Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs • Hacker News Board

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#131

Post by stavros » Wed, May 27, 2026, 1:46 PM UTC

notachatbot123 wrote: post #32

stavros wrote: post #27

Earlier quoted context omitted.

Because you're better able to take over the codebase a local model wrote than one Claude wrote? The original question was about taking over an LLM-written codebase, it doesn't sound to me like the argument was about a codebase that Claude, specifically, wrote.

The original question is: > What happens when you have a codebase made with claude using this setup and claude is down for let's say 8 hours? So: - A codebase made with Claude - Using this [Claude] setup - Claude is down

What does it matter what the codebase is made with? If Claude is down, use Codex, or Gemini, or Deepseek. That version of the argument is just way too easy to counter.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#132

Post by thunky » Wed, May 27, 2026, 1:56 PM UTC

moron4hire wrote: post #120

thunky wrote: post #96

Earlier quoted context omitted.

What happens if you get up in the morning and your car won't start? Do you walk to work?

Yes, I actually have done that.

[flagged]

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#133

Post by beezlewax » Wed, May 27, 2026, 2:04 PM UTC

binary0010 wrote: post #128

mindwok wrote: post #101

How many times can I read the same shallow guidance written by AI on using a coding agent? Good god when will it stop

I find it interesting how they are almost all specifically for Claude and/or Claude code. When open source glm-5.1 is just as good - if not better and stuff like opencode exists. Makes one wonder...

How easy is that to setup by comparison?

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#134

Post by chrisweekly » Wed, May 27, 2026, 2:08 PM UTC

fer wrote: post #116

professor_v wrote: post #52

Earlier quoted context omitted.

I just use docker and I don't feel I'm missing anything?

nix develop ensures your dev env is the same as your build/test/prod env. At least with Python everything is a flurry of requirements.txt, Python versions, poetry, pyproject.toml, perhaps automated with direnvs, a hefty Dockerfile/docker-compose, and perhaps conda (ugh) along the way; lots of moving parts. I have a project that's mostly Rust sprinkled with C++ libs and Python helpers and it's easier to manage than th…

Pythonistas have mostly moved to uv, which solves much of the "flurry" you describe. Tools like Mise add more of the benefits ascribed to nix. And smolmachines' smolvms can provide better isolation than Docker. Just saying, TIMTOWTDI. Not hating on nix, just pointing out it's not the only game in town.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#135

Post by nomel » Wed, May 27, 2026, 2:09 PM UTC

hootz wrote: post #111

mindwok wrote: post #101

How many times can I read the same shallow guidance written by AI on using a coding agent? Good god when will it stop

Can't wait to learn more about how to vendor-lock-in myself really hard into not being able to code without the help of a specific corporation!

For most people, CC is cheaper tokens for a SOTA model.

What agentic platform would you recommend for those with API access (including other models)?

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#136

Post by misja111 » Wed, May 27, 2026, 2:10 PM UTC

rimliu wrote: post #89

thedeadp12t wrote: post #38

In the recent weeks, I think the harness/model came to a point that you can just ask it to do stuff and it just does. You can use plan mode, you can also use superpowers, or whatever other skill, but given that you'll review something anyway, why not work directly with code instead of silly amounts of md files?

In the recent weeks I trust Claude less and less. Yes, you can ask it to do stuff and it does stuff. But if you do look what it did you will often find corners cut, work based on assumptions and not verification, a lot of stuff missed. Even tests - it is common for it to write tests which in reality test nothing.

Yep, Claude is behaving more and more like a human being.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#137

Post by chrisweekly » Wed, May 27, 2026, 2:14 PM UTC

BorisMelnik wrote: post #123

new_account_101 wrote: post #63

Earlier quoted context omitted.

[dead]

agree and also not sure if they are saying claude the app/ide or claude the model

Wait, what is "claude the model"? Anthropic's models are named versions of Opus, Sonnet, and Haiku. Claude, Claude Cowork, and Claude Code are their products which leverage those models. Right?

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#138

Post by binary0010 » Wed, May 27, 2026, 2:17 PM UTC

beezlewax wrote: post #133

binary0010 wrote: post #128

Earlier quoted context omitted.

I find it interesting how they are almost all specifically for Claude and/or Claude code. When open source glm-5.1 is just as good - if not better and stuff like opencode exists. Makes one wonder...

How easy is that to setup by comparison?

Extremely easy.

Download opencode GUI or cli. Sign up for Go or Zen plan, choose GLM-5.1 model.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#139

Post by hootz » Wed, May 27, 2026, 2:17 PM UTC

nomel wrote: post #135

hootz wrote: post #111

Earlier quoted context omitted.

Can't wait to learn more about how to vendor-lock-in myself really hard into not being able to code without the help of a specific corporation!

For most people, CC is cheaper tokens for a SOTA model. What agentic platform would you recommend for those with API access (including other models)?

Basically any other that is not stuck to being managed just by one company. Claude Code does things like using CLAUDE.md and other stuff specific to just their platform, so you are basically locking your project, and everyone else who works on it, to Claude Code only, if you don't also port everything you do to other harnesses. If Anthropic is giving cheaper tokens in exchange for locking you in into their ecosystem, then maybe it's time to test other models and not just use Claude for everything.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#140

Post by Someone1234 » Wed, May 27, 2026, 2:21 PM UTC

beezlewax wrote: post #133

binary0010 wrote: post #128

Earlier quoted context omitted.

I find it interesting how they are almost all specifically for Claude and/or Claude code. When open source glm-5.1 is just as good - if not better and stuff like opencode exists. Makes one wonder...

How easy is that to setup by comparison?

Not hard; just initially expensive (hardware mostly).

While I'm also a huge fan of local LLMs and believe they will be key in the future; I think the claim of "just as good" is hyperbole. They're productively useful tools though, and something worth exploration.