disclaimer at the bottom:

IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.

Codex follows the AGENTS.md far better. CC seems to have nudged people away from taking the CLAUDE.md as mandatory instructions.

This bug was closed Not Planned and from a recent analysis of the system prompt the behavior is still there even with the new inclusion of AGENTS.md.

https://github.com/anthropics/claude-code/issues/18560

What worked well previously was to have the Claude.md file contain just "@AGENTS.md".

But this is a good change.

The world of managing skills between providers still feels messy though.

This is simply the obvious, non-stupid thing to do, like Apple switching to USB-C.

This just be a recession indicator

BTW if you hate these Antrophic moments but still want to use CC, you can patch it: https://github.com/Piebald-AI/tweakcc

Claude also checks your settings.json first, and if it sees a default there it then prefers that over anything in CLAUDE.md. This is particularly nefarious as they ship logic to presume a default if a setting is not there in settings.json, even if there are instructions in CLAUDE.md for exactly that.

For instance, say you added "do not add 'Made with Claude Code' in any issues, pull requests or wiki entries" in your CLAUDE.md. So far, so good.

Well the latest update now looks for something in your settings.json. Since you don't know about it, it is not set. Claude then says "not explicitly set, so now it is true by default". It completely ignores your CLAUDE.md.

Wait, what?

You shouldn't be shipping logic that arbitrarily redefines the behavior of the program, especially if your new logic actually ignores your own configuration or directives.

LOL https://thenewstack.io/shopify-claude-code-agentsmd/

> “I’m thinking about banning Claude Code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc.,” Lütke posted Tuesday on X.

Caught myself about to praise this, but it's the absolute bare minimum.

Time to delete the symlinks

I couldn't care less what the filename is, I do care however that Claude still forgets about 14 times per week that -r with ripgrep means replace (and not recursive, like with grep). Even though it's literally spelled out in my CLAUDE.md. Claude code, even with the most advanced models, forgets or disregards very simple and clear instructions from my modestly sized MD file.

Still can't read what their models vomit at me.

The madlads finally did it, now if only I could use my Claude sub in other harnesses without risking getting banned.

My claude.md:

# CLAUDE.md

This project uses `AGENTS.md` as its agent instruction file (kept provider-agnostic). Treat any `AGENTS.md` file exactly as you would a `CLAUDE.md` file — at the root level and in any subdirectory you are working in.

@AGENTS.md

Meanwhile, I just setup codex for the first time (to try Astra) and it offered to load my Claude and Cursor conversations and claims to even do it in a way where it says in sync if you use both. The only reason to use Claude Code is the 20x usage of the 200$ plan is ridiculous value if you have the need for that volume.

Finalllyyyy!! We need industry wide standards. I come from the 3d industry and oh god changing softwares and adapting to different hotkeys it's a pain. I have always thought every industry should be standardized for the sake of the users.

The fact that something like this is so widely celebrated shows just how user hostile anthropic has become.

Finally doing something standards-compliant instead of forcing users into a proprietary workflow.

AGENTS.md is the new autoexec.bat.-

This is not a news to celebrate, they must follow standards

I wonder when they'll finally fix the VS Code plugin to not constantly dump your current file into the context.

Oh, finally! Time to delete symlinks

That said, AGENTS.md doesn't seem like a good name, right?, technically, it's an instructions file read by a single agent, not necessarily for agents, so it always struck me as a bit odd

But until the next standardization, keeping just AGENTS.md is the best approach.

Better late than never... Now it's time for Claude Code to load skills from .agents/skills!

Finally, I can delete `sync-agent-docs.sh`, which recursively symlinked AGENTS.md to GEMINI.md and CLAUDE.md...

undefined

Thanks guys, you did the right thing.

I gotta hand it to programmers (or whatever we call ourselves now) for sticking to principle on something this trivial.

It was either this or Claude had to become a generic term like sheetrock.

Gotta say, it is hilarious that this is the current top HN post. I feel like it's gotta say something about our current AI zeitgeist, that there is such vigorous attention on a seemingly-minor change. Feels like something is on the tip of my tongue but I can't name it at the moment.

If anyone wants to write/link a much better-thought-out post, I'm all ears!

Just to touch on the wording of "in a project with no CLAUDE.md" does that mean user-level ~/AGENTS.md or ~/.agents/AGENTS.md isnt supported?

I wonder if Anthropic's vending machine only serves customers wearing a Claude™ branded hat.

Wow..... Progress and technical innovation right here!!!

Thank you Tobi Lutke.

Genuine question: Does the Agent harness matter ? I mean why use Claude CLI ?

(As I mentioned elsewhere) I use oh-my-pi (and opencode, and toad) but use (client paid) Opus 5 with these harnesses.

All three of these understand AGENTS.md

Wild that it didn’t already do this

This allows us to remove our one line Claude.md files that just say "AGENTS.MD"

undefined

First feature to borrow after peaking into openai repos? ))

Commoditization commoditizes commodities.

Hell froze over?

finally! Now this might sound sorta off-topic but i really wonder how people feel about skills.md, skill.md, skills.sh domains...

the fact that they're owned by different companies (ok vercel is a little less random) still leaves me with a sour taste in my mouth when thinking about the fact that they should all point to 1 place about how to create and find skills for ai agents?!

Before anyone even contemplates if Anthropic has any good intentions, remember, this is how petty and small minded they are.

Truly the last people you want with this kind of power.

Forcing their own proprietary filename was clearly a business decision (it's free advertising, along with commit co-authorship). I wonder what made them go back on it.

Truly incredible innovation.

great, one less step for me.

I was using my claude.md file as a pointer to my agents.md file

Only took them a year and a half of everyone complaining to finally do the right thing.

Congrats.

Everyone sharing the 513 ways you can already do this is entirely missing the point. Standards matter and there's very few things in the AI world everyone agrees on and this is one of them. .agents/skills is another and anthropic is still holding out there.

undefined

Great. Now if they could support the `~/.agents/skills` path next like everyone else does that would be even better.

Great, now I have to redo my scaffold harness. I guess this agent.md awareness is part of the system prompt?

Sanity prevails

Anyone have a good guide on properly setting up/optimizing local llm stuff like this?

I've been using omlx and qwen for almost a year but have bounced around clients a bunch, and it seemed like everything was specific to claudes style of config layout, so I've been putting all of my skills/agents/md files in my ~/.claude as a catchall for bouncing between pi.dev/claude/vscode/etc. and just seeing what happens. I really haven't used claude itself much so reasonable but I didn't know it didn't look at AGENTS.md, for instance. Also using some memory/kb system that puts $myKB.md in directories to pre-fill context by project/workspace.

I'm currently using oh-my-pi but in the quest for optimization and token trying to get better than 30t/s on my m1 max 64gb (qwen3.6-a35b) I probably need to spend some time just making pi base into what I need and not the opinionated omp setup I have that probably makes the initial context larger than it should be.

I'm between work and can't afford the $100+ frontiers but it does get really frustrating spending hours/days tweaking this stuff to almost no benefit sometimes. When I do get to use a frontier it's such a nice break from fixing things. The local llm stuff can definitely be a bit frustrating right now and zap the energy I have for work out of me when it goes awry.

Can it read copilot.md if neither of the other files are present? Also: agents should be the standard, or we need to invoke the XKCD for "one more standard to rule them all"?

Thank Christ

didn't it always read it?

I just wiped all agents and it’s always readme.md

So far I've been managing this with a symlink.

Same with skills, symlink to skills at .claude/skills

Great, now please standardize the skills folder and the MCP config.

About time!

Hi, September 2026, meet September 2025

Still don't understand the point of the markdown files.

Isn't it literally all just more text you're adding to the prompt. How can you even be sure it isn't just clouding context with nonsense for whatever you're asking for?

undefined

Forced to do something for the users...

why did it take so long?

Ah yes, the peak of technology.

Now do skills

Finally.

Now is the time to git mv CLAUDE.md AGENTS.md.

A reminder that needs to be said: Don't use a closed-source harness.

Why? This is why. [0]

[0] https://news.ycombinator.com/item?id=49750694

[flagged]

[flagged]

[dead]

[flagged]

[dead]

[dead]

[dead]

[dead]

[dead]

yay! /s

Why are people still putting up with this kind of attitude, especially when there are so many good alternatives available?

[flagged]

People still use Claude?