cc-sentiment 0.1.8

Local Claude Code session scorer that contributes metrics to sentiments.cc

cc-sentiment

A macOS CLI that scores your Claude Code conversations on-device and contributes the numbers to an open dashboard at sentiments.cc.

Your conversations stay on your Mac. Only anonymous numeric scores are uploaded.

Run it

uvx --from https://sentiments.cc/run cc-sentiment

Also installable from PyPI as cc-sentiment. The command above installs faster.

Needs macOS on Apple Silicon, Python 3.13+, and uv. The first run links your GitHub account, scores transcripts in ~/.claude/projects/, and uploads the numbers.

What gets uploaded

Only numbers and timestamps. For each 5-minute bucket of a conversation:

• Sentiment score (1–5, scored locally by Gemma 4)
• Read:edit ratio, edits-without-prior-read %, write:edit ratio, tool calls per turn, subagent spawn rate
• Turn count, thinking present/chars
• Claude model and Claude Code version
• Your GitHub handle (so uploads are attributable)

Your conversation text, file contents, file paths, and tool inputs/outputs never leave your machine.

Commands

Command	Description
cc-sentiment	Run the whole flow — set up if needed, then scan and upload
cc-sentiment setup	Link your GitHub account for attributable uploads
cc-sentiment scan --upload	Score new transcripts and upload
cc-sentiment scan	Score transcripts without uploading
cc-sentiment upload	Upload previously scored results
cc-sentiment rescan	Clear state and re-score everything

Links

• Dashboard: sentiments.cc
• Source: github.com/yasyf/cc-sentiment
• Issues: github.com/yasyf/cc-sentiment/issues