13 comments

  • R00mi 1 hour ago
    The 56% conversation vs 21% coding split is a really interesting finding — it lines up with trajectory studies on SWE-bench where ~38% of an agent's actions are pure exploration (grep, find, file reads). The remaining "no-tool" turns are likely the agent digesting what it read and planning its next move. These two costs are linked: the less efficiently the agent localizes, the more thinking turns it needs to piece things together. PatchPilot (ICML 2025) quantified this — localization capability accounts for ~47% of an agent's total improvement. One thing that would be really interesting in your tool: separating exploration turns (grep/find/read) from pure thinking turns, and seeing how the ratio scales with project size. On large monorepos, exploration should blow up non-linearly.
  • yashjadhav2102 1 hour ago
    That’s really helpful – token usage is definitely something everybody knows about yet can’t quite put their finger on. This split between non-tool conversations and coding looks rather shocking, like there’s a ton of inefficiency in our interaction with such services. I like the fact that it doesn’t require any LLM to run – nice and simple concept.
  • Normal_gaussian 11 hours ago
    This is cool.

    I do find the activities a little suspect - it has 1 turn of planning for me in the last 30 days. I have claude write plans first before every coding session, often using one agent session to plan and then output a plan file, and then others to execute on it. I also have several repos dedicated to 'planning' in the sense of what should I do next based on what emails/tickets/bugs etc. I have. In other words - I do all kinds of planning!

  • giancarlostoro 18 hours ago
    > The interface is an interactive terminal UI built with Ink (React for terminals)

    Just like Claude Code btw.

    I'm working on a custom harness because I don't like or trust some of the ones out there, so I'm going to build one purely for myself and my own needs to see just how they work, and figure out some of what you've learned by looking at how Claude works, so I might add your project to my list of tooling to look at.

    • agentseal 18 hours ago
      yeah Ink, it was the fastest path to something that felt native next to Claude Code itself
  • Isolated_Routes 17 hours ago
    I like this a lot An interesting next iteration would be to add a functionality that evaluates a user's work for inefficiencies and suggests where they can improve cut cost. Might be outside the scope of your project, but it could be interesting.
  • jimbokun 10 hours ago
    So how much did the tokens to build this cost?
  • hmokiguess 18 hours ago
    Very cool! I saw a similar product recently that I liked but I much prefer your approach to theirs[1]

    [1] https://github.com/cordwainersmith/Claudoscope

  • ieie3366 17 hours ago
    "Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens."

    holy slop. the $200/month plan has NEVER hit rate limits for me and I often run 5+ tabs of concurrent agents in a large 300k LoC codebase

    • ethan_smith 16 hours ago
      The $200/month plan throttles you when you hit limits - you just wait in a queue. API usage at $1400/week means unthrottled, parallel execution with no waiting. These are very different use cases, and for teams or heavy automation workflows the API cost can make sense if the time savings justify it.
      • weird-eye-issue 10 hours ago
        That's not how it works

        You've never actually hit the limit have you? If you have you would know it's a hard limit.

        • cududa 6 hours ago
          You’ve never used the API version versus the $200 plan and set the two at the exact same task, have you?
          • weird-eye-issue 5 hours ago
            I used the API version for quite a while before using a subscription, which I now have used extensively for many months.

            So, is your claim that they just slow down and queue the subscription version, or are you accusing them of using nerfed models, or is it something else? The only time I ever get some slowness has to do with the models being overloaded and has nothing to do with limits. Those are two separate concepts you seem to be confusing. And luckily, this is pretty rare for me since I don't work during US time zones.

    • agentseal 17 hours ago
      not $1,400 out of pocket, thats the API equivalent cost of the tokens. I am on the $200/month Max plan :D.

      In my case I mostly consume every bit of the weekly subscription.

  • halostatue 18 hours ago
    Doesn't seem to work with Cursor Agent (which may store its data in ~/.cursor).
    • agentseal 17 hours ago
      you are right. thats cursor-agent (the CLI), not the Cursor IDE. CodeBurn only parses the IDE's state.vscdb right now. cursor agent keeps transcripts under ~/.cursor/projects/*/agent-transcripts/ which we dont read yet.

      filed an issue to add it: https://github.com/AgentSeal/codeburn/issues/55

      cursor support only landed yesterday, so CLI is next. thanks for catching it.

      • halostatue 17 hours ago
        Cursor Agent itself suggests that this probably won't be easy as some of the data is missing.
  • coatol5 17 hours ago
    Made something similar a while back: https://www.clauderank.com/ Completely open source
  • Sim-In-Silico 10 hours ago
    [dead]
  • KaiShips 17 hours ago
    [flagged]
  • maroondlabs 19 hours ago
    [flagged]