nntrivi2001
57dc91585d
Internal SmartGift build of a Claude Code monitoring dashboard. Lanes: a durable unit of parallel agent work, one per working directory, tracked across session restarts. Managed lanes are git worktrees the dashboard provisions and can reset or remove behind a three-check destroy guard and a counted preflight; adopted lanes are directories you already own and are never destroyable. Pipelines: a lane moves through pipeline stages. A stage the agent declares with evidence renders green; a stage inferred from the tool-event stream renders dashed amber and never counts as done. Detection is forward-only within a 30-minute window, and never writes the declared stage. Workspace: one page at /run with a lane grid, the selected lane's pipeline, and a full Claude console behind a disclosure.
945 B
945 B
description, argument-hint
| description | argument-hint |
|---|---|
| List the most expensive sessions pushing your spend up | [top-N] |
List the sessions driving Claude Code spend up — the top $ARGUMENTS most expensive (default top 10 if empty).
-
Fetch a wide slice of sessions:
curl -s "http://localhost:4820/api/sessions?limit=200" -
Sort the returned sessions by inline
costdescending and take the top N. -
Print a table — rank, session id/name,
model,started_at,metadata.turn_count, andcost(USD, 4 decimals). Below it:- Sum of the top N and what share of fleet spend they represent (sum top-N
cost/ sum of allcost). - Flag any Opus session with a low
turn_countas a downshift candidate (point to themodel-savingsskill).
- Sum of the top N and what share of fleet spend they represent (sum top-N
If the dashboard is unreachable, tell the user to start it with npm start from the
repo root. Keep it to one table plus two summary lines. Read-only — do not modify anything.