Claude Code now supports Hooks

(docs.anthropic.com)

200 points | by ramoz 8 hours ago

18 comments

  • nojs 7 hours ago

        Exit Code 2 Behavior
        PreToolUse - Blocks the tool call, shows error to Claude
    
    This is great, it means you can set up complex concrete rules about commands CC is allowed to run (and with what arguments), rather than trying to coax these via CLAUDE.md.

    E.g. you can allow

        docker compose exec django python manage.py test
    
    but prevent

        docker compose exec django python manage.py makemigrations
    • rco8786 7 hours ago
      You can already do this in .Claude/settings.json
      • nojs 7 hours ago
        Ah you’re right, but for more complex logic it’s useful to be able to run it through a custom script
  • ramoz 8 hours ago
    Really excited to see this implemented.

    Hooks will be important for "context engineering" and runtime verification of an agent's performance. This extends to things such as enterprise compliance and oversight of agentic behavior.

    Nice of Anthropic to have supported the idea of this feature from a github issue submission: https://github.com/anthropics/claude-code/issues/712

    • chisleu 7 hours ago
      It is indeed. I don't use Claude Code. I use Cline which is a VS Code extension (cline.bot).

      This is a pretty killer feature that I would expect to find in all the coding agents soon.

  • mkagenius 2 hours ago
    As an aside, people say AI will eliminate coding jobs, but then who will configure these hooks? Or think about adding such a feature?

    These kinds of tooling and related work will still be there unless AI evolves to the point that it even thinks of this and announces this to all other AI entities and they also implement it properly etc.

    • mrmincent 2 hours ago
      To misuse a woodworking metaphor, I think we’re experiencing a shift from hand tools to power tools.

      You still need someone who understands the basics to get the good results out of the tools, but they’re not chiseling fine furniture by hand anymore, they’re throwing heaps of wood through the tablesaw instead. More productive, but more likely to lose a finger if you’re not careful.

      • forgotoldacc 1 hour ago
        And we may get an ugly transitory period where a lot of programs go from being clearly hand made with some degree of care and some fine details that show the developer's craftsmanship, to awful prefab and brutalist software that feels inhuman, mass-produced, and nothing is really fit for the job but still shipped because it kind of works well enough.

        People go to museums to admire old hand-carved furniture and travel to cities to admire the architecture of centuries past made with hand-chiseled blocks. While power tools do let people make things of equal quality faster, they're instead generally used to make things of worse quality much, much faster and the field has gone from being a craft to simply being an assembly line job. As bad as software is today, we're likely to hit even deeper lows and people will miss the days where Electron apps are good compared to what's yet to come.

        There's already been one step in this direction with the Cambrian extinction of 90s/early 2000s software. People still talk about how soulful Winamp/old Windows Media Player/ZSNES/etc were.

    • wastewastewaste 34 minutes ago
      Yea man, people say combine harvesters will eliminate agriculture jobs, but then who will operate these combine harvesters? Obviously every single manual farm laborer will just switch to being an operator of those.

      God, will we never move this discussion past this worthless argument? What value would there be in any of these automatization tools, be in in agriculture or AI, if it just made every single worker switch to being an [automatization tool] operator?

    • energy123 55 minutes ago
      If programmers become 10x more productive but demand only grows by 5x, what will happen?
    • jonathanstrange 23 minutes ago
      > unless AI evolves to the point that it even thinks of this

      The #1 goal of every AI company is to create an AI that is capable of programming and improving itself to create the next, more powerful AI. Of course, these kind of configuration jobs will be outsourced to AI as soon as possible, too.

  • brynary 7 hours ago
    This closes a big feature gap. One thing that may not be obvious is that because of the way Claude Code generates commits, regular Git hooks won’t work. (At least, in most configurations.)

    We’ve been using CLAUDE.md instructions to tell Claude to auto-format code with the Qlty CLI (https://github.com/qltysh/qlty) but Claude a bit hit and miss in following them. The determinism here is a win.

    It looks like the events that can be hooked are somewhat limited to start, and I wonder if they will make it easy to hook Git commit and Git push.

    • alfons_foobar 1 hour ago
      Why is it that regular git hooks do not work with claude code?
  • carraes 7 hours ago
    So, form my limited understanding, this doesn't take up context, it's something auto where you can configure per tool use, and not MCP that Claude decides "when" to run it?!
  • cheriot 4 hours ago
    Amazing how there's whole companies dedicated to this and yet claude code keeps leading the way.
    • stavros 1 hour ago
      Does it? Claude Code is the product that works the least well for me, mainly because of its tendency to go off and do tons of stuff. I've found LLMs are at their best when they produce few enough lines of code that I can review and iterate, not when they go off and invent the world.

      For that reason, I mainly use Aider and Cursor (the latter mostly in the "give me five lines" comment mode).

    • wippler 4 hours ago
      Not to take away anything here, but hooks are present in other similar products. Atleast one example here - https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/com...
  • petethepig 7 hours ago
    Would love to see this in Cursor. My workaround right now is using a bunch of rules that sort of work some of the time.
    • ed_mercer 3 hours ago
      As an ex-Cursor user myself, is there any reason that you’re still using it? Genuinely curious.
      • porker 3 hours ago
        That tab autocomplete and predicting what I'm going to edit next is the best I've found.

        The rest I can take or leave (plenty of good or better alternatives)

        • wahnfrieden 1 hour ago
          Claude Code has Cursor integration you can use both
      • jerrygoyal 2 hours ago
        I've been using cursor for last 1 year but haven't tried Claude Code, Do you think it has gotten better?
        • myflash13 1 hour ago
          Yes, I abandoned Cursor recently and went back to Claude Code. Two main reasons: 1. The “plan mode” for Claude makes it execute complex tasks much more reliably. It automatically keeps track of todos and completes them. With Cursor I’m constantly fighting with it. 2. I can now use my IDE of choice (JetBrains) rather than a poor fork of VS Code. 3. Daily usage limits now included in the monthly $20/month Claude Pro plan seems to be enough for my daily needs. No extra costs.
      • Aeolun 2 hours ago
        Cursor is still the best when you don’t have access to a Claude subscription.
        • am17an 2 hours ago
          You get CC when you sign up for their $20 plan also.
          • vl 2 hours ago
            Without Opus (larger model), for $20 you get only Sonnet. $100 and $200 plans have Opus.
      • nxobject 2 hours ago
        To be frank? I can't justify paying for a single-purpose LLM service subscription: Cursor has have a 1-year free educational plan, and for general-purpose multimodal reasoning model work (e.g. OCR, general knowledge reference, math computations, prose processing), I already have a ChatGPT Plus subscription. It's the streaming service dilemma all over again.
  • aantix 2 hours ago
    Wish it supported rollbacks..
  • parhamn 7 hours ago
    This needs a way to match directories for changes in monorepos. E.g. run this linter only if there were changes in this directory.
    • ramoz 7 hours ago
      An abstraction via a script should work, right? They document that it pipes the JSON data to your command's stdin,

        ```lint-monorepo.sh
      
        # read that data
        json_input=$(cat)
      
        # do some parsing here with jq, get the file path (file_path)
      
        if [$file_path" == "$dir1"*]
          run lint_for_dir1
        ```
    • dcre 4 hours ago
      Whatever you run in the hook can check whatever conditions you want.
    • brynary 6 hours ago
      This can be implemented at the line level if the linter is Git aware
  • artursapek 7 hours ago
    adding a hook to have it push to prod every time baby
    • bgwalter 5 hours ago
      We have to do this, otherwise China wins the "AI" race!
    • thelittleone 7 hours ago
      This also:

      1) Assign coding task via prompt 2) Hook: Write test for prompt proves 3) Write code 4) Hook: Test code 5) Code passes -> Commit 6) Else go to 3.

    • apwell23 7 hours ago
      you can just tell it do that or in your claude.md. don't need hooks
      • thelittleone 7 hours ago
        In some cases cc misses rules in CLAUDE.md.
        • ramoz 6 hours ago
          In many cases.
          • apwell23 6 hours ago
            so its back to hand coding stuff again.

            They are going to slowly add "features" that brings handcoding back till its like 100% handcoding again.

            • ramoz 5 hours ago
              This doesn’t come without consideration. You can see I mention this in the original feature request.

              Yes - it’s fine to think of it as handholding (or handcoding). These model providers cannot be responsible for ultimate alignment with their users. Today, they can at best enable integration so a user, or business, can express and ensure their own alignment at runtime.

              The nature of these systems already requires human symbiosis. This is nothing more than a new integration point. Will empower agents beyond today’s capabilities, increase adoption.

  • jonstewart 6 hours ago
    I've been playing with Claude Code the past few days. It is very energetic and maybe will help me get over the hump on some long-standing difficult problems, but it loses focus quickly. Despite explicit directions in CLAUDE.md to build with "make -j8" and run unit tests with "make -j8 check", I see it sometimes running make without -j or calling the test executable directly. I would like to limit it to doing certain essential aspects of workflow with the commands I specify, just as a developer would normally do. Are "Hooks" the right answer?
    • bfLives 5 hours ago
      For the `-j` issue specifically, exporting `MAKEFLAGS=-j8` should work.
  • bearjaws 7 hours ago
    Claude Code has basically grown to dominate my initial coding workflow.

    I was using the API and passed $50 easily, so I upgraded to the $100 a month plan and have already reached $100 in usage.

    I've been working on a large project, with 3 different repos (frontend, backend, legacy backend) and I just have all 3 of them in one directory now with claude code.

    Wrote some quick instructions about how it was setup, its worked very well. If I am feeling brave I can have multiple claude codes running in different terminals, each working on one piece, but Opus tends to do better working across all 3 repos with all of the required context.

    Still have to audit every change, commit often, but it works great 90% of the time.

    Opus-4 feels like what OAI was trying to hype up for the better part of 6 months before releasing 4.5

    • wahnfrieden 1 hour ago
      You can’t use it across three repos like a workspace in Xcode?
  • rtp4me 7 hours ago
    Just started using Claude (very late to the game), and I am truly blown away. Instead of struggling for hours trying to get the right syntax for a Powershell script or to convert Python to Go, I simply ask Claude to make it happen. This helps me focus on content creation instead of the mind-bending experience of syntax across various languages. While some might call it laziness, I call it freedom as it helps me get my stuff done quicker.

    I have been using it for other stuff (real estate, grilling recipes, troubleshooting electrical issues with my truck), and it seems to have a very large knowledge base. At this point, my goal is to get good at asking the right kinds of questions to get the best/most accurate answers.

    • dmix 6 hours ago
      That’s great. Regardless of the naysayers about AI hype in tech, it was a major development for general society even if this is all it ends up being.
      • billbrown 4 hours ago
        It remains to be seen whether it's a net value once the VC firehose dries up and the true costs are revealed. It's quite possible that the profitable price is not worth it for most companies.
        • KoolKat23 30 minutes ago
          It can still be a lot more expensive and be cheaper than a human, it might mean less chance taking and spending the money to try set it up and see if it works though. More existing setups, less new setups.
  • apwell23 7 hours ago
    [flagged]
    • chisleu 7 hours ago
      Yup, slowing down the AI is a really hard thing to do. I've mostly accomplished it, but I use extensive auto prompting and a large memory bank. All of it is designed explicitly to slow down the AI. I've taught it how to do what I call "Baby Steps", which is defined as: "The smallest possible change that still effectively moves the technology forward." Some of my prompting is explicit about human review and approval of every change including manual testing of the application in question BEFORE the model moves on to the next step.
    • wewewedxfgdf 7 hours ago
      The key phrase is "Do not overengineer."

      I say stuff like:

      This code must be minimal.

      Meet only the stated requirements.

      Do not overengineer.

      Create a numbered index of requirements.

      Verify after you write the code that all requirements are met and no more.

  • coherentpony 7 hours ago
    [flagged]
  • bionhoward 7 hours ago
    Given the Anthropic legal terms forbid competing with them, what are we actually allowed to do with this? Seems confusing what is allowed.

    No machine learning work? That would compete.

    No writing stuff I would train AI on. Except I own the stuff it writes, but I can’t use it.

    Can we build websites with it? What websites don’t compete with Anthropic?

    Terminal games? No, Claude code is a terminal game, if you make a terminal game it competes with Claude?

    Can their “trust and safety team” humans read everyone’s stuff just to check if we’re competing with LLMs (funny joke) and steal business ideas and use them at Anthropic?

    Feels like the dirty secret of AI services is, every possible use case violates the terms, and we just have to accept we’re using something their legal team told us not to use? How is that logically consistent? Any safety concerns? This doesn’t seem like a law Asimov would appreciate.

    It would be cool if the set of allowed use cases wasn’t empty. That might make Anthropic seem more intelligent

    • ethan_smith 6 hours ago
      Anthropic's terms typically restrict training competing AI models with their outputs, not building standard applications or websites that simply use their API as a tool.
    • nerdsniper 7 hours ago
      Would you argue that Cursor (valued at $10B) is breaking Anthropic's terms by making an IDE that competes with their Canvas feature?
      • varenc 6 hours ago
        Cursor isn't building models trained with the outputs of Anthropic models (I think). That's what the ToS is forbidding.
      • jazzyjackson 7 hours ago
        Is Cursor using Claude code to build? Or they just allow it to plug into Claude?
      • moralestapia 7 hours ago
        Yes.
    • jazzyjackson 7 hours ago
      Oh come on, your CRUD app is not competing with an LLMaaS
      • moralestapia 7 hours ago
        Oh come on, understand how contracts work before posting a comment like this one.
    • paulsutter 7 hours ago
      You’re only competing with them if you’re doing something they consider competitive. OpenAI is competitive, you are not
  • wilde 8 hours ago
    This is nice but I really wish they’d just let me fork the damn thing already.
  • AdieuToLogic 7 hours ago
    So many people yearn for LLM's to be like the Star Trek ship computer, which when asked a question unconditionally provides a response relevant and correct, needing no verification.

    A better analogy is LLM's are closer to the "universal translator" with an occasional interaction similar to[0]:

      Black Knight: None shall pass.
      King Arthur: What?
      Black Knight: None shall pass!
      King Arthur: I have no quarrel with you good Sir Knight, But I must cross this bridge.
      Black Knight: Then you shall die.
      King Arthur: I command you, as King of the Britons, to stand aside!
      Black Knight: I move for no man.
      King Arthur: So be it!
      [they fight until Arthur cuts off the Black Knight's left arm]
      King Arthur: Now, stand aside, worthy adversary.
      Black Knight: 'Tis but a scratch.
      King Arthur: A scratch? Your arm's off!
      Black Knight: No, it isn't.
      King Arthur: Well, what's that then?
      Black Knight: I've had worse.
    
    0 - https://en.wikiquote.org/wiki/Monty_Python_and_the_Holy_Grai...