YHK - yet another hacker news clone

Claude Code reads AGENTS.md only when telemetry is on

85 points pszypowicz 50 minutes ago 25 comments

nfRfqX5n 31 minutes ago | parent

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

vaylian 22 minutes ago | parent

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

hgoel 21 minutes ago | parent

Vibe coding

thejazzman 14 minutes ago | parent

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”

jpitz 20 minutes ago | parent

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

kennethops 20 minutes ago | parent

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

serial_dev 18 minutes ago | parent

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

Razengan 18 minutes ago | parent

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.

chrisjj 30 minutes ago | parent

Vibe-coding at its best.

tjoff 19 minutes ago | parent

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.

sandrello 18 minutes ago | parent

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 12 minutes ago | parent

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.

Traubenfuchs 16 minutes ago | parent

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?

lucfranken 15 minutes ago | parent

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.

vorticalbox 14 minutes ago | parent

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

0m13 13 minutes ago | parent

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?

rvz 12 minutes ago | parent

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

teekert 10 minutes ago | parent

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?)

mpoteat 9 minutes ago | parent

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.

piltdownman 8 minutes ago | parent

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

mpoteat 4 minutes ago | parent

The AGENTS.md support was implemented via our new extensibility system for CC, which is launching soon-ish.

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.

mgaldys4 6 minutes ago | parent

This is beyond comprehension. Claude Code lately just comes across as hostage-taking, forcing users into absurd rules. I have tried hard to give it the benefit of the doubt. This is too much. It is basically poisoning the code.

arrowsmith 5 minutes ago | parent

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.