TokGuess
Track real AI token usage from local session logs — plus file estimates before you send.
Inspired by Token Watch and Eating Token, but lighter and TokViz-branded.
How it works
Copilot → ~/.copilot/session-state/*/events.jsonl → real tokens
Claude → ~/.claude/projects/**/*.jsonl → real tokens
Editor → chars ÷ 4.2 → file estimate
| Layer |
Source |
Accuracy |
| Copilot Watcher |
events.jsonl (assistant.message, session.shutdown) |
Real API tokens |
| Claude Watcher |
Claude Code JSONL (message.usage) |
Real API tokens |
| File Estimator |
Open file in editor |
~90–95% approx. |
No cloud. No prompt content stored — only token counts and metadata.
Features
- Context Budget — alert before send:
file + selection = ~8k / 32k tok
- Sidebar dashboard — cost, trends, models, sessions, budget meter
- Status bar — session usage + live budget indicator (🟢🟡🔴)
- Period filters — today / 7d / 30d
- Rescan logs command for full rebuild
Context Budget
Estimates what you'd send to Copilot/Claude before you send:
No selection → full file tokens
Selection → file tokens + selection tokens
| Level |
When |
| 🟢 OK |
Below 75% of threshold (default 32k) |
| 🟡 Warn |
≥ 75% — popup + yellow status bar |
| 🔴 Over |
≥ 100% — warning before context overflow |
Commands
| Command |
Shortcut |
| TokGuess: Open Dashboard |
Ctrl+Shift+T |
| TokGuess: Check Context Budget |
— |
| TokGuess: Rescan Logs |
— |
Configuration
| Setting |
Default |
tokguess.budget.threshold |
32000 |
tokguess.budget.warnPercent |
75 |
tokguess.budget.alerts |
true |
tokguess.sources.copilot.enabled |
true |
tokguess.sources.claude.enabled |
true |
tokguess.sources.copilot.path |
~/.copilot/session-state |
tokguess.sources.claude.path |
~/.claude/projects |
Disclaimer
- Session tokens = real counts from local Copilot/Claude logs when available
- Context Budget = local file estimate (~90–95%), not official billing
- Cost = public API rates (approx.)
Develop
npm install && npm run compile
# F5 in VS Code
License
MIT
| |
