token-usagelisted

# Token Usage Analyzer Analyze token consumption patterns and estimate costs from Claude Code session files (`~/.claude/projects/`). ## What It Does - Parses all JSONL session files to extract token metrics (input, cache creation, cache read, output) - Groups usage by project and session - Estimates costs based on Claude model pricing - Identifies most expensive sessions and subagent usage - Supports time range filtering (today, week, month, N days, specific date) - Generates a detailed markdown report ## Usage Run the analyzer with a time range argument: ```bash python3 .claude/skills/token-usage/scripts/analyze.py $ARGUMENTS ``` ### Arguments | Argument | Example | Description | |----------|---------|-------------| | *(empty)* | | All time | | `today` | `today` | Since midnight UTC | | `week` | `week` | Last 7 days | | `month` | `month` | Last 30 days | | N (number) | `3` | Last N days | | Date | `2026-04-01` | Since that date | | Datetime | `2026-04-01 11:00` | Since that datetime | ### Additional flags - `--compare` — show current period vs previous period of same length Example: `--compare week` shows this week vs last week. ### Output The script prints a summary to stdout and saves a detailed report to: ``` ~/.claude/token-usage-reports/token_report.md ``` ## Cost Estimation Prices are per million tokens, detected automatically per model: | Model | Input | Cache Create | Cache Read | Output | |-------|-------|-------------|------------|--------| | Opus |