Sculptured docs

Where tokens went

See what a run's tokens were spent on (setup, files, handoffs, the plan window) and what to change to use less.

Where tokens went explains a run's usage as causes you can act on. It shows how much of every agent's start was setup it did not need, which files agents printed into their own context, how many agents worked at once, and how much of your plan window the run used against its budget.

It is made by MAIS, an open-source reader of Claude Code and Codex session files, on the computer that ran the team. Only the report leaves that computer.

Open it

  1. While a team runs
    On the Run board, open More → Where tokens went. The report is refreshed every minute while the run goes, and once more after it ends.
  2. For an earlier run
    Open More → History, choose the run, then Where tokens went. Agents goes back to the run's agents.

What it shows

SectionWhat it tells you
What stands outA few plain sentences, such as "Your own CLI setup was 41% of the starting context". Each rests on a section below.
Plan windowYour Claude or Codex window before the run, at its highest, and the points the run added, with the budget's wrap-up and stop marked.
Over timeTokens every few seconds and how many agents were making model calls, with the moments many agents started together.
By causeEvery token of the run: the starting context each agent re-read on every call, what agents added as they worked (files printed, tool results, messages), and what they wrote.
By agentEach agent's calls, tokens, starting and final context, and how long it spent in model calls and waiting. A name links to the agent's page.
Costliest in contextThe command outputs and files whose re-reading cost the most, files several agents each read for themselves, the part of every agent's start that was identical, and tools agents were given but never called.
TimeHow long model calls took, and how agents' time divided between model calls, tools and waiting for work.

Every agent re-reads its whole context on every model call, so something added early costs again on each later call. The report counts that: an item's re-read is its size times the calls that re-sent it.

How sure each number is

A CLI reports what each model call read in total, not what was in it. The report labels every figure:

Use less next time

If the report saysTry
Your own CLI setup is a large share of the startLeave Claude Code setup for agents off (team Advanced). It is off unless you turned it on.
Files printed are the largest cause of growthAsk agents in their job to read only the parts of files they need, or give one agent the reading and have it hand out summaries.
Many agents started togetherSet Most agents working at once in the run budget.
Several agents read the same filePut the shared facts in the team's context once, or have one agent read it and hand it over.
The run used much of your plan windowSet a run budget so the run wraps up and stops where you choose.

Privacy

MAIS reads the session files on the computer that ran the team. The report carries sizes, causes, the command lines agents ran and the names of the files they read or changed. It does not carry the files' contents or the agents' messages. Passwords, tokens and keys that appear in command lines are masked, and a patch is named by its files, never its text; masking catches common forms only, so a command that printed a secret in an unusual form can still show it in the Costliest in context table. On a computer you connected, turn reports off with sculptured connect --disable usage-reports.

A computer whose runner was installed before reports existed says so; reinstall the runner from Computers to see them.