• Use `/plugin` to open Claude Code's plug-in manager

• In the Discover tab, enter `lsp` in the search box

• Use `spacebar` to enable the ones you want, then `i` to install

Hope that helps!

I was playing around with codex this weekend and honestly having a great time (my opinion of it has 180'd since gpt-5.2(-codex) came out) but I was getting annoyed at it because it kept missing references when I asked it to rename or move symbols. So I built a skill that teaches it to use rope for mechanical python codebase refactors: https://github.com/brian-yu/python-rope-refactor

Been pretty happy with it so far!

[1]: https://opencode.ai/

But in all seriousness, LLMs have their strengths but we’re all wasting tokens and burning the planet unnecessarily getting LLMs to work so inefficiently. Use the best tool for the job; make the tools easier to use by LLMs. This mantra is applicable generally. Not just for coding.

Pretty sure Cursor has had this for a while.

Dug through their obfuscated JS and it looks like they forgot to re-add a function call in the LSP manager initialize function that actually adds/indexes the lsp registered from plugins.

I’ve not noticed the agent deciding to use it all that much.

[0] https://github.com/charmbracelet/crush

Opus 4.5 is fairly consistent in running QA at proper times. Lint checks and all are already incorporated into a standard & native processes outside of IDE. I think lookup can be useful when definitions are hidden deep in hard to reach places on my disk... hasn't been a problem though the agent usually finds what it needs.

Anyway, here is what it stated it could do:

    > Do you have access to an lsp tool?

     Yes, I have an LSP tool with these operations:

    - goToDefinition - Find where a symbol is defined
    - findReferences - Find all references to a symbol
    - hover - Get documentation/type info for a symbol
    - documentSymbol - Get all symbols in a file
    - workspaceSymbol - Search for symbols across the workspace
    - goToImplementation - Find implementations of an interface/abstract method
    - prepareCallHierarchy - Get call hierarchy item at a position
    - incomingCalls - Find what calls a function
    - outgoingCalls - Find what a function calls

I cannot stand VSCode - even if I configure it to my liking I am unable to make it look or feel the way that makes me feel at home.

I cancelled my subscription a week ago. Yes I still dislike VSCode. But the same product Jetbrains has honed has struggled to integrate with AI agents as well.

I've played with some combination of picking vim/emacs with Claude CLI. I find navigating code a little bit slower since I have trouble building the muscle memory. I've always been big at using my mouse to jump around the file tree.

Configuring LSPs for these text editors and getting things to "just work" takes a little bit more time. I don't know what special sauce is in IntelliJ but for the supported languages, but it took a while for me to be okay with LSPs compared to IntelliJ.

But LLMs and Agents remove a need for a lot of the the advanced IDE features and I've found it better to return back to just treating everything like a text buffer again and using specialized tools to fill in the gaps that were missing with the loss of IntelliJ

The difference for me was night and day!! A lot of the hard wired prompts on the app are only sane for single shot crud work. Habits and behaviors that would make me loath working with a person doing the same.

With a fair disclaimer, that it is very easy to vibe-code a skill oneself, with both pros (you can create one just for you!) and cons (if you look online, these are of any quality, quite a few with some hard-coded versions or practices).

  Added gift tag pictogram for year-end promotion message

I have churned from CC in favor of codex until the scrolling bug is fixed. There is no set of features that will convince me to switch back until they fix their broken UI.

I haven’t dug into the JS code base but I imagine they will have a hard time matching the performance of the rust based codex.

They are definitely coding in a LLM maximalist way, in a good way.

● LSP(operation: "goToDefinition", symbol: "mtz", in: "src/mtz.cpp") ⎿ No LSP server available for file type: .cpp

● No C++ LSP server is configured.

It's that bad. It's embarrassingly bad.

No lock files. Nothing. And then most plugins in turn install MCPs from pypi with uvx so you have two layers of no pinning.

It's a supply chain nightmare. It's so bad that I'm ashamed for our industry

insane way to distribute a core product considering the state of npm.

Maybe whynotboth.gif?

If you're vibe coding without an editor, would this have any benefits to code quality over a test suite and the standard linter for a language?

Claude Code is also solid and this is welcome improvement.

Just try copy-pasting text, say a prompt from a notes app or a text file.

and they completely ignore all complaints. Why would anyone use this crap as opposed to ChatGPT etc.?