Manage costs effectively changedcosts
Nearest release: v2.1.305, published 2 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 20 Oct 2026 21:32 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 20 Oct 2026 21:37 UTC.
Upstream edited
Recorded here
Lines+23added
Lines−4removed
From line
51
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits43to this page, all time
#### Apply recommendations with the fix shortcut
The whole hunk
from line 51, old and new numbered
/
from line 51
5151
5252#### Plan usage breakdown
5353
54On a Pro, Max, Team, or Enterprise plan, `/usage` also shows a breakdown of what counts against your plan limits:
54On a Pro, Max, Team, or Enterprise plan, `/usage` also shows a breakdown of what counts against your plan limits, with recommendations:
5555
5656* **Attribution**: recent usage attributed to skills, subagents, plugins, and individual MCP servers, each shown as a percentage of the total. An MCP server's share counts only the requests that consumed one of its tool results. Before v2.1.222, after one call to an MCP server, Claude Code attributed every subsequent request to that server, overstating its share.
57* **Behavior flags**: behaviors such as long context or cache misses, flagged when one accounts for 10% or more of recent usage.
57* **Recommendations**: changes that lower your usage, one per row. Each row starts with the share of recent usage it addresses, at least 10%, as in `25% Trim ~/code/api/CLAUDE.md · 49k tokens per request`. To have Claude Code apply the ones it can, see [Apply recommendations with the fix shortcut](#apply-recommendations-with-the-fix-shortcut).
5858* **Loops**: a row for each of the heaviest [`/loop` or other session-scoped scheduled tasks](/docs/en/scheduled-tasks) that ran recently, ordered by total tokens, with a count of the rest. Requires Claude Code v2.1.242 or later.
5959 * **What each row reports**: how often the task fires, how many times it ran, its total and per-run tokens, and when it last ran
6060 * **Stopped and re-created loops**: Claude Code keys a row by the task's prompt, so a loop you stop and re-create stays one row
from line 61
6161
6262Press `d` or `w` to switch between the last 24 hours and the last 7 days. The figures are approximate and computed from local session history on this machine, so usage from other devices or claude.ai is not included.
6363
64In the [VS Code extension](/docs/en/vs-code#check-account-and-usage), the attribution shares and behavior flags appear in the Account & usage dialog with a Day and Week toggle, without the Loops rows.
64In the [VS Code extension](/docs/en/vs-code#check-account-and-usage), the attribution shares and recommendations appear in the Account & usage dialog with a Day and Week toggle, without the Loops rows.
6565
66#### Apply recommendations with the fix shortcut
67
68When the `/usage` footer shows a hint such as `f to fix 2 of 3`, press `f` to have Claude Code act on the recommendations it can. The `f` shortcut requires Claude Code v2.1.305 or later.
69
701. After any turn in progress ends, Claude Code runs each [`/effort`](/docs/en/model-config#adjust-effort-level) command shown in a row without `run`.
712. Claude then gets one prompt with a step for each of the other rows it can act on. The prompt asks Claude to show you each change before making it.
72
73To see what pressing `f` does with each of your rows, find the row's shape in the first column:
74
75| Row shape | Example row | When you press `f` |
76| :- | :- | :- |
77| Ends in an `/effort` command with no `run` before it | `40% Switch from max to high effort · /effort high` | Claude Code runs the command |
78| Ends in `run` and a command | `30% Compact before you step away · run /compact` | Nothing happens for this row. Run the command yourself at the Claude Code prompt |
79| Ends in anything else | `25% Trim ~/code/api/CLAUDE.md · 49k tokens per request` | Claude gets a step in the prompt for some of these rows, and nothing happens for the rest. If Claude shows you no change for a row, follow that recommendation yourself |
80
81In `f to fix 2 of 3`, the first number counts the rows Claude Code acts on when you press `f`, and the second counts the rows shown. A hint with no `of` in it, such as `f to fix both`, means Claude Code acts on every row shown.
82
83While [Remote Control](/docs/en/remote-control) is connected, the footer shows no `f` hint. If pressing `f` closes `/usage` with `Nothing was sent. Turn off Remote Control to use fixes.`, Remote Control connected while `/usage` was open. To use `f` again, [disconnect Remote Control](/docs/en/remote-control#check-connection-status), then run `/usage` at the Claude Code prompt and press `f` again.
84
6685#### Check your usage-credits spend
6786
6887`/usage` also shows a usage-credits row while [usage credits](#add-usage-credits-to-your-subscription) are on. What the row shows depends on your plan:
from line 390
371390* **Agent teammates**: each active [teammate](#agent-team-token-costs) keeps consuming tokens until it exits
372391* **Compaction**: `/compact` reads the conversation it summarizes, so [compacting a large context](/docs/en/prompt-caching#compacting-the-conversation) is itself a large request. When you want a fresh start instead of continuity, `/clear` costs nothing
373392
374On a Pro, Max, Team, or Enterprise plan, the `/usage` breakdown flags behaviors that account for 10% or more of your recent usage, such as long context or cache misses, each with a tip to reduce it.
393On a Pro, Max, Team, or Enterprise plan, the [`/usage` breakdown](#plan-usage-breakdown) recommends a change for behaviors behind 10% or more of your recent usage, such as long context or cache misses.
375394
376395## Understanding changes in Claude Code behavior
377396
No line in this hunk matches that.