Why did that agent run cost so much? Sort your sessions by cost and see where it went

ACTVT estimates what every Claude Code and Codex session would cost at API rates, from its tokens and the model’s published prices. Sort the session list by cost to find the expensive ones, then open one: the inspector shows its cost, its tokens and cache hit, and what its subagents cost as part of the total. It is an estimate at API rates, not your bill if you are on a plan. The session browser and its sort are part of the Premium tier.

0:445 chapters

Step by step

  1. 0:00Two runs, the same job

    Two agents ran the same code review earlier. Did one cost more?

  2. 0:05Sort by cost

    Sort today’s runs by cost. The run that fanned out to subagents is on top.

  3. 0:15What it cost

    What it cost, at API rates. Not your bill if you’re on a plan.

  4. 0:23Where it went

    Its tokens: most of the input was read from cache. Six subagents, and $0.29 of the $0.52 is theirs.

  5. 0:34The same job, one agent

    The same review, done by one agent: $0.10. The same cache hit, no subagents, about a fifth of the cost.

More tutorials

All tutorials →
1:24

Every machine you code on

See agent sessions from every machine you code on, over SSH

Start Claude Code on another Mac over SSH, watch the session live from your own, and read the full transcript when it finishes.

3:42

Leftover ports

Find and kill the dev server your AI agent left running

Claude Code starts a dev server, quits, and leaves port 3000 taken. ACTVT spots the orphan and frees the port safely.

0:48

A plan-aware agent

Can I afford this refactor? Check your plan limits first

Before a two-hour job, Claude Code asks ACTVT how much of your plan is left, and the same limits show in ACTVT with reset countdowns.

Try it on your own agents

ACTVT is free to start, and reads the session files Claude Code, Codex CLI and Pi already write. Nothing to configure.