agent-usagelisted

# Agent Usage Analyze the shared usage archive with dot and DuckDB. Preserve the difference between recorded token usage, estimated cost, and the provider's actual bill. ## Workflow 1. **Bound the question**: harnesses, time range, sessions, models, and the comparison needed; inspect the existing archive before collecting more data. 1. **Use the owner**: dot owns source synchronization and archive schemas; read [queries.md](references/queries.md) for layout, fields, DuckDB queries, and exports. 1. **Analyze comparable data**: account for missing sessions, model aliases, cache tokens, provider accounting differences, and time zones before aggregating. 1. **Report**: include period, sources, completeness, units, assumptions, and the query or artifact supporting the result; protect prompt and account data. Use `dot agent stats --tokens-only` for a quick total with coverage dates and API equivalents. Add `--monthly` for UTC months or `--billing --agent codex` for configured subscription cycles. Terminal reports use wrapped sections per agent, model, project, or period; exact counts and accounting qualifications remain visible. Add `--by-model` or `--json` for detail; omit `--tokens-only` when prompt statistics are also needed. [queries.md](references/queries.md) owns configuration examples and accounting limitations. Reports first sync changed sessions incrementally; sync failures print on stderr and the report still prints. API equivalents use the offline rate card in `agen