HN Showcase
Back to browse
Rudel – Claude Code / Codex sessions reveals 9 types of AI coder

Rudel – Claude Code / Codex sessions reveals 9 types of AI coder

by keks0r·May 4, 2026·5 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidCrowd PleaserEye Candy

Spotify Wrapped for AI coding sessions with playful archetype cards you'll actually share.

Strengths
  • •Nine behavior archetypes derived from 20k+ sessions provide genuine insight, not vanity metrics.
  • •Classifier uses real metadata: token counts, model mix, repo breadth, commit rates.
  • •Open source classifier code lets users verify the methodology behind their archetype.
Weaknesses
  • •Novelty wear-off risk: fun for one share, but limited ongoing utility after initial curiosity.
  • •Requires uploading session data; privacy-conscious devs may hesitate despite open source claims.
Category
AI/ML
Target Audience

Developers using AI coding assistants

Similar To

Spotify Wrapped · GitHub Wrapped · Stack Overflow Year in Review

Post Description

Claude Code / Codex session metadata can actually tell a story about how you work with AI coding agents.

50 days ago we posted about analyzing 1.6k Claude Code sessions from our own team. Skills were used in 4% of sessions, 26% were abandoned early, and we had no real benchmark for what good looked like.

Now across 20k+ sessions, we started looking at behavior patterns from derived session metadata: consistency, intensity, session shape, repo breadth, output, cost intensity, and model range.

Nine archetypes fell out, which we turned into playful cards.

We built a Spotify Wrapped meets trading cards experience on top of the classifier: upload your sessions and get a story about how you use AI coding agents.

The classifier runs on metadata like duration, token counts, model mix, repo count, and commit rates.

Create yours today. It’s free and open source: https://app.rudel.ai/wrapped

Repo: https://github.com/obsessiondb/rudel

Similar Projects