Hacker News new | past | comments | ask | show | jobs | submit

Show HN: Rudel – Claude Code Session Analytics

https://github.com/obsessiondb/rudel
118keks0r | | 72 | HN
dmix | parent | next
I've seen Claude ignore important parts of skills/agent files multiple times. I was running a clean up SKILL.md on a hundred markdown files, manually in small groups of 5, and about half the time it listened and ran the skill as written. The other half it would start trying to understand the codebase looking for markdown stuff for 2min, for no good reason, before reverting back to what the skill said.

LLMs are far from consistent.

cbg0 | parent | next
Try this: Keep your CLAUDE.md as simple as possible, disable skills, and request Opus to start a subagent for each of the files and process at most 10 at a time (so you don't get rate limited) and give it the instructions in the skill for whatever processing you're doing to the markdowns as a prompt, see if that helps.
loading story #47355691
keks0r | parent
yes we had to tune the claude.md and the skill trigger quite a bit, to get it much better. But to be honest also 4.6 did improve it quite a bit. Did you run into your issues under 4.5 or 4.6?
loading story #47352460
emehex | parent | next
For those unaware, Claude Code comes with a built in /insights command...
loopmonster | parent | next
insights is straight ego fluffing - it just tells you how brilliant you are and the only actionable insights are the ones hardcoded into the skill that appear for everyone. things like be very specific with the success criteria ahead of time (more than any human could ever possibly be), tell the llm exactly what steps to follow to the letter (instead of doing those steps yourself), use more skills (here's an example you can copy paste that has 2 lines and just tells it to be careful), and a couple of actually neat ideas (like having it use playwright to test changes visually after a UI change)
loading story #47353372
keks0r | parent | next
Ohh this is exciting, I kinda overlooked it. I assume there are still a lot of differences, especially for accross teams. But I immediately ran it, when I saw your comment. Actually still running.
loading story #47352496
evrendom | parent
true, the best comes out of it when one uses claude code and codex as a tag team
loading story #47356487
Aurornis | parent | next
> 26% of sessions are abandoned, most within the first 60 seconds

Starting new sessions frequently and using separate new sessions for small tasks is a good practice.

Keeping context clean and focused is a highly effective way to keep the agent on task. Having an up to date AGENTS.md should allow for new sessions to get into simple tasks quickly so you can use single-purpose sessions for small tasks without carrying the baggage of a long past context into them.

loading story #47354315
longtermemory | parent
I agree. In my experience: "single-purpose sessions for small tasks" is the key
longtermemory | parent | next
From session analysis, it would be interesting to understand how crucial the documentation, the level of detail in CLAUDE.md, is. It seems to me that sometimes documentation (that's too long and often out of date) contributes to greater entropy rather than greater efficiency of the model and agent.

It seems to me that sometimes it's better and more effective to remove, clean up, and simplify (both from CLAUDE.md and the code) rather than having everything documented in detail.

Therefore, from session analysis, it would be interesting to identify the relationship between documentation in CLAUDE.md and model efficiency. How often does the developer reject the LLM output in relation to the level of detail in CLAUDE.md?

loading story #47353541
loading story #47356176
152334H | parent | next
is there a reason, other than general faith in humanity, to assume those '1573 sessions' are real?

I do not see any link or source for the data. I assume it is to remain closed, if it exists.

languid-photic | parent | next
it's reasonable to note that w/o sharing the data these findings can't be audited or built upon

but i think the prior on 'this team fabricated these findings' is v low

keks0r | parent
Its our own sessions, from our team, over the last 3 months. We used them to develop the product and learn about our usage. You are right, they will remain closed. But I am happy to share aggregated information, if you have specific questions about the dataset.
marconardus | parent | next
It might be worthwhile to include some of an example run in your readme.

I scrolled through and didn’t see enough to justify installing and running a thing

keks0r | parent
Ah sorry, the readme is more about how to run the repo. The "product" information is rather on the website: https://rudel.ai
blef | parent | next
Reminds me https://www.agentsview.io/.
mentalgear | parent | next
> A local-first desktop and web app for browsing, searching, and analyzing your past AI coding sessions. See what your agents actually did across every project.

Thx for the link - sounds great !

keks0r | parent
Our focus is a little bit more cross team, and in our internal version, we have also some continuous improvement monitoring, which we will probably release as well.
KaiserPister | parent | next
This is awesome! I’m working on the Open Prompt Initiative as a way for open source to share prompting knowledge.
keks0r | parent
Cool, whats the link? We have some learnings, especially in the "Skill guiding" part of our example.
mbesto | parent | next
So what conclusions have you drawn or could a person reasonably draw with this data?
loading story #47353513
loading story #47355706
ericwebb | parent | next
I 100% agree that we need tools to understand and audit these workflows for opportunities. Nice work.

TBH, I am very hesitant to upload my CC logs to a third-party service.

loading story #47354259
alyxya | parent | next
Why does it need login and cloud upload? A local cli tool analyzing logs should be sufficient.
keks0r | parent
We used it across the team, and when you want to bring metrics together across multiple people, its easier on a server, than local.
bool3max | parent | next
Why is the comment calling out the biggest issue with this so heavily downvoted? Privacy is a massive concern with this.
ekropotin | parent | next
> That's it. Your Claude Code sessions will now be uploaded automatically.

No, thanks

keks0r | parent
It will be only enabled for the repo where you called the `enable` command. Or use the cli `upload` command for specific sessions.

Or you can run your own instance, but we will need to add docs, on how to control the endpoint properly in the CLI.

loading story #47351329
anthonySs | parent | next
is this observability for your claude code calls or specifically for high level insights like skill usage?

would love to know your actual day to day use case for what you built

keks0r | parent
the skill usage was one of these "I am wondering about...." things, and we just prompted it into the dashboard to undertand it. We have some of these "hunches" where its easier to analyze having sessions from everyone together to understand similarities as well as differences. And we answered a few of those kinda one off questions this way. Ongoing, we are also using a lot our "learning" tracking, which is not really usable right now, because it integrates with a few of our other things, but we are planning to release it also soon. Also the single session view sometimes helps to debug a sessions, and then better guide a "learning". So its a mix of different things, since we have multiple projects, we can even derive how much we are working on each project, and it kinda maps better than our Linear points :)
| parent | next
{"deleted":true,"id":47351946,"parent":47350416,"time":1773328687,"type":"comment"}
mentalgear | parent | next
How diverse is your dataset?
keks0r | parent
Team of 4 engineers, 1 data & business person, 1 design engineer.

I would say roughly equal amount of sessions between them (very roughly)

Also maybe 40% of coding sessions in large brownfield project. 50% greenfield, and remaining 10% non coding tasks.

cluckindan | parent | next
Nice. Now, to vibe myself a locally hosted alternative.
vidarh | parent | next
I was about to say they have a self-hosting guide, but I see they use third party services that seem absolutely pointless for such a tiny dataset. For comparison, I have a project that happily analyzes 150 million tokens worth of Claude session data w/some basic caching in plain text files on a $300 mini pc in seconds... If/when I reach billions, I might throw Sqlite into the stack. Maybe once I reach tens of billions, something bigger will be worthwhile.
loading story #47350799
loading story #47351989
lau_chan | parent | next
Does it work for Codex?
keks0r | parent
Yes we added codex support, but its not yet extensively tested. Session upload works, but we kinda have to still QA all the analytics extraction.
dboreham | parent | next
One potential reason for sessions being abandoned within 60 seconds in my experience is realizing you forgot to set something in the environment: github token missing, tool set for the language not on the path, etc. Claude doesn't provide elegant ways to fix those things in-session so I'll just exit, fix up and start Claude again. It does have the option to continue a previous session but there's typically no point in these "oops I forgot that" cases.
sriramgonella | parent | next
[flagged]
keks0r | parent
1. can only partly be answered, because we can only capture the "edits" that are prompted, vs manual ones. 2. for us actually all of them, since we do everything with ai, and invest heavily and continously, to just reduce the amount of iterations we need on it 3. thats a good one, we dont have anything specific for debugging yet, but it might be an interesting class for a type of session.
socialinteldev | parent | next
[flagged]
loading story #47353565
loading story #47354155
mrothroc | parent | next
[dead]
keks0r | parent
This is great. How are you "identifying" these stages in the session? Or is it just different slash commands / skills per stage? If its something generic enough, maybe we can build the analysis into it, so it works for your use case. Otherwise feel free to fork the repo, and add your additional analysis. Let me know if you need help.
loading story #47352800
ptak_dev | parent | next
Used Claude Code to build CareerCraft AI - a conversational career consultant that generates tailored resumes. The session analytics angle is interesting because my experience lines up with the "explain the why" pattern.

The sessions where I gave Claude Code context about the problem space (job seekers rewriting resumes 20x) produced dramatically better results than sessions where I just said "build a resume generator." The AI designed a conversational intake flow, live resume preview with real-time updates, and PDF export - things I hadn't explicitly asked for but that emerged from understanding the problem.

Would love to see Rudel break down sessions by "context richness" vs output quality. My gut says the first 60 seconds of context-setting predicts the entire session's productivity.

Built on SuperNinja (no-code AI app platform): https://super.myninja.ai/apps/6de082c7-a05f-4fc5-a7d3-ab56cc...

multidude | parent | next
[flagged]
indiosmo | parent | next
I usually instruct the agent to use the skills explicitly, e.g. "/writing-tests write the tests for @some-class.cpp"

So the skills are mostly a sort of on-demand AGENTS.md specific to the task.

Another example is I have a `plan-review` skill, so when planning something I add at the end of the prompt something like: "plan the task, .... then launch claude and codex /plan-review agents in parallel and take their findings into account before producing the final plan".

keks0r | parent
The 4% usage was about our internal team, and we have skills setup. So it is not necessary that they are not built, but rather that they were not used, when we expected them to be used. So we adapted our CLAUDE.md to make claude more eager to use them. Also the 4% usage was on the 4.5 models, 4.6 got much better with invoking skills.
mihir_kanzariya | parent | next
[flagged]
rob | parent | next
It's crazy how fast I'm able to identify these bots now. You just get an uncanny valley type of feeling immediately reading it. Sure enough you click the profile and it's a brand new account with one or two similar posts in the same style. There's some sort of writing style here that identifies it because I've picked upon it multiple times quickly but it's hard to articulate into words.
bspammer | parent
Heavy use of /rewind helps with this - it's much better to remove the bad information from the context entirely instead of trying to tell the model "actually, ignore the previous approach and try this instead"
ozgurozkan | parent | next
[flagged]
x187463 | parent | next
> The 26% abandonment rate, the error cascade patterns in the first 2 minutes — these are behavioural signals, not just performance metrics.

> When Claude Code gets stuck in a loop, tries an unexpected tool chain, or produces inconsistent outputs under adversarial prompts — those aren't just UX failures, they're security surface area.

Twice in one paragraph, not even trying to blend in.

howdareme | parent
LLM comment spotted
vova_hn2 | parent
This is so sad that on top of black box LLMs we also build all these tools that are pretty much black box as well.

It became very hard to understand what exactly is sent to LLM as input/context and how exactly is the output processed.

keks0r | parent
The tool does have a quite detailed view for individual sessions. Which allows you to understand input and output much better, but obviously its still mysterious how the output is generated from that input.