Quota Rules

  • Desktop app
  • All plans

What it does

A quota rule watches one quota gauge of a provider (an account, a window, a threshold) and acts on its own when the condition is met: block some launches, send a launch to another account, launch on another provider, model or effort, run one of your triggers, or move the agents already running to another account. Examples: "at 99 % of the Claude session, keep scheduled agents from starting", "at 90 %, run new agents on a more economical model", "when the week reaches 90 %, run the cleanup brief", "when Claude reaches 99 % on any gauge, start new agents on Codex". Rules run while AgentsRoom is open. Since 2026-09-23 they are also what drives Account Auto-Switch: the old global switch became rules.

Video (1 min 17 s): Quota rules across two installations, shown in the real app. Save a shared rule, retrieve it in an independent installation on the same account, then change its threshold and see the first installation update.

Where to find it

  • Footer usage badge > Usage panel > Quota management card (marked Recommended) in the middle Control column, under Manage your usage, just under the Temporary launch override card (since 2026-10-27 the panel opens centred, in three columns: Overview, Control, Optimize). It reads "Set up a rule: block, redirect or trigger on a quota." when you have none, "N in force" otherwise, with a dot when a rule is acting right now.
  • Clicking it opens the Quota rules window (Quota automation), with New rule, the list of rules and the editor.
  • Settings > Multiple accounts, last row of Settings shared by all accounts: a Quota rules shortcut with the same "N in force" badge and a Manage rules button opening the same window (since 2026-09-28: a user looking for why accounts do not switch on their own looks in Settings first). The Settings search finds it ("quota", "rule", "switch").

How to use it

  1. Open Quota management and pick a template under Start from a template: Use another provider (Claude at 99 % on any gauge, new launches go to Codex; shown as "Claude → Codex"), Use a lighter model (90 %, change model or effort), Use another account (95 %, redirect the launch), Run a recovery trigger (90 %, run a trigger). Each card shows the real condition sentence of the rule it creates. Or press New rule.
  2. The editor draws the rule the way the list does, as a diagram you click: the Quota to watch box, an arrow carrying the threshold, and the Then box. Clicking one opens a small panel holding only that part's settings, so nothing else is on screen while you set it (since 2026-09-29; the old editor opened on a grid of providers and showed every field at once).
  3. Quota to watch: the provider, the Account (Most constrained looks at whichever account is closest to the wall, or one named account; when a rule acts on a launch and the account that launch uses is known and measured, the rule judges that account instead, so an agent pinned to an account at 10 % is not redirected because another account is at 91 %) and the Model group when the provider publishes a separate quota per group of models (Antigravity: Gemini Models and Claude and GPT models, plus a model's own weekly gauge such as Gemini 4 Argon on accounts that have one; Claude: a model's own weekly gauge; Codex: a model family; Cursor: Included usage, Auto usage, API usage), All groups by default.
  4. The arrow: Threshold from 1 to 100 % with reaches or drops under, and the Window (Any gauge, Session, Day, Week, Month, Pace; every new rule, blank or from a template, starts on Any gauge). Pace (since 2026-11-16) does not read the percent used: its threshold counts Points ahead of pace, from 1 to 50, on the weekly and monthly gauges (what you used minus what your work days allowed by now, the pace marker of the Usage panel, under the work days of Settings > Multiple accounts > Quota pace: work days). The most ahead gauge counts, reaches only, and the rule lifts by itself as time catches up, without waiting for the reset. It cannot move running agents.
  5. The two rare conditions are dashed + chips under the diagram instead of fields: Only near the reset (Any time, 10 min, 30 min, 60 min, 3 h) fires in the last minutes of the window, and Second condition (Required) asks a second window to hold too, since "20 % left" means little if the week is at 95 %. Once added they show as labels on the arrow.
  6. Then: pick the action, fill what it needs (Which launches, Account to use, Launch on with model and effort, Project and Trigger), and Save. The name is optional.
  7. Under the diagram, the rule is written out as a sentence, then the line Right now: says what it would do with the current reading (Will not fire, 42%, Firing now, 99%, No reading yet); a rule still missing something says so there too. Each row of the list carries the same status.
  8. Scroll down in the editor to Synchronize this rule with my other machines, below the diagram. It is checked by default. Save, then open Quota management on another installation signed in to the same AgentsRoom account: the rule appears without importing or recreating it. Edit its threshold there and save; the first installation retrieves the change on its next refresh, which can take up to 60 seconds.

The actions:

  • Block a launch: stops launches of that provider before they consume quota. Which launches: Every launch, Scheduled agents, Webhook calls or Manual launches. A blocked agent prints a red line "Quota rule "X": launch blocked" in its terminal; a blocked trigger does not open an empty tab and notifies you instead.

  • Redirect a launch: sends the launch to another account of the same provider. Only the account changes; provider, model and conversation stay. Account to use (since 2026-11-05): Most quota left takes the account furthest from its limit, Next to reset takes the account whose longest quota window (the week on most plans, not the 5-hour session) resets soonest and still has room, and A specific account is the account you name. With the first two, AgentsRoom chooses at each launch, so one rule covers all your accounts, including one added later. New rules start on Most quota left; rules that already name an account keep it. Only an account whose quota has been read can be chosen, and accounts you excluded from the spare pool never are. When no other account has room, the launch stays on its account and the next rule applies.

  • Change provider, model or effort: new launches run on the chosen provider, model and reasoning effort while the condition holds. Saved agent settings are untouched. Picking another CLI shows Different CLI: launches only: this action never changes the CLI of an agent already running. To do that, use Move running agents below.

  • Run a trigger: starts an existing trigger of a project, once per quota window.

  • Move running agents: moves the agents running on that account, once their turn is over. Another account is the default: another signed-in account, same provider, same conversation (see Account Auto-Switch). Which account (since 2026-11-05): Most quota left, the default and the previous behaviour, or Next to reset, which also decides where new launches go while the full account is set aside. With either choice, an account whose usage cannot be read right now (never measured, or a usage read that failed) comes after every measured account, so agents are not all sent to it (since 2026-11-12). Another CLI (since 2026-11-04) restarts them on the provider, model and effort you pick, with one target per source model if you want. A conversation cannot cross from one CLI to another: the new one reads what the old one wrote, carries on by itself if the last turn did not finish, and the agent stays on that CLI until you change it. While the rule holds, a new agent of the full CLI starts directly on the target CLI instead of starting on the full one and moving later (since 2026-11-07). The Continue on another CLI template starts from Claude to Codex at 99%.

  • Alternate providers (since 2026-10-06): no threshold. The new launches of the provider shown in the first box are shared out in turn between the providers of the Rotation (2 to 6 rows, each with its provider, its Account when that provider has several (Usual account = the one the launch would use anyway), and its model: Agent's model keeps the model the agent would have launched with (its settings, the ticket or the project), Default model is the default of the chosen CLI). Alternate by:

    • Number of launches: each row takes its launches in a row (×1, ×2…) then hands over. Claude ×1 then Codex ×1 is "one ticket out of two"; Claude ×2 then Codex ×1 is 2 for 1.
    • Quota used: each row keeps the launches until its own Gauge (Session or Week) has moved by its share (for example 10 % of the Claude session, then 10 % of the Codex week), then hands over. A gauge that resets also ends the turn. A provider that publishes no session window (some Codex plans only have a weekly limit) is measured on its week.
    • Most quota left (since 2026-11-07): no share and no turn to wait for. Each new agent starts on the row furthest from its limit, whichever row had the last launch: the highest of the gauges its model draws from decides (a full Fable week says nothing about a Sonnet agent). Rows within 1 point of each other take turns, so two balanced accounts alternate and a burst of launches does not pile up on one. A row at 99 % or more, never measured, with an expired session or set aside after a limit takes nothing; when no row can, the launch goes through unchanged. The Always the most quota left template fills in the accounts of Claude, or Claude and another provider when you only have one account.

    Which launches (rotation and Most quota left alike): Every launch, Backlog tickets (agents launched for a ticket), Scheduled agents, Webhook calls or Manual launches. Project: one project, or All projects. The rule card of the list reads "Next launch: Codex". Only brand-new agents are shared out: a running, restarted or resumed agent keeps its tool (it comes back on the provider the rotation gave it, with its conversation). A provider at 99 % or more skips its turn; when every row is full, launches go through unchanged. The agent's terminal prints a cyan line "Quota rule "X": this new agent runs on Codex (alternation)". Nothing is written on the agent's saved settings, and no notification is sent at each launch. The Alternate providers template creates Claude ×1 then Codex ×1.

Never pick an account above (since 2026-11-13, requested by a user): on Alternate providers (both modes and Most quota left), on Redirect a launch when Most quota left or Next to reset picks the account, and on Move running agents to another account. No limit (the default) keeps today's behaviour; 80%, 90% or 95% means that when the app CHOOSES an account for a new or moved agent, it skips any account whose session or weekly gauge (the highest one the agent's model draws from) has reached that value. Agents already running on an account keep using it up to the usual 99 % wall, and a console already on an account a redirect would pick stays there. When no account is under the ceiling, the rule does what it does when nobody has room: a rotation lets the launch through unchanged, a redirect hands over to the next rule, a move leaves the agents where they are. Move running agents already never picks an account at 90 % or more: the stricter of the two applies. An account never measured is not judged by the ceiling (each action keeps its own rule for it).

Which models (block, redirect and change actions, shown when the provider publishes model groups): Those of the reached gauge, the default of a new rule, only touches the launches whose model draws from the gauge that met the threshold: with Antigravity's Claude and GPT models gauge at 100 % and Gemini Models at 0 %, an agent on a Gemini model starts normally and only the Claude or GPT agents are blocked, redirected or moved to another model. All models touches every launch of the provider, which is how rules written before 2026-09-29 behave. To give each group its own fallback, write one rule per group: for example Claude and GPT models at 95 % runs its agents on Claude, Gemini Models at 95 % runs them on Codex.

Priority: rules apply in list order. At launch the first satisfied rule wins, whatever its action. From two rules each row shows Priority N; drag a row to reorder. Each row also has its enable switch, Duplicate, Edit and Delete. Duplicate (since 2026-10-06, desktop and phone) opens a full copy of the rule in the editor (name, conditions, every destination, enabled or not); nothing is created until Save, and Back or Escape drops the copy. The saved copy goes last in priority, and the original is left untouched.

Settings

  • quotaRules (global, edited from the Quota rules window): the array of rules, in priority order. Each rule holds a condition (provider, account, optional model group pool, window any, session, daily, weekly or monthly, comparator, percent, optional reset window and second condition) and an action (kind block-launch, reroute-account, adjust-launch, run-trigger or switch-running, launch scope, launchModels pool or all, target account, accountChoice most-quota or next-reset (the app picks the account: replaces the target account on reroute-account, ranks the accounts on switch-running, absent means most quota), provider, model, effort, project, trigger, and for adjust-launch an optional modelMap: one row per source model family with its own target model and effort, the action's model and effort being the "Other models" default; for split-launch a split { mode: count | quota | most-quota, slices: [{ provider, share, model?, effort?, window? }] }, an optional projectId, and the extra launch scope backlog). Empty means no rule.
  • quotaRules[].action.pickCeiling (per rule, Never pick an account above in the rule editor, desktop and phone): integer percent 50 to 99, absent = no ceiling (default). Accepted on split-launch, on switch-running to another account and on reroute-account with accountChoice.
  • usageAlerts (global, Settings > Notifications > Usage alerts): its channels (card in the app, desktop notification, phone) are the ones a rule uses to tell you it acted.

Agent tools (MCP)

  • quota_rules_list: every rule in priority order, with a one-line summary, plus the account ids each provider can target and the model groups known per provider (Antigravity gemini / claude-gpt, plus the pool of a per-model gauge such as gemini-4-argon taken from usage_overview; Cursor included / auto / api).
  • quota_rules_save: create one rule, or change only the fields passed on an existing one (ruleId); position moves it in the priority order. Every field is checked (provider with a quota, model group, gauge, percent, account, required destination) and the rule is re-armed for its window, like an edit made in the editor. condition.pool picks a model group, action.launchModels (pool or all) the launches concerned, action.accountChoice (most-quota or next-reset) lets the app pick the account of a reroute-account (send targetAccountId: null when it had one) or rank those of a switch-running, action.modelMap (adjust-launch) one target per source model family ([{ source: "fable", targetModel: "gpt-6-astra", targetEffort: "xhigh" }, …], a row without target keeps that family on its provider, null removes the table). action.kind: "split-launch" with action.split alternates providers ({ mode: "count", slices: [{ provider: "claude", share: 1 }, { provider: "codex", share: 1 }] }; in quota mode share is 1 to 100 points of the slice's gauge and window is session or weekly; in most-quota mode no share, each launch goes to the slice furthest from its limit, for example two claude slices on two accountId), action.launchScope may then be backlog, action.projectId limits it to one project; its condition only names the source provider. Since 2026-11-08 an unknown field is refused by name, and an empty string in place of an id (projectId: "") counts as no value. action.pickCeiling (integer 50 to 99, null removes it) sets Never pick an account above on a split-launch, a switch-running to another account or a reroute-account with accountChoice; anywhere else it is refused with the reason.
  • quota_rules_delete: remove one rule.
  • settings_get / settings_set still read or rewrite the whole quotaRules array, without the checks.
  • usage_overview: the per-account quota bars a rule reads; each bar carries the pool id a rule takes as condition.pool (null for a gauge of the whole account).

Providers

GitHub Copilot CLI has one monthly premium allowance bar for the account currently signed in to the CLI. It needs a CLI version that can report account quotas; unlimited or unavailable allowances have no percentage gauge. Its bar uses the same bells, threshold and reset alerts, and quota rules as the other providers. There is no AgentsRoom Copilot account profile or automatic account switch. The phone receives the same bar and can edit its quota rules.

Only providers that publish a quota can be watched: Claude, Codex, Grok, GitHub Copilot CLI, Kimi, Cursor, Antigravity, OpenCode (its plans OpenCode Go and Z.AI Coding Plan) and, since 2026-10-21, Command Code and Muse Code. Cursor, Antigravity, Command Code and Muse Code have one gauge for the whole machine (the CLI's own sign-in), not one per account, so a rule can watch them but has no second account to move their agents to: use Change provider, model or effort to send the next launches elsewhere when they are full. The editor names the remaining CLIs ("… publishes no quota level: it cannot be watched."): they have no gauge, so no rule can react to them.

A block only concerns the provider of the condition: "Claude full" never blocks Codex launches; write two rules for both. Redirect a launch and Move running agents to another account need another account of the same provider, so in practice Claude, Codex or Grok. Move running agents to another CLI works from any provider with a gauge. To cascade between providers (Claude full, then Codex, then another), write one Change provider, model or effort rule per provider: Claude at 99% launches on Codex, Codex at 99% launches on Z.ai. Since 2026-10-13 a launch sent to a provider that is itself over its threshold follows that provider's rule in turn, so with Claude and Codex both full a Claude agent starts on Z.ai. A block on the last provider of the chain blocks the launch, a redirect to another account of that provider uses that account, and the chain never comes back to a provider it already left. The terminal prints one line per rule crossed, one notification tells the whole chain, and a rule whose target is itself redirected reads "Firing now, 99% · then" followed by the provider the launch really ends on.

Mobile

The desktop and phone editors both offer Synchronize this rule with my other machines, checked by default. Rules follow your AgentsRoom account, including existing rules. Uncheck to keep a rule only on the current computer; its shared copy disappears from the others. A specific subscription is matched by a hash of its identity, never its local profile id or an email sent in plain text. When identity is unavailable, use the same profile name on each computer. A missing account stays inactive. Changes made offline retry after reconnection, and independent edits from two computers are merged without replacing the collection.

Edited from the phone since 2026-09-24: Activity > Usage segment > Quota management card opens the full-screen rules list and editor (the desktop executes what the phone edits), including the By source model table since 2026-09-29. Since 2026-09-28 a Quota rules card in Settings > Usage lands on that same segment. The phone keeps its own form, section by section: the clickable diagram is on the desktop only, and both edit the same rules. An agent launched directly from the phone still does not go through the launch-time actions (block, redirect, change model). The phone editor also shows Never pick an account above (since 2026-11-13), once the paired desktop knows it.

Ignore quota rules (2026-10-07)

Enable Ignore quota rules when creating or editing an agent, configuring a flash-agent profile, creating a trigger or editing a team. It is off by default: existing agents continue to follow the rules. The flash-agent launch menu also offers this choice below the provider list, near the launch settings. The option preserves the chosen provider, model and account, including for every step of a team, and skips launch blocking, redirection, rotation and automatic running-account switches. Provider limits still apply.

When a rule affects an agent, the notification keeps the compact quota-to-action diagram and a banner "A quota rule changed this launch." appears above its composer, with Manage rules and Ignore quota rules for this agent. Since 2026-10-08 that banner is a launch notice: it shows once per launch, for 6 seconds (hovering it pauses the countdown, clicking inside it keeps it open), and does not come back when you leave the agent and return; the next launch of the agent announces its own rule again. While the banner is on screen, the corner card announcing the same rule change is not shown a second time; the desktop notification and the phone push are unchanged. Ignore quota rules for this agent saves the choice for the next launch, without replacing the active conversation. Since 2026-10-26 the banner starts with what the rule changed for this launch: Planned, the provider, account (colour, logo and email) and model the agent would have started on, then Launched on, the ones it really started on. When a rotation lands on the account the agent would have used anyway, only Launched on is shown. Since 2026-10-29 that diagram is tighter, so it fits above a composer without pushing the conversation down, and it stays readable while the agent asks you a question (it is drawn above the question card, not inside the composer). The same option and banner (same 6 seconds, once per launch) are available on the phone through the desktop bridge; the phone also offers an override when launching an existing team. Team creation remains desktop-only.

Most constrained is a selection mode, not a pinned account. The editor now labels that mode explicitly and names the currently watched account separately. Account selectors refresh with settings and quota readings and keep configured accounts visible before their first reading.

Limits

  • The desktop app must be open: it reads the gauges and runs the actions.
  • A rule acts once per quota window, then re-arms at the reset. Editing a rule re-arms it. With Any gauge, the rule reads the most constrained gauge that meets the threshold (including the several per-model weekly gauges some providers publish), and two independent gauges can each fire it once.
  • The Use another provider template acts at launch only: agents already running stay on their CLI. Continue on another CLI is the one that moves them, and it also sends the new launches of the full CLI to the target CLI.
  • A redirect or a model change applies to the launch only; nothing is written on the agent.
  • A manual account pin on an agent stays above every rule.
  • Warn me is no longer offered for new rules: notifications belong to Usage Alerts. Older Warn me rules still work and stay editable.
  • Precision is that of the usage scan, so an action starts shortly after the threshold, not at the exact second. Every gauge is read on Windows too: Grok, Cursor, Kimi and OpenCode through their usage API, Antigravity through agy, Kimi and Grok falling back to the usage terminal when their API gives nothing.
  • Model groups: AgentsRoom tells which group a launch draws from by its model. Antigravity's own default model (no model picked) is a Gemini model, so it counts in Gemini Models. On Claude and Codex, a launch on the CLI's default model counts in every group, on the safe side. The Usage panel hides an Antigravity group still at 0 % everywhere, so a rule on that group shows No reading yet until the group is used.
  • Move running agents always moves every agent running on the saturated account, whatever its model group.
  • Most quota left and Next to reset on Redirect a launch do not apply to a Claude project hosted over SSH: an account only works there with its server token, so the launch stays on its account. Name the account with A specific account for those projects.
  • Moving to another CLI never happens mid-turn, and nobody moves when that CLI is switched off, absent from the computer the agent runs on (for a project hosted over SSH, the host, not this computer), or at the same threshold itself (so two crossed rules cannot bounce agents between two full CLIs). Since 2026-11-16 the rule's status says so: Firing now, 100% · Codex is full too, agents stay put (or is turned off, or is not installed, the last one only about this computer), on the desktop and on the phone. An agent driven by a live team run stays where the run pinned it. A CLI that has run out of quota cannot write a summary: the new one reads its screen, which is less tidy than a summary written by hand with Switch provider.
  • OpenCode: a rule can watch one plan (OpenCode Go or Z.AI Coding Plan) or Most constrained. At launch AgentsRoom does not know which plan the agent will use, so a block or model change set on one plan applies to every OpenCode launch.

Common questions

  • My plan has no 5-hour limit any more and agents can burn the whole week in a day. Can AgentsRoom put a brake back? Yes, since 2026-11-16 (asked by the team): a rule on the Pace window. The template Slow down when the week runs too fast blocks new launches while usage is more than 10 points ahead of the weekly pace; launches resume by themselves as time catches up. You can also redirect the launch to another account or a lighter model instead of blocking, or just be notified. Your work days (Settings > Multiple accounts > Quota pace: work days, or Set work days in the pace card of a usage bar) decide what "on pace" means.

  • New agents and moved agents land on an account at 96 % and have to move again soon. Can the app skip nearly full accounts when it chooses? Yes, since 2026-11-13 (requested by a user): open the rule (an Alternate providers rotation, a Redirect a launch with Most quota left or Next to reset, or Move running agents to another account) and set Never pick an account above to 95%. The app then never chooses an account whose session or weekly usage has reached 95 %, while agents already on an account keep going up to 99 %. Over MCP: quota_rules_save with action.pickCeiling: 95.

  • I moved an agent to another account by hand, and at its restart a rule put it back on the old one. Fixed on 2026-11-09: an account you pick yourself on an agent that an Alternate providers rule had assigned now takes it out of the rotation, and the restart keeps your account. A default account changed at the project, folder or global level keeps the rotation; a Redirect a launch rule still applies at every launch.

  • The CLI says my Claude account is at 100 %, but my rule never moved my agents. Fixed on 2026-11-02 (reported by a user): a rule only judged the gauge read from the provider's API, which can fail right at the wall. Two more sources now count. When Claude Code stops on the account's usage limit, AgentsRoom reads the gauges again and judges the rules at once; if no reading is possible, the account counts as full until the reset. And an account with no figure from the API is read through its CLI's /usage (Claude, Codex, Grok). An account that answers neither, with no agent stopped on it, still gives nothing to judge.

  • I have three Claude accounts. Do I need one rule per account to go round them? No, since 2026-11-05 (requested by a user): one Redirect a launch rule on Most constrained, with Account to use set to Most quota left or Next to reset. AgentsRoom picks at each launch, so adding or removing an account needs no edit. Add a Move running agents rule to move the agents already running too.

  • Can a rule always launch whichever of my two Claude accounts has the most quota? Yes, since 2026-11-07 (requested by a user): pick the Always the most quota left template, or Alternate providers with Alternate by set to Most quota left and one row per account. There is no threshold: every new agent is compared, and an account stays if it is the one with the most room. Accounts within 1 point of each other take turns. Running, restarted and resumed agents stay where they are, and a launch on an account the rule does not list is left alone.

  • What is the difference with Redirect a launch on Most quota left? Redirect a launch waits for a threshold: it only acts when the launch account reaches it, and only moves to an account still under it. It never compares two accounts both under the threshold, and it also applies to a restarted agent. Alternate providers on Most quota left compares at each new launch, with no threshold, and leaves running agents alone. Use the first as a safety net when an account fills up, the second to spend your accounts evenly.

  • Most quota left or Next to reset: which one? Most quota left favours stability: agents land on the account furthest from its limit. Next to reset favours using what you pay for: agents land on the account whose quota would be lost soonest, and it fills up sooner, so moves happen more often.

  • Can I pick the target account or limit "Move running agents" to one project? No: it always picks the account itself and applies to all projects. You choose how it picks: Most quota left or Next to reset. quota_rules_save refuses a target account or a project on this action, with a message saying what to use instead. Choosing another CLI is possible: set Another CLI in the editor.

  • Can an agent change CLI on its own when Claude is full? Yes, since 2026-11-04: Move running agents > Another CLI. Without that rule, nothing changes CLI on its own: a new CLI means a new conversation, so it stays your decision.

  • When does a full provider come back? In the provider picker, a tile at 90% or more shows its reset time under the name ("Resets 19:00"), and the percentage's tooltip gives it at any level. The Usage panel keeps the full detail.

  • My agent is pinned to an account that is far from its limit, yet a "Most constrained" rule sent it elsewhere. Why? Fixed on 2026-10-14: at launch, a Most constrained rule now looks at the account the agent actually launches on when that account's usage is known. It still falls back to the most constrained account when the launch account is unknown or not measured yet.

  • A rule says "Not synced with your other machines: the server refused this rule". Since 2026-11-08 a rule the account refuses stays on this computer and keeps working here, the list names the refused field, and your other rules still sync. Edit the rule to send it again; otherwise the app retries every 6 hours.

  • Is there a video that shows it? Yes: open the footer Usage badge, then Quota management. Scroll below the rule diagram to the synchronization checkbox. This real recording shows one rule retrieved and edited across two independent installations on the same account: https://youtu.be/BOUCdEYcKyA.

  • Can I make a second rule that looks like the first one? Yes: Duplicate on the rule's row opens a copy in the editor; change what differs and Save. The copy is added last in priority.

  • Can I alternate Claude and Codex, one ticket out of two, or 10 % of the Claude session then 10 % of the Codex week? Yes, since 2026-10-06, with the Alternate providers action: Number of launches for "one out of two" (or 2 for 1), Quota used for the percentages. Codex plans with only a weekly limit are measured on their week. Pick Backlog tickets and a Project to limit it to the tickets of one project.

  • Can I alternate two Claude accounts instead of two providers? Yes: put Claude twice in the Rotation and pick a different Account on each row (the field appears as soon as the provider has two signed-in accounts). In Quota used mode each row then reads the gauge of its own account, for example 20 % of the Perso session, then 20 % of the Pro session.

  • Which agents does the rotation skip? I launch with an agent tier (Fast, Powerful, Expensive agent) or pick an account on a backlog ticket. Since 2026-10-21, only an account picked by hand takes an agent out of the rotation: the account of a backlog ticket, the account saved on the agent, or the account picked in the flash-agent menu. That agent starts on its account. Since 2026-10-22, a rotation whose rows all name an account only takes launches on those accounts: with "account 1, then account 2", an agent launched on account 3 starts on account 3, untouched. Agent tiers and a provider picked in the flash-agent menu follow the rotation like any new agent.

  • What does "Agent's model" mean in the rotation? The model the new agent would have started on without the rule: the one of its saved settings, of the ticket or of the project default. Pick a model on the row to force one instead. For another provider, Default model is the default model of that CLI.

  • I restarted an agent that the alternation had sent to Codex. Will it come back on Claude? No. The rotation remembers which provider it gave each agent on this computer: a restart or a resume goes back to that provider with its conversation, and does not count as a new turn. The rotation itself (whose turn it is) stays on this computer. Rules synchronize through the AgentsRoom account unless their synchronization checkbox is unchecked.

  • My agents kept bouncing between two accounts that were both full. Fixed on 2026-10-02 (reported by a user). Two causes: the reset time read from a gauge drifts a little between two readings, and each reading looked like a new window, so Move running agents fired again; and the agents were moved even when no other account had room. A rule now treats readings within 30 minutes of the same reset as one window, and Move running agents leaves an agent where it is when no other signed-in account can take over.

  • A rule sent every launch away from Grok, then an agent started on Grok anyway although it was still at 100 %. Fixed on 2026-09-27: when a gauge can no longer be read before its reset (the provider's sign-in expired because no agent ran), rules keep judging on the last reading until the reset time, since usage cannot go down before then. A gauge with no known reset time is not held. Since 2026-10-05 the expired sign-in no longer waits for an agent: AgentsRoom starts that account's CLI in a hidden terminal so it renews itself, and the gauge reads again within minutes.

  • The editor only shows three boxes, where are the fields? Click one: the quota box, the threshold on the arrow and the action box each open their own panel. Only near the reset and Second condition are the + chips under the diagram. Nothing was removed on 2026-09-29, only put behind the part it belongs to.

  • Where did the account auto-switch toggle go? It became quota rules on 2026-09-23. If it was on, AgentsRoom created two rules per provider with a spare account, "Keep working when an account runs out (Session)" and "(Week)", at 99 % with Move running agents. Edit, disable or delete them like any rule.

  • Can I watch Cursor or Antigravity? Yes, since their gauge appeared in the Usage panel. It is one gauge per machine, so "move running agents" and "use another account" have no other account to pick for them.

  • Does a scheduled or team launch respect the rules? Yes. A scheduled trigger is stopped before any agent starts. A trigger that runs a team is judged on the provider and account of the team's first agent, and every agent of that run keeps the run's origin (scheduled or webhook) for the Which launches scope; a blocked team run stops with "Quota rule "X": run stopped". Only Block a launch stops a run: the other actions only change where a step runs.

  • My team run stopped with "Quota rule: run stopped" although my rule only changes the provider. Fixed on 2026-10-09 (reported by a user). When a step pinned to a provider above the threshold came back a second time (a review sending work back, for example), its agent, already moved to the rule's provider, was restarted for nothing, and the run was cancelled when no visible terminal could take that restart (project not on screen, terminals in another window, app starting). A step now keeps the agent the rule already moved, with its conversation, and Change provider, model or effort or Use another account never cancel a run: an agent still on the full provider is restarted on the rule's target instead.

  • A rule alternates two accounts, but every agent shows the colour of my default account. Which account did it really use? Fixed on 2026-10-26: the account dot on the avatar (agent list and terminal header, desktop and phone) read the agent's saved settings instead of the account the rule started it on. It now shows the account the agent really runs on, and its tooltip says "Launched on this account by a quota rule, instead of ..." with the planned account. The banner above the composer shows Planned and Launched on, each with its account colour, provider logo and email.

  • My agent stayed on a full account after saying it had reached its limit, and the rule never switched it. Fixed on 2026-10-29: a switch-running rule gave up for the rest of the window as soon as its first attempt found no console or no free account, and it also missed an account whose login is shared by two slots (the same Claude account in two places). It now retries at every reading until the switch really happened, follows every slot of the watched login, and no longer mistakes an old prompt for a turn in progress. Notifications and triggers still fire once per window.

  • Two accounts are full, my "any account" rule moved the agents of one and left the others failing on "You've hit your 5-hour limit". Fixed on 2026-11-12 (reported by a user). A rule watching Any account only read the most constrained account, so when two accounts were full at once (one of them refused by its CLI while its usage could not be read), the agents of the second one were never moved. Move running agents now moves the agents of every account that meets the rule, keeps each of those accounts aside until its own reset, and a rotation (Split launches) skips an account that is set aside or that its CLI just refused. An account whose usage merely cannot be read is not treated as full.

  • My rule moves running agents to Codex, but a new Claude agent still opened on Claude, and agents of my SSH project never moved. Fixed on 2026-11-07 (reported by a user). A Move running agents > Another CLI rule only acted on agents already running, so a new agent started on the full CLI. It now starts directly on the target CLI while the rule holds. Agents of a project hosted over SSH were also left alone when the target CLI was not installed on this computer, although they run on the host: they now move like the others.

  • The quota banner above my agent's composer disappeared, where is it? It is shown for 6 seconds, once per launch. To see or change the rule afterwards, open Quota management from the footer Usage badge.

  • Two rules match, which one wins? The higher one in the list. Drag to change the order.

  • Will a 90 % rule fire every ten minutes? No, once per window.

  • What does "Any gauge" watch? Every gauge of the chosen account (session, day, week, month, per-model weeks): the rule fires as soon as one of them reaches the threshold. Pick a single window when only one matters.

  • Where did the Pause scheduled agents template go? It is no longer among the template cards; build the same rule with New rule, Block a launch and Which launches set to Scheduled agents.

  • Does "Claude full" block my Codex agents? No, only launches of the watched provider.

  • When Claude overflows to Codex, can Fable go to GPT-6 Astra and Sonnet to GPT-6 Luna instead of one model for everything? Yes, since 2026-09-29. In Change provider, model or effort, set Target model to By source model: one row per model of the watched provider (Fable, Opus, Sonnet, Haiku), each with its target model and reasoning effort on the fallback provider, pre-filled by capability tier (Fable to Astra, Opus to Sol, Sonnet to Luna). Other models is the default row, Do not redirect keeps a model on its provider, and a version alias such as Opus 5.5 follows the Opus row. Same model for all is the previous behaviour, and rules written before keep it. Since 2026-10-06 Target model is the first field of the action, a full-width two-way switch with By source model first, and it is the default of every new rule and every new change action; existing rules and their copies keep the mode they had. In the rule diagram, such a rule's action box reads By source model instead of naming one model, and hovering an action that sends launches to another provider names the account they will use there (that provider's default account).

  • Antigravity: my Claude and GPT gauge is full but Gemini still has room. Will a rule also reroute my Gemini agents? Not with Which models set to Those of the reached gauge (the default of a new rule): only the agents on a Claude or GPT model are rerouted. Pick the group under Model group to give each group its own fallback. A rule written before 2026-09-29 keeps All models until you change it.

  • Antigravity: my Gemini 4 Argon weekly gauge is full. Will a rule on Gemini Models reroute my Gemini Flash agents? No. Argon's own weekly gauge is a separate model group (Gemini 4 Argon): a rule on Gemini Models only reads the shared Gemini budget, and a rule on Gemini 4 Argon with Those of the reached gauge only touches the agents launched on an Argon model. Agents launched on the CLI's default model (a Gemini Flash) are not affected by the Argon gauge.