Claude Code Token Usage

  • Desktop, mobile and web
  • All plans

What it does

Two meters, both computed on your machine from the files the CLIs already write. Per session: a live token counter on the right of every agent's header, followed by how full the context window is (for example "1.2M tok · 34%"); it turns orange from 60 % context fill and red from 85 % (the gauge can show tokens instead, "300K/1M", and measure against a target ceiling of your own, see Settings), and opens a Session info panel with input, output, cache write and cache read tokens, cache hit rate, context window fill, exchanges, tool uses, models routed, files read, an indicative API-rate cost and ready-made tips to consume less. Per account: the footer Usage badge and panel show how much of each provider's quota you have burned (session, daily, weekly, monthly windows), for every signed-in account, and estimate how that quota splits across your projects and agents. Accounts you pin from that panel each get their own gauge in the status bar, and every bar carries a bell that warns you when it crosses a threshold (see Usage Alerts). Weekly and monthly bars carry a pace marker, a thin tick at what you may have spent by now: the fill left of it means you are within budget, and the line under the bar says how many points ahead or under pace you are, or, in the last 24 hours, how much budget the reset is about to throw away. By default the marker spreads the quota evenly over the whole window; tell AgentsRoom the days you actually work and each work day unlocks an equal share instead (5 days = 20 % a day). When an account also has a 5-hour session gauge, AgentsRoom counts the 5-hour windows that can still start before the weekly reset (back to back, on your work days, 8 am to 11 pm unless you work at night) and compares them with the full sessions the rest of the week needs (one full session costs a measured share of the week, the same figure as Robin Hood): when every window counts, or when even all of them cannot spend the rest of the week, a line under the weekly bar says so before the tokens are lost. Hover the tick or the line for the explanation, your average per work day, where it lands at the reset and, on weekly bars, a Day by day chart: how much of the week each day took, against a dashed daily budget. That history is recorded on your machine from the moment AgentsRoom reads the gauge, so it cannot go back before that: what was spent earlier is shown as one figure. Nothing is sent anywhere.

Where to find it

  • Agent header, in the small stats card on the right before the panel buttons (since 2026-10-23; it used to sit next to the model pill): the N tok column, with the context fill under it (gauge icon). Click it for Session info.
  • Agent header, the column beside the tokens in the same stats card (since 2026-10-23): the cost badge, one figure per line, for example "$4.89", "≈1% 5h", "≈0.3% wk" (only "$" and "wk" when the account has no 5-hour window): the session's cost at API rates (indicative, never billed on a subscription), then this agent's share of the plan on the current 5-hour window and on the week when the quota split can be measured. Click it to open the agent's stats: the Tokens and Cost cards, on a row of their own, flash once, and the Cost card shows the same two lines. Hide it in Settings > Interface elements > Agent panel > Cost badge; Simple mode hides it. In a narrow pane (split view) the cost column steps aside on its own, and when the pane gets narrower still, the header's action buttons fold behind a More actions (…) button.
  • Project agent list (sidebar), since 2026-11-16 (reported by Tu), off by default: once Gauge on each agent row is ticked (Settings > Appearance > Context gauge), each open agent's row ends its title line with the same context fill (gauge icon, then "34%" or "300K/1M" depending on the Context gauge setting), orange from 60 % and red from 85 %, so you see which agent is close to a hand-over without opening it. Nothing is shown when the CLI gives no figure.
  • Session info: the foldable Session trace section, under the context window gauge, is the turn-by-turn trace of the session (tool calls, bytes, context growth, running totals), see Session Trace.
  • Footer: the usage badge with the shortest available window, click for the Usage window. Since 2026-10-27 it opens centred in the app window, in three columns read as a path, with a step bar above them: 1 Overview ("What your CLIs have used"), 2 Control ("Act on your quotas right now"), 3 Optimize ("Fewer tokens for the same work"). The two right-hand columns have the same width. When the app window is too narrow for three columns, Optimize your usage moves under Manage your usage and the two steps share one column. The header holds the title, the Usage alerts switch and the refresh button (Refresh all providers). Since 2026-10-22 the title row also holds the Account / Per machine switch: Per machine swaps the gauges for what each of your computers spent, session by session (see Usage per machine).
  • Gauges refresh by themselves when a quota window resets: since 2026-10-01, a bar that shows a reset time is read again just after that time (then once more a minute later), so it drops back without waiting for the next periodic refresh or a click on Refresh. All providers whose bars carry a reset time; the phone shows the bars the desktop sends.
  • Column 1, Overview: CLI usage, the gauges, one section per provider, one header per account, Refresh {provider}, and Show this one in the status bar on a bar to pick the window it shows. On each account header (or on the provider header when it has a single account): the pin Show this account in the status bar. Pinned accounts also appear under Settings > Multiple accounts > Quotas in the status bar, with the Side by side / Compact choice once two are pinned. Under the gauges (Account view only), Insights into your usage (renamed from By project and agent on 2026-10-16; in this column since 2026-10-27): first the averages, one line per plan reading "1 full session ≈ 15.4% of the week": Average for your projects (your own sessions measured on this machine) and Average for other users (the community figures per provider and plan, for example Claude Max 20x, Claude Max 20x Fable only, Claude Max 5x), with More info opening the full Robin Hood window; then the For this project / For this agent split; then the Robin Hood card (Compare plans).
  • Column 2, Control: Manage your usage, the Temporary launch override card ("Your resources are running low." with Temporarily change model when a quota is nearly spent, Stop override while one is active, the only way to end one set to Until I stop it), the Quota management card that opens the quota rules (see Quota Rules), marked Recommended, and the Quota kick-off card. The old account failover switch is gone: it became quota rules.
  • Column 3, Optimize: Optimize your usage, one card per line: AI Suggestion, Adaptive Model and Every message (both marked Recommended), then the Vibe Coding Optimizer audit (Run the audit, only inside a project). Each setting card shows its state in words, a pill reading On or Off next to its name, and an active card is tinted green; its link reads Turn off or Turn on and opens the setting.
  • Provider tiles: since 2026-10-02 each tile of the provider picker (Add agent, Switch Provider, the temporary launch override) carries the footer gauge of that provider, the tile filled up to the percentage and the figure in its top-right corner, the same account and window as the footer pill. No reading, no gauge (never a made-up 0 %). The phone's Switch Provider sheet shows the same tiles, sent by the desktop.
  • Opening the panel scrolls to the provider the footer gauge was showing (the foreground agent's, else the first pinned account, else the most urgent provider).

How to use it

  1. Work as usual; the badge updates every few seconds. Orange means the context window is 60 % full, red 85 %: consider /compact or a fresh session.
  2. Click the badge. Session info shows the cumulative tokens, the cache hit rate (higher is better: cache reads cost roughly a tenth of fresh input) and the Context window fill of the last turn. The session id is copyable for a manual --resume.
  3. Under Tips to consume less, each tip has Fix this: an editable prompt you can send to the agent, copy, or save to the Prompt Library.
  4. Click the footer badge to see quota per provider and per account, with the reset time: the clock alone when it is today, "tomorrow 09:00" for the next day, and further away the days left first, then the date ("in 14 days, Nov 12, 09:00"), on the phone too. Under Insights into your usage, the averages compare what one full session costs of your weekly limit with what other users measure on each plan (the other users' group is folded by default, one click unfolds it, on the phone too), and For this project / For this agent splits the account's percentage across what ran on this machine, weighted by the estimated cost of each session; the figures are labelled as estimates.
  5. To keep several accounts in sight, click the pin on their headers. With nothing pinned the footer shows one figure, the account the foreground agent is spending. With pinned accounts, Side by side draws one pill per account (logo, percentage, filled gauge, the account name in the tooltip when the provider has several), Compact draws a single pill with the most-urgent pinned account and "+N"; hover it to list them all with a mini gauge. Any pill opens the same panel. With Side by side, drag a pill onto another one to change their order, as in the project list. A pinned account with no reading yet keeps a logo-only pill ("no reading" in the list); unpin the last one to get the single badge back.

Settings

  • contextMeter (global, Settings > Appearance > Context gauge): { display: "percent" | "tokens", capTokens: number | null }. Percent (default) shows the context fill as "34%", Tokens shows the tokens in the live window against the ceiling, "300K/1M". Target ceiling (capTokens, default Model window = null; presets 100K, 200K, 400K or Custom from 10K to 10M) makes the percent, the token ceiling and the orange/red colours measure against your own budget, for example 200K on a 1M model, so it can read over 100 %. Display only: the CLI still compacts at the model's limit, and a ceiling larger than the model's window is ignored. The Session info panel follows the same setting and recalls the real window under the bar. Synced on your account: every machine and the phone read the same gauge, and the phone can change it (Settings > Context gauge, presets only; a custom value typed on the desktop shows as its own option). Since 2026-10-26 (reported by Ben).

  • agentRowContextFill (global, Settings > Appearance > Context gauge > Gauge on each agent row, default off): also shows the gauge at the end of each open agent's row in the project's agent list, with the same figure, the same contextMeter display and target ceiling, and the same colours as the header. Synced on your account. Desktop only: the phone's agent rows show the model and its window size, not the fill.

  • usageBadgeWindow (global): which quota window the footer badge shows per provider (session, daily, weekly, monthly); unset = the shortest available.

  • usageBadgeAccounts (global, Settings > Multiple accounts > Quotas in the status bar): { pinned: ["<provider>|<account slot>", ...], layout: "row" | "compact" }; the order of pinned is the order of the pills (drag and drop in the footer). Empty pinned = the single badge of the account being spent. Machine-local, not synced to the account. Since 1.180.0.

  • usageAlerts (global, Settings > Notifications > Usage alerts): thresholds and channels of the bell on each bar, see Usage Alerts.

  • Quota breakdown per project and agent: opt-in from the beta panel (Settings > Beta), on the desktop; the phone shows it only when the desktop has it on.

  • Show or hide the footer badge: Settings > Interface elements (uiElements.footer.usage).

  • usagePace (global, Settings > Multiple accounts > Quota pace: work days, also reachable from Set work days in the pace card of a usage bar): { workDays: [0-6], byAccount: { "<provider>|<account slot>": [0-6] } }, 0 = Sunday. Default: all seven days, the marker is a continuous prorata of the window. With days off, the window is cut into local calendar days (midnight to midnight; the day the window opens counts whole, the reset day belongs to the next window) and each work day unlocks an equal share of the quota at midnight. Until 2026-10-02 the days were counted from the reset hour, so with a Thursday 14:59 reset Friday morning still read as the first day and the bar showed you ahead of pace for nothing. Own days on an account line gives that account its own days (a work subscription on weekdays, a personal one on weekends). nightWork (I also work at night (11 pm to 8 am), default off) makes the 5-hour windows left in a week run around the clock instead of 8 am to 11 pm; an account with own days has its own switch (nightByAccount). windowsAlert (Warn me before 5-hour windows are lost, in the pace card of a weekly bar of the Usage panel or the phone's pace sheet, default off) sends a usage alert (card, banner, phone, under the usage alerts master switch) once when every window left is needed and once when part of the week can no longer be spent, per weekly window. Synced on your account since 2026-10-19 (it used to stay on each machine): the first machine to sign in after the update seeds the account with its own value.

  • featureFlags.usagePace (global, Settings > Features > Quota pace, default on): turns the whole pace marker off (tick, pace line, card, the work-day setting, the phone's marker and the pace fields of usage_overview).

Agent tools (MCP)

  • agents_context (since 2026-11-16, reported by Tu): an agent reads its OWN context fill, the same figures as its header gauge, instead of guessing them from the conversation (agents asked to "hand over at 80%" used to think they were at 92% while the CLI said 186K of 1M). Answers usedTokens, windowTokens, percent, measuredAgainst (window, or target when the Context gauge has a target ceiling, then given in targetTokens), windowPercent (always against the model's window) and the model label when known. With to (an id from agents_list_live), it reads a teammate with a console in the same checkout, so a coordinator can tell when a worker should hand over. When the gauge shows nothing, it answers status: "unknown" with a reason (no live console, no turn measured yet, or a CLI that gives no reliable per-turn figure), never 0%. Nothing new is polled: it reads the figure the desktop already holds for the gauge, so the desktop app must be open.
  • usage_overview: read-only, anonymous. Per provider, whether it exposes a quota signal and, per signed-in account (account: its email or name; profile: the name it was given in Settings, empty for the CLI's own sign-in, which is marked systemAccount), the usage bars (percent used, window, reset label, machine-readable resetsAtIso; on weekly and monthly bars the pace: windowStartIso, windowSeconds, expectedPercentUsed, paceDelta, paceStatus, unusedBudgetExpiresSoon; on weekly bars dailyUsage, percentUsedBeforeTracking and, when the account has a session gauge, sessionWindows: windows left, full sessions needed, reachable and lost percent, status ok / tight / loss), plus a census of running agents by status and provider. Meant for "how close am I to a limit" and "what is running", never to enumerate agents.

Providers

  • Session info (tokens, cache, cost, files read): Claude Code and Codex, read from their local transcripts (~/.claude/projects/... or the account's directory for Claude, CODEX_HOME/sessions/... for Codex). The cache breakdown is a Claude billing feature. Since 2026-11-12 the counter and the cost include the agent's sub-agents (those of a workflow run too), which Claude Code and Codex write to files of their own: the context gauge, exchanges, tool uses and files read stay the main conversation's, since a sub-agent works in its own context window. Since 1.184.0 OpenCode agents have the badge too: OpenCode keeps its transcript in a database AgentsRoom cannot read, so the figures are pushed by the AgentsRoom plugin running inside OpenCode, with the input, output, reasoning (counted as output) and cache tokens and the cost OpenCode computes itself, the same numbers its TUI prints, non-zero on the flat-rate OpenCode Go plan as well. The agent's profile stats and the per-provider cost split of the Open space band pick them up. A /new in the OpenCode TUI resets the counter like /clear does for Claude. Antigravity, Grok, Mistral Vibe, Cursor and Aider show no badge.
  • OpenCode counts only what its plugin saw: the earlier turns of a resumed conversation are not recounted, and an OpenCode agent launched from the phone gets no plugin, so no figures.
  • Quota panel: every CLI whose usage AgentsRoom can read: Claude, Codex (since 2026-09-29 every signed-in Codex account is read on its own, with its own sign-in, from the usage endpoint the Codex CLI's /status reads, even when no agent has run on it; the figures of its last session stand in when that read fails, dated), Grok and Kimi through their own usage commands, and since 1.184.0 OpenCode Go through the subscription's usage endpoint, called with the key the OpenCode CLI already stores after /connect (three bars: 5h limit, Weekly limit, Monthly limit; no ghost terminal, so it works on Windows too). A pay-as-you-go OpenCode setup with no Go key shows nothing. Since 2026-09-23 the Z.AI Coding Plan used through OpenCode gets its own block under the OpenCode section, "Z.AI Coding Plan" with the plan level in brackets (5-hour and weekly bars), and OpenCode models show their plan next to the name ("glm-5.3 · Z.AI Coding Plan"). The footer gauge follows the plan the OpenCode agent really uses (the foreground agent, else the project's OpenCode agents when they all use one plan, else OpenCode Go), and stays empty rather than showing another plan's figure. Antigravity shows the 5-hour and weekly windows of each model pool, read from its own /usage panel (agy 1.1.11 or later, see Usage Alerts). A CLI with no usage source (Mistral Vibe or Aider, for instance) is simply not listed in the panel; only Claude keeps its section, so "not detected" stays visible.
  • Context window: sized from the model id, or from the CLI's own startup banner when the model is left on Default (so a Claude 1M session shows the right gauge).

Mobile

Present in part. The phone has a Usage screen with the same per-provider, per-account quota bars, reset times, pace markers and snapshot age (tap a weekly or monthly bar for the pace sheet: the same figures as the desktop card, the Day by day chart, the 5-hour windows before the reset block with its alert switch, and the work days and nights, which you can change from the phone; the line about windows that count or will be lost shows under the bar as on the desktop), and each agent row shows its cumulative tokens, model and window size in the spec strip, while the console header adds the context fill (percent or tokens, against the target ceiling, per the Context gauge setting). Since 1.184.0 the phone also shows the quota split: under each account of the Usage screen, a By project and agent block (For this project, For this agent, "of the current week" and the other windows), and under the Cost card of an agent's profile sheet the share that agent takes of its account's window, followed since 2026-10-23 by its share of the week. The header cost badge itself is desktop-only. The desktop computes the split and sends it over the encrypted relay; the phone replays nothing, and an agent or project with no measurable share shows nothing, never 0 %. In the bottom tab bar, the Activity label gives way to the same gauge as the desktop footer (threshold dot, provider logo, percentage) for the account of the agent in the foreground, as soon as the desktop has a figure to send. The per-session Session info panel with cache breakdown and tips is desktop-only, and so is account pinning: the phone has no status bar, its Usage segment already lists every account of every provider.

Limits

  • The colour follows the context window fill of the last turn (orange from 60 %, red from 85 %), not the cumulative token count. Red is a warning, not a throttle. A provider that gives no reliable per-turn figure shows no percentage, never 0 %.
  • The indicative cost is what the tokens would bill at raw API rates; on a subscription you never pay it, it is only the weight used to split the plan.
  • Usage from another machine or from the web is outside the split, so project and agent shares are floors, not totals; a model missing from the rate card is flagged.
  • Quota readings can be rate-limited by the provider's API; the panel says so and retries by itself.
  • Claude, Codex and Grok are read with the CLI's own sign-in, which only the CLI renews when it runs. Since 2026-10-05, when an account's session has expired AgentsRoom starts that account's CLI for a few seconds in a hidden terminal so it renews itself, then reads the quota again: right away when you click Refresh or Retry, otherwise in the background (at most every 30 minutes per account, three tries in a row). An account whose session cannot be renewed (signed out elsewhere, revoked) keeps saying the session expired: sign in to it again. The background renewal does not run in a development build. Cursor is not covered: its CLI has no quota panel to open.
  • Grok: when x.ai publishes a billing period without a percentage (a free account, or just after a weekly reset), the account shows no bar and reads as unavailable, never a fake 0 %. A bar whose window has already reset is dropped instead of showing last period's figure. Fixed on 2026-09-25.
  • OpenCode plans connected with a recent OpenCode (which keeps its keys in a local database) are read with the system sqlite3 command. Windows does not ship it: without it, or without an older auth.json, those plans show no bars.
  • Large transcripts (hundreds of thousands of lines) take a moment to parse when Session info is open.

Common questions

  • Can I see which agent's context is almost full without opening each one? Yes, since 2026-11-16 (reported by Tu): tick Settings > Appearance > Context gauge > Gauge on each agent row (off by default) and every open agent's row in the project's agent list shows its context fill, the same figure as its header gauge, turning orange at 60 % and red at 85 %.

  • Why did Session info show a different context percent than the header? Before 2026-11-16, Session info sized the window from the model saved on the agent, while the header used the model the console was really launched with (a bare opus launched as opus[1m] by the context default read 27 % there and 5 % in the header). The header, the agent row, Session info and agents_context now all read the same figure, against the window the CLI really runs and your target ceiling if you set one.

  • My agents think their context is almost full when it is not. Can they read the real figure? Yes, since 2026-11-16 (reported by Tu): tell them to call agents_context before applying a rule like "hand over at 80% of context". It returns the figures of their header gauge (tokens used, window size, percent, and your target ceiling when you set one in Settings > Appearance > Context gauge). A coordinator can read a teammate's figure with to. A CLI without a reliable figure answers "unknown" with the reason.

  • One of my Claude accounts vanished from the usage panel. Fixed on 2026-11-02 (reported by a user): an account whose sign-in could not be read was left out with no explanation. It now stays listed and says "This account's CLI session has expired. AgentsRoom renews it in the background. If the account stays unavailable, sign in to it again."

  • My Claude agent was cut at 200K although my default context window is 1M. Why? Fixed on 2026-10-26 (reported by Marian): a Claude agent with no context window chosen on it now launches with the default context window of the project, else of the account (Settings > AI providers > Claude), and its header gauge reads the same window. Only an explicit 200K choice on the agent caps it at 200K. Relaunch the agent to apply.

  • My Codex bars stayed frozen on yesterday's figures, even with Refresh. Fixed on 2026-09-26: a very long Codex session (a transcript past 50 MB) was skipped, so the bars came from an older session. Its latest quota reading is now read from the end of the file. Update AgentsRoom.

  • I have two Codex accounts but the panel shows one, and the footer shows the other account's percentage. Fixed on 2026-09-29: a Codex account had no reading until an agent ran on it. Every signed-in Codex account is now read on its own (its email appears on its header), and the footer follows the account you set as default or pinned. Update AgentsRoom, then click Refresh Codex. An account whose Codex sign-in has expired says so, and AgentsRoom renews it in the background (next question).

  • My quotas only update when I open and use the CLI, and two machines show different figures. Fixed on 2026-10-05 (reported by Nessaddam): the quota of an account is read with its CLI's sign-in, and a CLI renews that sign-in only when it runs, so an account nobody used for a few hours on a machine (Grok after 6 hours, Claude after a few hours, Codex after about 10 days) stopped updating there. AgentsRoom now starts the CLI of that account in a hidden terminal, just long enough to renew its session, then reads the quota again: at once when you click Refresh or the account's Retry, otherwise by itself within about ten minutes. If the account still says its session has expired after that, its sign-in is no longer valid: sign in to it again (Settings > Multiple accounts).

  • On my Mac, the Claude account says its session expired and Retry changes nothing, yet my Claude agents work. Fixed on 2026-10-14 (reported by Nessaddam): on macOS, Claude Code keeps its sign-in in the Keychain, but an old sign-in file can stay behind in ~/.claude (left by an older version, a container or a synced folder). AgentsRoom read that file first, saw a session expired long ago, and no renewal could refresh it. It now reads the Keychain first, like Claude Code itself. Update AgentsRoom, then click Refresh on Claude.

  • Can the header show the context in tokens rather than a percentage, or against my own limit? Yes, since 2026-10-26 (reported by Ben): Settings > Appearance > Context gauge. Pick Tokens to read "300K/1M", and a Target ceiling (100K, 200K, 400K or custom) to have the percent and the warning colours measure against that budget instead of the model's full window. It only changes the display, the agent still compacts at the model's limit.

  • My agent ran many sub-agents, but its token counter shows far less than the CLI. Fixed on 2026-11-12 (reported by Bennet): Claude Code and Codex write each sub-agent to a file of its own, and the counter only read the agent's main conversation. It now adds every sub-agent's tokens, and its cost, for Claude Code and Codex. An agent with hundreds of sub-agents catches up over the first minute after the app starts. The agent's stats and the per-machine usage follow.

  • Is the token count accurate? Yes for Claude and Codex: it is read from the per-message usage the CLI writes locally, no estimate. The dollar figure and the per-project split are estimates and say so.

  • How do I know how many tokens I have left? Subscriptions have no balance: providers meter rolling windows. The footer panel shows the percentage used per window and the reset time, and the session badge shows what predicts the wall.

  • Why is cache hit rate important? Cache reads are about ten times cheaper than fresh input. A low rate usually means the start of the prompt changes too often; the tips explain how to stabilise it.

  • Does it work for Codex, Grok, Cursor, OpenCode? Quota bars: yes for every CLI whose usage can be read (Claude, Codex, Grok, Kimi, Antigravity, OpenCode Go, Z.AI Coding Plan through OpenCode). Session info: Claude, Codex and OpenCode.

  • My OpenCode agent stayed at 0 tokens / $0.00. Update to 1.184.0: the figures are now pushed by the AgentsRoom plugin inside OpenCode. They still stay empty for an OpenCode agent launched from the phone, and on an OpenCode 2 build without --standalone support.

  • Where is the OpenCode Go bar? It appears once the OpenCode CLI holds a Go key (run /connect inside OpenCode). Without one, the provider has no section: nothing is read, nothing is shown.

  • Does anything leave my machine? No. Both meters read local files; the quota panel asks the provider's own usage endpoint with the account's credentials.

  • Can the footer show two accounts at once? Yes. Pin them from their header in the Usage panel: each pinned account gets its own gauge, side by side or in one compact pill that lists them on hover. Side by side, drag a pill onto another to reorder them. The pin on a bar chooses the window, the pin on an account header chooses the account.

  • I have both OpenCode Go and the Z.AI Coding Plan, which one does the footer show? The plan of the OpenCode agent you are working with. Each plan has its own block in the panel; pin one from its header to keep it in the footer.

  • My Grok gauge shows nothing, or "unavailable". x.ai sometimes returns the billing period without a percentage (free accounts, or right after the weekly reset). AgentsRoom then shows no figure rather than 0 % or last week's number; the bar comes back at the next reading that carries one.

  • Where did the buttons of the Usage panel go? Since 2026-10-27 the window has three columns: the gauges and Insights into your usage (with Robin Hood) under Overview, the override, quota rules and kick-off under Control, the AI Suggestion, Adaptive Model and audit cards under Optimize.

  • Can I be warned before a limit? Yes, every bar has a bell with 50 %, 75 % and 90 % thresholds by default, see Usage Alerts.

  • Am I spending my week too fast? Look at the tick on the weekly bar: left of it you are within budget. The line under the bar gives the gap in points; hover it for your average per day and the projection at the reset.

  • How much of my weekly limit did I use each day? Hover the pace tick or the pace line under a weekly bar of the Usage panel: the Day by day chart shows each day of the current window. On the phone, tap the bar in Activity > Usage. Days are recorded by the desktop from the moment it first reads the gauge (no history before that), and a day the desktop was closed is counted on the next day it reads the gauge. Agents get the same days from usage_overview (dailyUsage).

  • How many 5-hour windows do I have left this week? Will I lose tokens? Hover the pace tick or line under a weekly bar of the Usage panel: the 5-hour windows before the reset block gives the windows left, the full sessions the rest of the week needs, what you can still spend at best, and whether part of the week will be lost. The line under the bar only appears when every window counts or some quota will be lost. Turn on Warn me before 5-hour windows are lost in that block to get a notification. Windows are counted on your work days, 8 am to 11 pm unless you turn on I also work at night in Settings > Multiple accounts > Quota pace: work days. Accounts without a 5-hour gauge (Grok, Cursor) have no such count.

  • I only work on weekdays, the marker says I am over. Set your work days in Settings > Multiple accounts > Quota pace: work days (or Set work days from the pace card): with Monday to Friday, each work day unlocks 20 % and the weekend unlocks nothing. You can set different days per account.

  • Usage Alerts: the bell on each bar, a notification when a threshold is crossed.
  • Multiple Accounts: one usage section per signed-in account, and the accounts you can pin in the status bar.
  • Quota Rules: the Quota management block of the same panel.
  • Account Auto-Switch: moving running agents to another account, now a quota rule.
  • Adaptive Mode: a cheaper model when the best one is not needed.
  • Context Canary: what happens when a large context starts to hurt.
  • Project Statistics: time, prompts and cost per project.
  • Robin Hood: what one session costs of your week, opened from Insights into your usage.