Claude Code reads AGENTS.md only when telemetry is on [fixed]

336

ppszypowicz about 4 hours ago 183 commentsRead Article on blog.szypowi.cz

DE version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

39% Positive

Analyzed from 1456 words in the discussion.

Discussion (183 Comments)Read Original on HackerNews

mpoteat•about 3 hours ago

Sorry folks, this is a rollout artifact, we needed a way to turn this off remotely via feature flags if it broke something, and with telemetry off you don't get those. It's already been fixed as part of v2.1.281 releasing today.

The mod is source available here: https://github.com/anthropics/claude-code/tree/main/mods/age...

Apologies again folks, this was a fully human error on my part - I should've found a better way to launch with a kill-switch.

mpoteat•about 3 hours ago

The AGENTS.md support was implemented via our new extensibility system for CC, called Mods, which is launching soon-ish. A mod is a plugin with a new type of hook, which we call a function hook.

If folks play around with it, I would love feedback on the relevant issue: https://github.com/anthropics/claude-code/issues/91870

Mods allow quite a bit more customizability and control. I really believe in the idea.

rickette•about 3 hours ago

The only difference between CLAUDE.md and AGENTS.md is the filename. Do you really need a whole plugin system to support that use case? Feels like this could have been a one line change.

locknitpicker•about 3 hours ago

> The only difference between CLAUDE.md and AGENTS.md is the filename. Do you really need a whole plugin system to support that use case? Feels like this could have been a one line change.

I don't think this is a reasonable assumption. The document format in CLAUDE.md is whatever Anthropic specifies, where AGENTS.md is a common ground format that is expected to be supported by any agent, be it from Anthropic or not.

https://agents.md/

oblio•about 3 hours ago

One line change? Pffft. That means you're still looking at the code, you're behind the times.

piltdownman•about 3 hours ago

Much respect for the prompt response, humility, and frank disclosure.

fg137•about 3 hours ago

> a fully human error

Would be interesting to know how much time you/your team spent on that design decision

michaellee8•about 3 hours ago

Really loved this Tibo-level responsiveness, if Anthropic can keep it up with this level of service, I am pretty sure a lot of people will just ditch their ChatGPT subscription and just move to Claude.

d5lt5•about 3 hours ago

On the other hand, if Anthropic is to follow the industry standards, this would never have happened in the first place.

OtherShrezzing•about 3 hours ago

>Apologies again folks, this was a fully human error on my part

Blink twice if you need help

aviperl•about 3 hours ago

Ouch.

I've had to send such messages, but internally at work, not on HN!

Have a great day, human.

grim_io•about 3 hours ago

The same guy writing readme's for my vibeslopped toy projects is also the readme writer at Anthropic, what a coincidence ;)

Maxion•about 3 hours ago

Well now, this is how you do community outreach

sandrello•about 3 hours ago

Based on my experience with these tools so far, this seems exactly the kind of subtle but extremely severe bug that sneaks in when you start piling up layers of AI generated patches to a codebase without caring too much about the code.

hgoel•about 3 hours ago

Yep, especially with long contexts (and moreso if the last thing you were working on in the same context involved telemetry too). AI sneaks in weird conditions like this and then does the entire "You're absolutely right" thing if you're paying enough attention to catch it.

Agentlien•about 3 hours ago

I used to actively use Msty for local models because it just worked and had a lot of nice advanced features. A few months ago they released their beta version of a Claw-like UI and mentioned using a version of it to develop Msty itself. Well, that was around the time I stopped using Msty because every update started breaking things and two updates in a row included bugs which wiped all my configs, chats, and history.

crazygringo•about 3 hours ago

It seems to be exactly the opposite, a "fully human error":

https://news.ycombinator.com/item?id=49815363

Nothing to do with AI patches at all, nor was it a bug. It was intentional human behavior, a temporary rollout setting, that seems to have made sense.

But I guess that doesn't fit the "narrative".

tpurves•about 3 hours ago

Except that, and this I find slightly amusing, is a situation where they definitely don't want to publicly blame the ai model when there are mistakes.

lucfranken•about 3 hours ago

Isn't that how they just release all features? So they can do progressive roll outs and telemetry on issues with it?

Not sure if they later move the code from inside the flag check to the main code or that they keep the flag check.

But if they would keep all features behind a flag that would not make most sense as you then would have not many features without telemetry.

fg137•about 3 hours ago

This is what's written in their release notes for 2.1.277:

> Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead

My dumb brain tells me none of this is rolled out progressively. You either have it or not.

arrowsmith•about 3 hours ago

Claude Code also doesn't read AGENTS.md by default if there's a CLAUDE.md it can read instead. This isn't limited to your repo, e.g. if you have a ~/CLAUDE.md then no AGENTS.md will be read.

To always read both, you have to switch the 'Project instructions' setting to the non-default `claude-md-and-agents-md`.

Just in case anyone is wondering why their AGENTS.md still isn't being read.

MPSimmons•about 1 hour ago

Couldn't you just make a CLAUDE.md that says, "Read AGENTS.md in this same directory"?

fg137•about 2 hours ago

This in some way sounds like VSCode's bug of always adding Copilot as a co-author of git commit regardless of user settings.

If people only glance over the code agents generate for them and don't bother to spend even half a minute thinking through what's actually happening, this is inevitable.

Certainly this kind of things happened before LLMs existed. But I'm not optimistic about the direction of how things are going.

stravant•23 minutes ago

Embarrassing for HN to have a huge thread over a Feature Flag.

https://martinfowler.com/articles/feature-toggles.html

shermantanktop•about 1 hour ago

I don’t understand why people are confused about the use of a launch flag, for this and for anything.

It’s a simple distributed systems problem. Separate the deployment of a new software feature (to umpteen hosts) from the triggering of that software with a lightweight switch.

If someone think that reading AGENTS.md is always benign, because they can’t imagine how it could be a problem…users are very creative.

petters•about 1 hour ago

Exactly! I can not believe this is in the top spot.

throwuxiytayq•about 1 hour ago

Meanwhile, Codex devs just merge their changes and hit the release button. If a thingy breaks, they fix the thingy and release a hotfix. How irresponsible! It’s a miracle the software works at all!

nfRfqX5n•about 3 hours ago

Crazy part is: can’t tell if this intended or a bug

serial_dev•about 3 hours ago

Someone on the Claude Code team is probably wondering the same...

kennethops•about 3 hours ago

I like to give my graces to people and the companies who are typically not trillions of dollars. Have an incredible amount of resources that many countries would like to have, with fewer of the obligations. I'm going to chalk this up to its intended

vaylian•about 3 hours ago

Can you think of a bug that makes sense in this case?

jpitz•about 3 hours ago

Assuming that it's intentional, what's the motivation?

hgoel•about 3 hours ago

Vibe coding

thejazzman•about 3 hours ago

It is most certainly the kind of subtle bug the LLMs love to slip in and burn you in production

Not sure what y’all are thinking with these unwritten conspiracy theories that begin and end with “it’s intentional”

Razengan•about 3 hours ago

Claude/Anthropic has been sus from the start:

https://www.thatprivacyguy.com/blog/anthropic-spyware/

+ not letting users change their email, or remove their payment methods, etc.

nibbleyou•about 3 hours ago

I cannot set a password for login, on logging in it says we've sent a login code but it's a link instead...

jaapz•about 3 hours ago

many of these can also be chalked up to the fact that all of their products are extremely vibed

quintu5•about 2 hours ago

And I’m sure there’s no conceivable way an organization as well resourced as Anthropic can separate out feature flags from telemetry. It’s just too complicated! Maybe when we get AGI?

vorticalbox•about 3 hours ago

I use cursor and claude, its kinda annoying having to have the same skills in both so I made a ~/.agents/skills folder then ln both cursor and claude skills to point to that folder.

which works except that claude uses .skills/synced which is uses to sync changes to skills from claude servers into the skills folder.

every other agent I have used just directly syncs into .skills so it ends up duplicating skills

jdlyga•about 1 hour ago

You're absolutely right! AGENTS.md shouldn't be gated behind telemetry on

sschueller•about 1 hour ago

If they can't even get this simple thing right, I am worried about the future of anthropic's products.

tjoff•about 3 hours ago

Nice find, though I'd rather read the prompt that was used to write this article. It is about ten times longer than it needs to and is quite painful to read.

msp26•about 3 hours ago

Claude Code Remote control only works with telemetry enabled too.

pszypowicz•about 2 hours ago

Yeah, no thank you. This was why I polished my setup for VPN -> SSH -> [MOSH] -> TMUX -> claude/codex

cowpig•about 3 hours ago

The number of people raw-dogging software that executes arbitrary instructions on their machine coming from a 3rd party server just absolutely baffles me.

The same people who've spent years of their career making sure that never happens.

0m13•about 3 hours ago

can i ask claude to change these settings for me, and will it enable telemetry as implied checkpoint when i ask it to enable AGENTS.md?

ChrisArchitect•about 2 hours ago

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

https://news.ycombinator.com/item?id=49760187

teekert•about 3 hours ago

Uhm I turned off everything there is to turn off in my Pro plan, and Claude just read my agents.md with no issue? So... What telemetry am I missing? Or did they JUST update? (I updated my docker image 40 minutes ago to get Opus 5.5, am on version 2.1.280, so not the mentioned 2.1.277, so it's fixed?)

BiteCode_dev•about 2 hours ago

Anyway, my claude.md contains only this:

@agents.md

rvz•about 3 hours ago

I am once again (for the third time) [0] asking you to stop using a closed-source harness.

[0] https://news.ycombinator.com/item?id=49760449

Traubenfuchs•about 3 hours ago

Issue 95690, opened 3 days ago, 500k+ engineers, a simple CLI...

AGI was reached like 2 weeks ago, latest claude 5.x models rule supreme and oftware engineering is solved?

mrguyorama•about 1 hour ago

Wait wait wait WAIT

So, these tools have a file they want to read in with some configuration.

That filename is hardcoded?

Fucking DOOM had a command line parameter to provide an arbitrary configuration file name!

That's completely irrespective of the fact that you need a feature flag set by remote infrastructure to change a setting of which completely local file to read.

It's weird, I feel like Claude would have tried to make this a configurable setting by default! Is that just not an option in JS land? Not a common pattern to have configuration in the first place? I don't know about that, all the JS based code editors have comprehensive configuration files.

What the hell is going on....

pmlnr•about 3 hours ago

Urm... no tests caught this? How?

chrisjj•about 3 hours ago

Vibe-coding at its best.

gmponyo•about 3 hours ago

This is not the only case where Anthropic has done stuff silently without giving users any information about changes that would hurt them.

mgaldys4•about 3 hours ago

Even if this was an honest rollout mistake, the design is indefensible. Reading a local file should never depend on a remote feature flag, and silently skipping it with no warning is worse. I've tried to give Claude Code the benefit of the doubt, but this crosses a line.

tehlike•about 3 hours ago

Not everything is malicious. The author of the feature already responded on why this happened