Claudoscope
Browse, search & track costs across Claude Code sessions
Start new thread
Liran Baba

Claudoscope - Browse, search & track costs across Claude Code sessions

by•
Free open-source macOS menu bar app for Claude Code. Browse full session history, search across conversations, track token costs per project with Anthropic or Vertex AI pricing. Built-in secret detection scans every session for leaked API keys, tokens, and credentials. Config health linter runs 19 rules against your CLAUDE.md files, skills, and hooks. Works with Enterprise API deployments (no cookies needed). Native Swift/SwiftUI, 100% local, zero telemetry. MIT licensed.

Add a comment

Replies

Best
Liran Baba
Maker
📌
Hey Product Hunt, I'm Liran. I built Claudoscope because I manage Claude Code rollout across engineering teams at my company and had no way to tell what sessions were costing us or what was happening inside them. The existing menu bar trackers scrape your session cookie from claude.ai. That doesn't work for Enterprise API deployments. Claudoscope reads the local JSONL session files directly from ~/.claude/projects/, so it works on any setup, Enterprise included. What actually got me started: I found my database password sitting in plaintext in a session file. Claude Code had read a .env and echoed it back as a tool result. Nobody was checking for that. So now the app scans for leaked credentials using entropy-based filtering and alerts you when something shows up. Beyond secret scanning, it gives you: Session history browser with a chat-style viewer and full-text search Cost analytics per project and per session (supports both Anthropic and Vertex AI pricing) Config health linter with 19 rules that checks your CLAUDE.md, skills, and hooks (found broken skill metadata and oversized configs across our team that nobody had noticed) MCP server and skills browser It's native Swift/SwiftUI, not Electron. Runs locally, no telemetry. brew tap cordwainersmith/claudoscope && brew install --cask claudoscope Free and MIT-licensed. If you're running Claude Code on an Enterprise plan where cost visibility is basically nonexistent, I want to know what else you'd need from something like this.
Artem Kosilov

@cordwainersmith Claude Code tools usually sell speed. This goes after the part that gets annoying later.

Once more than one person uses it, the problem is not the model. It’s that nobody really sees what’s going on anymore. What kept breaking often enough that you decided to build this?

Liran Baba
Maker

@artem_kosilov Thanks Artem. Yeah, the multi-person thing is what turned this from a weekend hack into something I actually use daily.

The credential leak is what got me started. Found my DB password in a session file. Claude had read a .env during a conversation and echoed it back. That's just how agents work, they read files, but nobody was looking at what ended up in the logs afterward.


Cost was the next problem. We kept having days that spiked and couldn't explain it. Wasn't the big sessions. It was people firing off tons of short ones, each loading full context with no cache. And on Anthropic's Enterprise plan there's no cost API, spend data only lives in the admin dashboard. Individual devs can't see what their own sessions cost. That was frustrating enough that I built the analytics view before anything else.


Then configs. People's CLAUDE[.]md files ranged from 500 to 5,000 tokens. One person was burning 10% of context window on instructions before the agent even started. Some had broken skill metadata that failed silently, not erroring, just not working. You don't notice that until someone builds a linter and runs it.

Gabriel P.

the token cost tracking per project in the menu bar is more useful as a signal than a budget tool. a session that costs 10x the average is almost always one where something went wrong, not one where you accomplished 10x more.

the secret detection scanning for leaked API keys is the feature that quietly saves someone's day. session histories can end up in sync directories or version control if you're not careful, and most people don't think about what's in them until after.

Liran Baba
Maker

@gabrielpineda The anomaly signal thing is how I use it. I never open the cost view to budget. I open it when a number looks wrong and I want to see what happened. Usually it's a session stuck in a loop, or compaction fired and the agent rebuilt context from scratch a few times.

Agreed on the secrets scanning. The hard part was making it useful and not annoying. Without entropy filtering you get a wall of false positives from example code and docs. It took a while to get the signal right, but now when it flags something, people actually look.