AI CODING ACTIVITY FOR GITHUB
Track every token.
Count tokens across coding harnesses, keep prompts and code on your machine, and publish one live profile card.
One more prompt. I swear.
- Collected
- Token totals and model metadata
- Ignored
- Prompts, replies, code, repo names
Static examplesample data
MIT licensedLive profile cardAutomatic updatesNo profile commits
SUPPORTED HARNESSES
Pick your coding harness.
Each integration uses the strongest official capability available. The panel tells you when collection is native, plugin assisted, or CLI assisted.
Install from the TokensBurned marketplace, connect GitHub, then let the official SessionEnd hook upload a short aggregate snapshot.
/plugin marketplace add Parsifal1986/TokensBurned
/plugin install tokensburned@tokensburned
/reload-plugins
/tokensburned:connect
Optional history import reads only Claude Code JSONL usage fields for the approved date range.
Previewsample
Static fictional preview. Enter a GitHub username to generate the link; no API request is made here.
THE DATA BOUNDARY
Aggregate locally. Publish deliberately.
- Leaves your machine
- Aggregate token and request counts, tool/provider/model labels, and activity dates and hours.
- Stays on your machine
- Prompts, responses, source code, repository names, transcript paths, API keys.
- Runs automatically
- Connected plugins can upload usage. Start background collection with run and stop it with run --stop. No traffic proxy or Git commits.
Document the damage.
Open source, privacy bounded, and mildly judgmental.