Working with agents
ATH is the record and the evidence layer. The model is yours to choose.
Give your agent the instructions
ath init installs the skill in .agents/skills and any existing agent folders. Open your agent in that same folder. Use ath skill to check installed copies, or ath skill install to refresh them without upgrading the CLI.
ath --update refreshes an existing skill in the current folder after checking or updating ATH. The bundled v1 skill knows the SQLite record, stable IDs, revisions, previews and confirmation rules.
$ath skill$ath skill installRead before reasoning
Start with ath stats. Use structured output, preserve source attribution and name missing data. A day without a recorded session is not necessarily a rest day.
$ath stats --json$ath predict fran --jsonKeep the future out of the evidence
--as-of hides observations after a chosen date. This lets an agent reason from a historical view. Use ath backtest to replay historical results with gateway models and write a separate evaluation report.
$ath predict fran --as-of 2026-06-01 --json