Cook: A simple CLI for orchestrating Claude Code

(rjcorwin.github.io)

180 points | by staticvar 6 hours ago

24 comments

  • vadepaysa 4 hours ago
    I did a Show HN[0] a few days back with my CLI agent called cook[1] and for a moment I was ecstatic my tool made it to the front page. haha.

    [0]: https://news.ycombinator.com/item?id=47262711 [1]: https://getcook.dev

  • maCDzP 51 minutes ago
    I dunno. I just let Claude build a python script that calls Claude code though subprocess.run().

    I recently made a sort of Autoresearch with that approach. The script calls Claude Code to create a hyphotesis, then code based on that, evaluate- rinse and repeat. I am still trying to figure out if I am actually on to something or just burning tokens. Jury is still out.

  • smarx007 26 minutes ago
    A noob question: is there a tool that automatically instructs Claude Code to "continue" when the token quota is reset after 5h? I am interested in that more than some rather fancy loops.
  • rc_kas 6 hours ago
    Can someone explain what this is to my n00b brain. I don't get what claude-cli is missing that this adds in?
    • beshrkayali 5 hours ago
      IMO the raw Claude CLI is great for one-off interactive sessions, but as soon as you want repeatable multi-step workflows you’re either copy-pasting prompts forever or hacking your own solution manually. That’s exactly the gap these tools fill.

      My take on a solution for this is https://ossature.dev — .smd spec markdown files + ossature audit / build that gives you DAG orchestration, SHA-traced increments, and tiny focused contexts.

      • eloisius 4 hours ago
        Isn’t a repeatable, multi-step workflow exactly what a script or Makefile does?
        • beshrkayali 1 hour ago
          Yeah bash scripts start clean but the sprawl kicks in quick as the workflow and project becomes more complex. Prompts get copied, deps turn manual, and maintenance of your workflow itself becomes the chore.

          Ossature swaps that for structured SMDs and optional AMDs. Multiple specs build a clean DAG that drops into an editable plan.toml so everything stays traceable without the mess.

          Feel free to check the example projects on https://github.com/ossature/ossature-examples

          • wiseowise 1 hour ago
            > Yeah bash scripts start clean but the sprawl kicks in quick as the workflow and project becomes more complex.

            Then just use Python.

      • isodev 4 hours ago
        I use bash scripts. Both Claude and Vibe support all kinds of arguments if you need a prompt to “become a task”. Bash is also deterministic and easy to read and debug.
        • Yiin 2 hours ago
          can you elaborate on "easy to read and debug", because in my experience it is anything but
          • isodev 2 hours ago
            Compared to a random tool someone vibecoded?
      • je42 3 hours ago
        Had a quick look. Stumbled upon the markdown format smd.

        Was wondering if using front-matter instead of a "custom" encoding for parseble data was considered?

    • sghiassy 5 hours ago
      As a prerequisite you’d want to understand the purpose of Ralph Wiggum Loops

      But in general this is meta to the CLI agent.

      So if you were to use the CLI to perform a review of some code. This tool would allow you to loop the output of the code review 5 times onto itself.

      • exolab 2 hours ago
        > So if you were to use the CLI to perform a review of some code. This tool would allow you to loop the output of the code review 5 times onto itself.

        Claude already does that if you ask nicely.

    • transitorykris 5 hours ago
      Maybe not adds in, but wraps around. You could accomplish much of this with fairly simply bash scripts.
      • esperent 5 hours ago
        You could accomplish all of it with claude -p (headless mode).
        • transitorykris 5 hours ago
          Admittedly I might be missing a flag or two with claude, but how are multiple loops and comparisons of solutions done with just headless mode?
        • brcmthrowaway 5 hours ago
          Indeed.

          Where are people finding time for these sort of projects.

          • injidup 29 minutes ago
            They bootstrap a workflow with a prompt then build an orchestrator off that then prompt it to be converted to an opencode plugin and then prompt a website to be generated advertising it and then prompt a tool that reviews hacker news feedback and automatically incorporates feedback into next generation of the tool. At the end of the week they go to their manager and complain they are out of tokens for the actual job they are being paid for.
  • sbinnee 5 hours ago
    There is a skill installation option. The skill markdown has 180 lines [1].

    My take? I like it. It's concise enough for me to try it out. And I love the webpage.

    [1] https://github.com/rjcorwin/cook/blob/main/no-code/SKILL.md

  • genthree 41 minutes ago
    Semi-on-topic: Anyone know a way to get a good alternative UI on top of Cursor?

    My company’s tracking how much we use the damn thing (its autocomplete is literally less-useful than standard VSCode, only time it’s consistently good is when it sees me do one thing to a line, sees repeated similar lines after that, and suggests I do it on the next one too, one at a time, and that’s only useful to me because I’ve never actually bothered to learn how to properly use a text editor) so I can’t avoid it, but even on codebases in the hundreds of lines it’s OOM killing things on my 16GB laptop (it, plus goddamn Teams, were eating half the memory by themselves the other day… with Cursor sitting at almost 6GB alone. JFC. On the plus side if this is what software from a company that should be full of experts at using these things looks like, guess our jobs are safe from them… though not from recession and ZIRP unwinding)

  • jemmyw 3 hours ago
    Looks pretty nice. I think a lot of devs have been making similar tools, I've written my own thing that does a work review loop. I like the interface you've made. I'll probably give it a go, but I'm also reluctant to relinquish the control I have when it's my own code doing orchestration.
  • kasperstorgaard 2 hours ago
    How heavy on tokens is this? I don't use these style workflows and am fairly new to claude code, so I assume it's better than 3x tokens when doing 3 passes?
    • hasperdi 1 hour ago
      It's not 3x because of 3 runs; can be more token, can be less.

      The way of thinking it is, telling Claude to tackle the problem 3 times, each time it may or may not use different approach, fix or improve on things it did previously.

  • NetOpWibby 3 hours ago
    Dull colors and a display font used for copy makes this website incredibly unpleasant to read.
  • khazhoux 4 hours ago
    How does this handle when Claude needs user input? To choose an option, grant tool permission, clarify questions…
    • neilbb 58 minutes ago
      If you impl this as a backend and connect to Telegram bots, agents can just do `$ ask "Should I do this?"` for agent→human and `$ alert "this thing blocked me"` for coder→planner. That's what I'm actually doing — I have 1 manager + 3 designers + 1 researcher + 2 debugger + 1 communicator + any number of temporal coders/reviewers in my setup, all connected to taskwarrior for task-driven-dev
    • facorreia 3 hours ago
      It seems to be in the spirit of automated vibecoding. I assume it skips all permission checks.
  • nurettin 4 hours ago
    claude> "We want to add a title section that shows what page we are currently on, use cook to manage the development process"

    * coolers whirring, gpus on fire, tokens flying, investors happy, developer goes for 6th break of the day

  • BANRONFANTHE 21 minutes ago
    [dead]
  • erdmozkn62 22 minutes ago
    [dead]
  • perfmode 5 hours ago
    [dead]
  • eddie-wang 5 hours ago
    [dead]
  • shablulman 5 hours ago
    [dead]
  • fortylove 6 hours ago
    [dead]
  • NikitaCometa65 4 hours ago
    [dead]
  • panditaditya21 4 hours ago
    [dead]
  • pissedoffadmin 5 hours ago
    [dead]
  • rafaamaral 6 hours ago
    [flagged]
    • cheriot 4 hours ago
      If this was human written sarcasm, bravo.
    • Yiin 6 hours ago
      just use 200usd plan, I forgot what limits are.
      • tmatsuzaki 4 hours ago
        Do you hit the limit pretty quickly on the Pro plan these days? Im thinking about subscribing for video editing, but Im still not sure.
      • croes 5 hours ago
        You'll remember it soon
        • weird-eye-issue 5 hours ago
          Do you often hit the limits recently on the $200 plan? I don't even come close
          • dionian 5 hours ago
            i used to, its much better now. opus 4.6 has been great on tokens
            • weird-eye-issue 5 hours ago
              Yes, quite a while back, they used to charge a lot more for the Opus tokens
        • anonzzzies 4 hours ago
          Have not hit limits for 2 months now and I use it a lot. I have 200 max as well.
  • xiaolu627 4 hours ago
    [flagged]