Live data from Hacker News

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

arps18.github.io

241–250 of 297 posts

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

#241
post #166

Earlier quoted context omitted.

It also can respect AGENTS.md, just saying. It’s all about your README.md. But I’m with you about being agent agnostic.

Of course it can, it's Microsofty tactics, support everything but generate "proprietary" stuff by default. Read ODF but generate docx.

If you don't like CLAUDE.md, you can just add a memory/modify the plan agent to make an AGENTS.md. These aren't rigid systems. And, you don't have to tell it to look for an AGENTS.md, it'll just pick it up. First thing it does with /init is just look at what's already in the project folder. You should give CC a try!

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

#242

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 mean, to be fair there is nothing but shallow content available considering it's all stochastic responses that are incredibly difficult to actually measure and make real scientific inferences about. Until that changes I think it's going to be constant slop about optimization.

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

#243
post #238
post #234

Earlier quoted context omitted.

If you wrote this yourself, congratulations are in order. I was genuinely annoyed. It’s not easy. It’s hard. It’s not entertaining. It’s infuriating.

You're absolutely right! I was at a restaurant the other day and my kid noticed how the waiter started every sentence with "Absolutely!" That reminded me of the Anthropic Super Bowl ad, and got me thinking if the waiter's speech patterns had been influenced by AI.

Yes: https://arxiv.org/abs/2409.01754

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

#244

Earlier quoted context omitted.

You're absolutely right to call this out — and honestly? I want to sit with that for a moment. Here's the thing: this isn't really about AI writing. It's not even about coding agents. It's about something much deeper. What's genuinely worth knowing: while I generally agree, many people may not. I think there's a really interesting conversation to be had here. Thanks for naming this. It needed to be named. (/s - Blarg…

I could literally feel my blood beginning to boil. You have a talent for this.

Hah thanks. I also feel this way rage-spotting AI-generated text everywhere these days. I have been looking into the speech patterns of LLMs lately ("unslopping" my own AI outputs) so had a bunch of the most horrible cliches memorized. Unfortunately this is a useless talent as a "reverse mechanical turk" at approx $25,000 for 1M output tokens (at 0.3 tok/sec) is not competitive in today's market.

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

#246
post #194
post #192

Earlier quoted context omitted.

Hi Boris, what is the advantage of using /code-review vs just asking Opus to “code review”? As a casual user working on hobby projects, I struggle to keep up with the pace of changes and knowing what to use when. My default now is to use Opus for all coding (sonnet is fine but seems dumber) and to prompt it for everything I need. I’ve had great success with this but clearly I’m missing power user functions with the s…

The advantage is that /code-review supplies a structured idea of how to review and what that process should look like and then launches independent subagents to approach the issue from multiple angles. It's analogous to how in the early days you could see benefits by telling the models to "think step by step". /code-review is something like "review angle by angle". "Consider removed behavior" and also "Look at langua…

It’s simpler to just use “review code”. It’s also way cheaper

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

#247
post #168

We really need some consolidation around commands, skills, subagents, and plugins. For example, if you want to, say, review code, you have five options now: - Write a .claude/commands/review.md. Simple but deprecated. - Use a /code-review skill, either one you install or one you just write yourself (it's just Markdown, after all). - Use the /pr-review subagent. Also just Markdown, but it runs "in the background" and…

I have thought for a while now that skills were a bad abstraction. There's a lack of definition around what to use them for that I think contributed to why they rose to the top, but that's also why I think they aren't a good long term option.

The fact that I can have a skill that is just general guidance on front end design best practices that an agent can call upon whenever they feel, and another that is essentially a run book of steps that need to be followed exactly only when explicitly triggered, and a third that is basically just instructions on how to use a specific tool and all of those are acceptable just feels wrong to me. I get why it caught on and why the flexibility is attractive when the entire world is collectively learning a new tool, but skills have come to feel like the junk drawer in the kitchen where you just throw random shit when you don't want to think about a better place to put it.

I would love to see the world standardize on something like:

- Agents: Essentially personalities for a model to take on. This becomes the new place for skills like "front end expert" where you're not telling an agent to do a specific thing, just to think in a certain way about a task.

- Prompts: Repeatable instructions for specific tasks that an agent should follow when prompted. This could be something like a checklist style run book on how to resolve a certain error that an agent needs to follow exactly or it could be something like here's an idea I have for a new feature please poke holes in it.

- Tools: Tools (like CLIs, MCPs, or scripts) and instructions on how and when to use them. I'm purposefully not calling this skills because I think the term is overloaded, but that's kind of what this is.

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

#249
post #238

Earlier quoted context omitted.

You're absolutely right! I was at a restaurant the other day and my kid noticed how the waiter started every sentence with "Absolutely!" That reminded me of the Anthropic Super Bowl ad, and got me thinking if the waiter's speech patterns had been influenced by AI.

Yes: https://arxiv.org/abs/2409.01754

Eventually we will just speak tokenese rather than english

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

#250
post #139
post #135

Earlier quoted context omitted.

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,…

I do find it somewhat concerning that the incentives aren't aligned, but as long as things live on your computer it should take just a prompt to migrate to something new

And Codex is open source

Post reply on HN