Release notes for Claude Code, including new features, improvements, and bug fixes by version.

741 points•datadrivenangel•12 days ago•285 comments•

285 comments

deaux12 days ago
It took the Shopify CEO tweet and Astra causing a large move towards Codex for them to finally give in. It's hard to believe it was worth it in the end. On the other hand, most people will forget about this saga in a few months, so sadly it may just have been worth it.
derwiki12 days ago
What was the Tobi tweet?
perganomoly12 days ago
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.
thiht12 days ago
That’s a strong opinion for a mild inconvenience that’s trivially solved with a symlink
athrowaway3z12 days ago
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.

arendtio10 days ago
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.

chrisandchris12 days ago
We have a CLAUDE.md file whose only content is "please read .agents/agents.md"
yjftsjthsd-h12 days ago
Wouldn't symlinking it be faster and use fewer tokens?
x______________12 days ago
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?

pampas11 days ago
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.

arceister12 days ago
it's been a standard practice on open source projects, right? CLAUDE.md only have one sentence "read ./AGENTS.md", lol.
dainiusse11 days ago
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
LeoPanthera12 days ago
If you don't use Claude anymore, why do you care?
perganomoly12 days ago
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.

fragmede12 days ago
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.
NullifyNAN11 days ago
Yet it took Codex 8 months to get subagents after their introduction in claude code. This of course pales in comparison to having to symlink CLAUDE.MD to AGENTS.MD
stillpointlab12 days ago
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.

reedlaw12 days ago
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.
saghm12 days ago
Fable didn't want you to blame it for the limitations its creators gave it
cyanydeez12 days ago
Justba prompt change.
Frannky11 days ago
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.

desipenguin11 days ago
Do you mean oh-my-pi (omp) (https://github.com/can1357/oh-my-pi/)

I also use the same. But I use Anthropic models (Opus 5) with it.

Frannky11 days ago
yes
clutter5556112 days ago
Don’t get too excited, Claude code still won’t detect skills on .agents/skills.
vb-844812 days ago
They have AGI, but they don't have $20 of token budget to add a so basic functionality.
bel812 days ago
They probably have an explicit instruction in their own CLAUDE.md to not implement that support.
NiloCK12 days ago
Artificial General Intransigence
perganomoly12 days ago
Seriously, it’s unbelievable. Shows a serious lack of either understanding or empathy for how people use their product.
arendtio10 days ago
Claude isn't that cheap anymore ;-)
nomel12 days ago
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
springtimesun12 days ago
This is where I landed when a recent(ish) change broke symlinking for rules files. I didn’t like how hacky it was a first, but now I’m glad I did it. The same hook drives specific rules the non-Claudes get per repo.
ahurmazda12 days ago
Won’t you have to do it recursively for all child directories?
verdverm12 days ago
we shouldn't have to do this on a per-repo basis, Ant can choose to be a reasonable member of the ecosystem or not
jjordan12 days ago
Don't worry, it's on the roadmap for Q4 2029.
Sugimot012 days ago
I honestly hate .agents it's a big XDGBDS offender. Almost every plugin / lazy platform harness tries to use that dir too so I have to do a bunch of hacks to keep my $HOME clean. Also everyone tries to use a .claude .gemini .codex etc. Annoying that all these tools just completely ignore these things, it's literally like litterers you know it'd be terrible if every tool did this, but you still do it anyway

Read the full thread on Hacker News →

Related stories