YHK - yet another hacker news clone

Claude Code now reads AGENTS.md if there is no Claude.md

179 points datadrivenangel 1 hour ago 71 comments

hbarka 1 hour ago | parent

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

sync 58 minutes ago | parent

nope! they're releasing something called "Claude Code mods", toted as their "upcoming way to customize the Claude Code harness"

https://x.com/trq212/status/2101009392611278961

AGENTS.md implementation is open sourced as well: https://github.com/anthropics/claude-code/tree/main/mods/age...

hbarka 32 minutes ago | parent

Nice. Thanks!

vindex10 56 minutes ago | parent

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

askonomm 56 minutes ago | parent

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

klodolph 34 minutes ago | parent

CLAUDE.md: @AGENTS.md

fphilipe 32 minutes ago | parent

    ln -s AGENTS.md CLAUDE.md

mlnj 18 minutes ago | parent

Wake up babe, new recursive self learning technique just dropped.

gcampos 7 minutes ago | parent

I tried that before, it doesn’t work. Claude will not prioritize AGENTS instructions the same way it did for CLAUDE.

ln was the only thing that worked for me

neverrroot 52 minutes ago | parent

Thanks guys, you did the right thing.

clutter55561 49 minutes ago | parent

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

jjordan 45 minutes ago | parent

Don't worry, it's on the roadmap for Q4 2029.

vb-8448 39 minutes ago | parent

They have AGI, but they don't have $20 of token budget to add a so basic functionality.

bel8 37 minutes ago | parent

They probably have an explicit instruction in their own CLAUDE.md to not implement that support.

sscaryterry 6 minutes ago | parent

Its the only explanation. I mean, they are not living under a rock...

nomel 33 minutes ago | parent

A post-checkout git hook can handle this unfortunate situation.

  mkdir -p ~/.githooks
  git config --global core.hooksPath ~/.githooks

  cat > ~/.githooks/post-checkout <<'EOF'
  #!/usr/bin/env bash
  if [ -d .agents/skills ] && [ ! -e .claude/skills ]; then
      mkdir -p .claude
      ln -s ../.agents/skills .claude/skills
  fi
  EOF

  chmod +x ~/.githooks/post-checkout

datadrivenangel 49 minutes ago | parent

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

whalesalad 45 minutes ago | parent

ln -s AGENTS.md CLAUDE.md

lolpython 42 minutes ago | parent

Fine if you don't need to git checkout the repo on Windows :)

whalesalad 41 minutes ago | parent

oh god. sorry.

Arcuru 38 minutes ago | parent

Just .gitignore CLAUDE.md and handle it locally. Checking in a symlink would be weird.

jpollock 36 minutes ago | parent

I'm surprised Git and/or Windows don't support symlinks?

whalesalad 33 minutes ago | parent

are you though?

lolpython 32 minutes ago | parent

Windows supports it but git disables creating symlinks by default.

> Short version: there is no exact equivalent for POSIX symlinks on Windows, and the closest thing is unavailable for non-admins by default unless Developer Mode is enabled and a relatively recent Windows 10 version is used. Therefore, symlink emulation support is only turned on by default when that scenario is detected. Support can be enabled by the user, via the core.symlinks=true config setting.

See: https://gitforwindows.org/symbolic-links.html

ipaddr 30 minutes ago | parent

Windows does mklink. Not surprised with git.

skeledrew 32 minutes ago | parent

Wow, still not there yet. After all these years.

pixl97 16 minutes ago | parent

Windows does actually have symlinks but I don't think I've ever seen anything actually use them, and I don't myself because it smells of interop issues with other windows apps.

Even to this day Windows has all kinds of problems around long file paths in its ecosystem.

cmrdporcupine 48 minutes ago | parent

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

Congrats.

anukin 48 minutes ago | parent

Thank you Tobi Lutke.

fhub 44 minutes ago | parent

Context

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

- Tobi Lütke on X.

TomGarden 47 minutes ago | parent

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

Time to delete the symlinks

blueaquilae 46 minutes ago | parent

Forced to do something for the users...

dude250711 14 minutes ago | parent

They have achieved AGI/RSI internally and it told them "common, let's sort this s..t out, it's embarrasing".

seaal 43 minutes ago | parent

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

sidrag22 30 minutes ago | parent

yep, all i want is freedom to make a workflow where i don't feel tied to one provider, CC is exactly what i don't wanna get trapped in. I'll happily use claude MODELS, but if it means i have to keep learning two harnesses side by side to keep using one particular provider, then the second i can easily replace it, i am going to(even if its a small drop in performance).

throwaw12 43 minutes ago | parent

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

rvz 43 minutes ago | parent

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

aroman 40 minutes ago | parent

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

dinga 39 minutes ago | parent

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

frizlab 37 minutes ago | parent

If only there was a technology that existed to link files together… /s

gberger 34 minutes ago | parent

You mean symbolically?

frizlab 27 minutes ago | parent

Good one

dinga 26 minutes ago | parent

I think it is not actually reliable the way I did it, but the idea was to have it automatically detect nested AGENTS.md

Does your tech do that?

Anyway, the joke is on me I guess, because it might not work reliably.

stillpointlab 39 minutes ago | parent

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.

cyanydeez 34 minutes ago | parent

Justba prompt change.

reedlaw 33 minutes ago | parent

Seems agents understand their own bugs now. https://github.com/openai/codex/issues/9252 has 88 thumbs up and a workaround (switch to raw mode with Alt+R) found in a comment. Codex suggested the workaround to me today when I complained about its multi-line bash command being corrupted on paste because of the two-space indent in Codex's code blocks.

nunodonato 32 minutes ago | parent

yay! /s

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

sscaryterry 31 minutes ago | parent

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

Madmallard 28 minutes ago | parent

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?

mcherm 26 minutes ago | parent

You know it because you write the content of AGENTS.md. And if you are smart, you keep it brief and cover only the important things that anyone (human OR LLM) would want to know if working in this directory.

Madmallard 21 minutes ago | parent

As far as I understand even adding relevant information still eventually clouds context

pixl97 15 minutes ago | parent

You still need to define assumptions somehow. What you want and what the model wants will not match up by default.

Madmallard 8 minutes ago | parent

In my experience telling it what I want is not a reliable process at all whatsoever if what I'm asking for is sufficiently complex, no matter what context I provide. So instead I break tasks down into very small parts, ask for solutions to those that I can reasonably quickly assess and then put them together myself. Asking it to do the architectural or deep algorithmic legwork IME wastes so much time and is often just wrong.

electroglyph 12 minutes ago | parent

do you just manually type out your important instructions every time instead of being smart and putting a few lines in a text file?

armcat 27 minutes ago | parent

About time!

getpokedagain 21 minutes ago | parent

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

mococa 21 minutes ago | parent

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

kislakiruben 20 minutes ago | parent

why did it take so long?

timcobb 18 minutes ago | parent

There goes their moat...

budoso 18 minutes ago | parent

This just be a recession indicator

rukuu001 17 minutes ago | parent

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.

davidkunz 15 minutes ago | parent

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

mitchitized 15 minutes ago | parent

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.

jtbaker 14 minutes ago | parent

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.

yieldcrv 13 minutes ago | parent

Hi, September 2026, meet September 2025

SrslyJosh 13 minutes ago | parent

Truly incredible innovation.