Capture
One read of Claude Documentation
5 pages moved out of 216 read.
claude-tag/admins/troubleshooting Changed · +13 / -13 lines
from line 136
Claude replies in the channel: -> Claude doesn't respond in channels that include guests. You can remove the guests from this channel (Channel details -> Members -> filter by "guests"), or a claude.ai organization owner can allow it here. +> Claude doesn't respond in channels that include guests. You can remove the guests from this channel (Channel details -> Members -> filter by "guests"), or a claude.ai organization owner can allow it in Claude Tag settings under Advanced -> "Allow Claude to work in channels with guests". -In the message, "here" is a link to the guest setting described below. The role it names is a claude.ai organization owner, not a Slack admin. +In the message, "Claude Tag settings" is a link to the admin page where the guest setting described below lives. The role it names is a claude.ai organization owner, not a Slack admin. **What it means**
from line 346
> This workspace isn't set up for Claude Tag yet. A workspace admin can run `@Claude connect`, or set it up here. -It ends with a footnote that routes people looking for [the earlier Claude in Slack](/docs/claude-tag/concepts/glossary#the-earlier-claude-in-slack) to that product's own setup guide. The reply varies with the sender: someone who isn't a Slack workspace admin is told to ask their Claude workspace owner to run `@Claude connect`, without the settings link. +The reply varies with the sender: someone who isn't a Slack workspace admin is told to ask their Claude workspace owner to run `@Claude connect`, without the settings link. **What it means**
from line 426
> Claude is disabled in this channel. Your admin can re-enable it here. -Only the first sentence is fixed. A sender who isn't a Slack workspace admin is told to ask their Claude workspace owner to re-enable it, without the settings link. +Only the first sentence is fixed. A sender who isn't a Slack workspace admin is told to ask their Claude workspace owner to re-enable it, with a link to the Claude Tag product page instead of admin settings. **What it means**
from line 517
Claude replies in the DM: -> Your Claude account is connected, but it doesn't have access in this organization — usually this means your admin hasn't assigned you a seat that includes Claude Code. Ask them to add one, then mention me to retry. +> Your Claude account is connected, but it doesn't have access in this organization yet, usually because it needs a seat that includes Claude Code. A Claude admin can add one in your organization's settings. Once they do, mention me here and I'll pick this back up. **What it means**
from line 573
When Claude can name the cause, it posts one of these instead: -| Message | Cause | -| ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| "Hit the session rate limit — try again in a few seconds." (or "in \~Ns" when Claude knows the wait) | Too many sessions started at once; wait, then mention Claude again | -| A message naming a specific repository that isn't available or isn't configured | The repository isn't granted for this channel; see [GitHub doesn't work in this channel](#github-doesn%E2%80%99t-work-in-this-channel) | -| "That environment or repo isn't configured for Claude Code. Check claude.ai/code and try again." | The scope's pinned environment isn't set up; see [Channel sessions use the wrong environment](#channel-sessions-use-the-wrong-environment-or-can%E2%80%99t-find-one) | -| "Claude is having trouble starting sessions right now. Try again in a minute." | The service that runs sessions is briefly unavailable; retry | -| "You don't have permission to start a session here." | A permission check refused to start the session; when Claude knows which check failed, the message names it | +| Message | Cause | +| -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| "Hit the session rate limit — try again in a few seconds." (or "in about Ns" when Claude knows the wait) | Too many sessions started at once; wait, then mention Claude again | +| A message naming a specific repository that isn't available or isn't configured | The repository isn't granted for this channel; see [GitHub doesn't work in this channel](#github-doesn%E2%80%99t-work-in-this-channel) | +| "That environment or repo isn't configured for Claude Code. Check claude.ai/code and try again." | The scope's pinned environment isn't set up; see [Channel sessions use the wrong environment](#channel-sessions-use-the-wrong-environment-or-can%E2%80%99t-find-one) | +| "Claude is having trouble starting sessions right now. Try again in a minute." | The service that runs sessions is briefly unavailable; retry | +| "You don't have permission to start a session here." | A permission check refused to start the session; when Claude knows which check failed, the message names it | **What it means**
claude-tag/concepts/how-it-works Changed · +11 / -2 lines
from line 141
Three ideas recur across this page and the rest of these docs. * **Agent identity**: in channels, Claude acts under its own service accounts that an admin provisions, not as the person who asked. What it can reach is set per channel, so everyone in a channel works with the same access. See [How agent identity works](/docs/claude-tag/concepts/agent-identity). -* **Scheduling and long-running work**: a task can run on a schedule, trigger on a repository event, or keep going across many turns in one thread. The same channel access applies whether a person or a schedule started it. See [Set up routines](/docs/claude-tag/users/proactivity). +* **Scheduling and long-running work**: a task can run on a schedule, follow a pull request and act when it changes, or keep going across many turns in one thread. The same channel access applies whether a person or a schedule started it. See [Set up routines](/docs/claude-tag/users/proactivity). * **Memory**: what Claude learns in public channels is saved as workspace memory that any channel can use; private channels keep their own. See [What Claude remembers](/docs/claude-tag/users/memory). ## Lifecycle of a request
from line 221
### What survives between replies -The thread is durable; the sandbox is not. When a session is idle, its sandbox is released, and it is rebuilt when the next message arrives. +A thread is durable, but the sandbox behind it is not. Durable means the thread, and everything Claude read and said in it, stays in Slack and stays available to the session for as long as the thread exists. The sandbox is the computer where Claude runs commands and keeps working files for a task. A few minutes after a session finishes its turn, Anthropic releases its sandbox, and the same session resumes in a fresh one when the next message arrives. A thread's session keeps resuming this way for as long as people use the thread. Claude replaces it with a new session in two cases. +| When | What Claude does | +| :-------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------- | +| Someone sends [`@Claude !restart`](/docs/claude-tag/users/commands#restart-a-stuck-or-wrong-context-session) | Archives the session right away and starts a fresh one that rereads the thread | +| The session [gets stuck and fails](/docs/claude-tag/users/troubleshooting#claude-reacted-or-started-thinking-then-never-replied) | Starts the replacement when the next message arrives in the thread | + <img className="block dark:hidden" src="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/diagrams/session-lifecycle.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=9a56231787b03f179e8d552d887778fc" alt="Timeline with two lanes. The Slack thread lane is one continuous bar that persists from the moment a task starts. The sandbox lane below it is segmented, built when the task starts, released while the thread goes quiet, and rebuilt fresh when someone replies." width="1000" height="270" data-path="images/claude-tag/diagrams/session-lifecycle.svg" /> <img className="hidden dark:block" src="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/diagrams/session-lifecycle-dark.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=0693a90b98baa729dcacfd35261f6494" alt="Timeline with two lanes. The Slack thread lane is one continuous bar that persists from the moment a task starts. The sandbox lane below it is segmented, built when the task starts, released while the thread goes quiet, and rebuilt fresh when someone replies." width="1000" height="270" data-path="images/claude-tag/diagrams/session-lifecycle-dark.svg" />
from line 240
| Files that exist only in the sandbox | No. Claude recreates them if asked. | For long tasks, ask it to push branches and post drafts as it goes, so deliverables are saved somewhere durable while the work is still running. See [Good habits](/docs/claude-tag/users/good-habits#give-every-task-a-definition-of-done). + +The channel's own session, the one that handles top-level messages outside any thread, lives longer than a thread's. Claude replaces it with a fresh one when a top-level message arrives after about an hour with no top-level activity, when the session is about a day old, or when the channel's configuration has changed since the session started. Channel memory and the channel's history are unaffected, so the only visible effect is that Claude no longer carries what the previous session had been working on. + +Claude also stops reading a channel's top-level messages once about 100 of them have arrived since it last posted or replied there. An `@Claude` mention in the channel starts it reading again; see [When Claude stops reading a channel](/docs/claude-tag/users/when-claude-responds#when-claude-stops-reading-a-channel). These thresholds are defaults and can change, so treat the numbers as approximate. ### Channel and workspace memory
claude-tag/users/getting-started Changed · +20 / -9 lines
### Files you attach
from line 77
After you've handed Claude a task, the first question is what it has to work with. The short version: it reads the thread you tagged it in, it can search your workspace's public channels, and anything beyond Slack depends on what your admin connected. -| What you give Claude | Can Claude read it? | -| :----------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| Messages in this thread | Yes. Mentioning it mid-thread also gives it the thread's earlier messages | -| An image or screenshot you attach | Yes | -| Other public channels in your workspace | By searching only, the same way a person searches Slack; Claude can find a message by keyword but can't read a channel's full history unless it's been added there | -| Private channels and DMs | Only from inside them. Adding Claude to a private channel lets it work there, but the channel stays unreadable from any other channel or DM. | -| A link you paste, like a Google Doc or a webpage | Only if your admin allowed that site for this channel. If not, Claude tells you it can't reach it. For files in your personal Drive or Google account, DM Claude instead; [a DM uses your own connectors](/docs/claude-tag/concepts/agent-identity#direct-message-channels) | -| A Slack canvas | No | -| A message you edited after sending | Yes. Each edit sends Claude a note showing the text before and after the edit. Claude reads the note but doesn't act on it, so say a correction in a new reply. Deleting a message doesn't notify Claude | +| What you give Claude | Can Claude read it? | +| :---------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Messages in this thread | Yes. Mentioning it mid-thread also gives it the thread's earlier messages | +| A file you attach (image, screenshot, PDF, or another type) | Yes, up to a size limit that depends on the file type. See [Files you attach](#files-you-attach) | +| Other public channels in your workspace | By searching only, the same way a person searches Slack; Claude can find a message by keyword but can't read a channel's full history unless it's been added there | +| Private channels and DMs | Only from inside them. Adding Claude to a private channel lets it work there, but the channel stays unreadable from any other channel or DM. | +| A link you paste, like a Google Doc or a webpage | Only if your admin allowed that site for this channel. If not, Claude tells you it can't reach it. For files in your personal Drive or Google account, DM Claude instead; [a DM uses your own connectors](/docs/claude-tag/concepts/agent-identity#direct-message-channels) | +| A Slack canvas | No | +| A message you edited after sending | Yes. Each edit sends Claude a note showing the text before and after the edit. Claude reads the note but doesn't act on it, so say a correction in a new reply. Deleting a message doesn't notify Claude | The fastest way to find out for your channel is to ask: `@Claude can you read the doc I just linked?` gets you a yes or a "that site isn't allowed here." + +### Files you attach + +Claude reads images and PDFs directly. It puts any other file type in its working files and opens it from there when the task needs it. Claude accepts files within these limits. + +* **Images**: up to about 3.75 MB each +* **PDFs**: up to 5 MB each +* **Other files** (spreadsheets, code, archives, documents): up to 100 MB each +* **Number of files**: up to 5 per message. Claude ignores any beyond the fifth. + +Claude can't read an image or PDF over its limit and answers from the rest of your message. To hand Claude a larger image or PDF, resize the image, split the PDF, or paste the text. <Note>Slack doesn't expose personal account settings (your sidebar, notification preferences, channel membership, or DMs between you and other people) to apps. If you want help organizing channels, paste or screenshot the list and Claude can propose a scheme you apply yourself.</Note>
claude-tag/users/troubleshooting Changed · +73 / -53 lines
### I hit repeated API server errors ### I hit API rate limits ### I got disconnected partway through ### A session link Claude posted shows a not-found page ### I hit repeated API server errors and stopped after retrying ### I hit API rate limits and stopped after retrying ### I lost the connection to this session's container mid-turn
from line 106
**What you see** -Mentions in a channel shared with another company get no reaction and no reply, ever. +Mentions in a channel shared with another company get no answer. A direct mention gets a short notice that Claude doesn't respond there; anything else gets nothing. **What it means** -Claude doesn't operate in Slack Connect channels, the ones shared with another company. This holds regardless of admin settings; mentions there are dropped without a reply. See [externally shared channels](/docs/claude-tag/admins/restrict-access#externally-shared-channels). +Claude doesn't operate in Slack Connect channels, the ones shared with another company. This holds regardless of admin settings. A direct mention gets the reply "This channel is shared with another organization through Slack Connect, and Claude doesn't respond in Slack Connect channels yet." Other messages there are dropped without a reply. See [externally shared channels](/docs/claude-tag/admins/restrict-access#externally-shared-channels). A channel shared across workspaces inside your Enterprise Grid isn't silent; what happens there depends on how those workspaces connect to Claude. When every workspace in the channel belongs to your one Claude organization, Claude answers, but with only your organization's default access and settings, so a repository or an instruction set up for that channel doesn't apply. A notice in the thread points this out from time to time. When the workspaces are connected to different Claude organizations, you see "This channel is shared among several Claude workspaces, so Claude cannot respond here" instead of an answer.
from line 144
Claude replies in the channel: -> Claude doesn't respond in channels that include guests. You can remove the guests from this channel (Channel details -> Members -> filter by "guests"), or a claude.ai organization owner can allow it here. +> Claude doesn't respond in channels that include guests. You can remove the guests from this channel (Channel details -> Members -> filter by "guests"), or a claude.ai organization owner can allow it in Claude Tag settings under Advanced -> "Allow Claude to work in channels with guests". **What it means**
from line 230
The messages in this section mean a session started and then stopped partway through. In most cases the work isn't lost, and the same thread picks up where it stopped. Each entry says whether anything needs redoing. -### I hit repeated API server errors and stopped after retrying +### I hit repeated API server errors **What you see** Claude posts in the thread: -> I hit repeated API server errors and stopped after retrying. Mention me to continue. +> I hit repeated API server errors. I'll retry automatically in about 2 minutes — no need to do anything. Mention me to retry sooner. -The related messages "I hit repeated 529 Overloaded errors (the API is at capacity) and stopped after retrying. Mention me to continue." and "The API request timed out and I stopped after retrying. Mention me to continue." behave the same way. +The related messages that start "Claude is over capacity right now" and "I hit API rate limits" behave the same way. The wait Claude names grows with each retry. +If the retries run out, or the session isn't a thread session, the message ends "and stopped after retrying. Mention me to continue." instead. "The API request timed out and I stopped after retrying. Mention me to continue." and "An API server error cut my last response short, so it may be incomplete. Mention me to continue." always take that form. + **What it means** -The API serving the session returned repeated errors, so Claude stopped rather than keep retrying. The work isn't lost. +The API serving the session returned repeated errors. The work isn't lost. When the message says Claude will retry automatically, the same conversation wakes again on its own, up to three times; a newer message from you in the thread cancels the pending retry. **How to resolve** -Mention Claude in the same thread; it picks up where it stopped. +Nothing, when the message says Claude will retry automatically; wait for it. Mention Claude in the same thread to retry sooner, or when the message asks you to. -### I hit API rate limits and stopped after retrying +### I hit API rate limits **What you see** Claude posts in the thread: -> I hit API rate limits and stopped after retrying. Wait a moment, then mention me to continue. +> I hit API rate limits. I'll retry automatically in about 2 minutes — no need to do anything. Mention me to retry sooner. +When the retries run out, the message is "I hit API rate limits and stopped after retrying. Wait a moment, then mention me to continue." + **What it means** The Claude API rate-limited your organization's traffic partway through the turn. The work isn't lost. Rate limits are about momentary request rate, not accumulated usage: a single task makes many API requests in short bursts, so this can appear on an organization's very first request. It isn't the channel spend limit, and it doesn't mean anything is misconfigured.
from line 266
**How to resolve** -Wait a moment, then mention Claude in the same thread; it picks up where it stopped. If it recurs constantly across channels, the organization's sustained traffic is above its rate limits; an admin can stagger heavy use or contact their account team about limits. +Wait for the automatic retry, or wait a moment and mention Claude in the same thread; it picks up where it stopped. If it recurs constantly across channels, the organization's sustained traffic is above its rate limits; an admin can stagger heavy use or contact their account team about limits. If your message mentions a spend limit instead, that's a different problem; see [You've reached a Claude Tag spend limit](#you%E2%80%99ve-reached-a-claude-tag-spend-limit).
from line 292
Claude posts in the thread: -> Claude couldn't clone a repository for this session. Mention Claude in this thread to retry. +> Claude couldn't clone a repository for this session. This can be temporary (for example a GitHub rate limit) — mention Claude in this thread to retry in a few minutes. If it keeps happening, this session may lack access to a repository it needs, or its credentials or integration may need to be reconnected. **What it means** -The clone failed when the session started. A one-off failure is transient; the same repository failing every time usually means it isn't granted for this channel. +The clone failed when the session started. A one-off failure is transient; the same repository failing every time usually means it isn't granted for this channel, or the connection it depends on needs to be reconnected. **How to resolve** -Mention Claude in the same thread to retry. If the same repository fails every time, send your admin [the GitHub access entry](/docs/claude-tag/admins/troubleshooting#github-doesn%E2%80%99t-work-in-this-channel). +Wait a few minutes, then mention Claude in the same thread to retry. If the same repository fails every time, send your admin [the GitHub access entry](/docs/claude-tag/admins/troubleshooting#github-doesn%E2%80%99t-work-in-this-channel). -### I lost the connection to this session's container mid-turn +### I got disconnected partway through **What you see** Claude posts in the thread: -> I lost the connection to this session's container mid-turn — the work I was doing may not have finished. Mention me to resume. +> I got disconnected partway through and may not have finished. Reconnecting and resuming automatically — usually within a few minutes, though a slow recovery can take much longer. Mention me if I don't follow up. +When Claude reconnects, it edits that message to "I reconnected and I'm carrying on where I left off. No need to mention me." When automatic recovery isn't armed, the message is "I got disconnected partway through and may not have finished. Mention me to pick up where I left off." instead. + You can see it in a thread where you're working with Claude, including a direct-message thread; Claude doesn't post it in a channel it's only watching or from a routine. **What it means**
from line 320
**How to resolve** -Mention Claude in the same thread. Claude resumes there and continues from the conversation; ask it to check on the step it was working on and redo anything that didn't finish. If the same notice comes back, the underlying problem hasn't cleared yet. Wait a few minutes and mention Claude again. +Wait for the reconnect message, or mention Claude in the same thread when the message asks you to. Claude resumes there and continues from the conversation; ask it to check on the step it was working on and redo anything that didn't finish. If the same notice comes back, the underlying problem hasn't cleared yet. Wait a few minutes and mention Claude again. ### Something went wrong and I couldn't finish this turn
from line 402
Verify what stuck by asking what it remembers about the channel. See [What Claude Tag remembers](/docs/claude-tag/users/memory). +### A session link Claude posted shows a not-found page + +**What you see** + +You open a link to a session on claude.ai that Claude posted in Slack, such as the "open the session" link in a routine's completion message, and claude.ai shows a not-found page instead of the session. + +**What it means** + +A session Claude ran from a channel belongs to Claude's own identity rather than to the person who asked, so claude.ai shows it only to accounts in the Claude organization paired with the workspace, and then only to people who could see the conversation in Slack. Any workspace member can open a session from a public channel; a session from a private channel opens only for members of that channel and the person who started it. Anyone else sees not-found rather than a permission error. + +**How to resolve** + +Sign in to claude.ai with the account that belongs to the organization paired with your workspace. claude.ai matches you to your Slack identity through a connected Slack account or, failing that, through the email address on your Claude account, so if your Claude email differs from your Slack email, connect your Slack account first; DM `@Claude` and it prompts you. If the session came from a private channel, ask to be added to the channel. + ## Access and connections ### A connection my admin added isn't showing up
from line 523
Claude posts in the thread: -> You've reached a Claude Tag spend limit. Org admins can raise it in claude.ai admin settings. Once the limit is raised, mention me to retry. +> You've reached a Claude Tag spend limit. A Claude.ai organization owner can raise it in Claude.ai admin settings. Once the limit is raised, mention me to retry. You may also see a heads-up before you hit the limit. It starts "Heads up — your organization has used *N%* of its monthly Claude Tag spend limit." for the organization limit, or "Heads up — this channel has used *N%* of its monthly Claude Tag spend limit." for a channel limit. **What it means** -Usage hit a cap an admin set, either for the whole organization or for this channel. A rate limit looks similar but is a different problem, and raising the spend limit doesn't clear it. If your message says "Hit the session rate limit — try again in a few seconds." (or "in \~Ns" when Claude knows the wait), too many sessions started at once. Wait a moment, then mention Claude again. +Usage hit a cap an admin set, either for the whole organization or for this channel. A rate limit looks similar but is a different problem, and raising the spend limit doesn't clear it. If your message says "Hit the session rate limit — try again in a few seconds." (or "in about Ns" when Claude knows the wait), too many sessions started at once. Wait a moment, then mention Claude again. **How to resolve**
from line 564
Claude replies in the DM: -> Your Claude account is connected, but it doesn't have access in this organization — usually this means your admin hasn't assigned you a seat that includes Claude Code. Ask them to add one, then mention me to retry. +> Your Claude account is connected, but it doesn't have access in this organization yet, usually because it needs a seat that includes Claude Code. A Claude admin can add one in your organization's settings. Once they do, mention me here and I'll pick this back up. The Claude app's **Messages** tab and Slack's assistant panel both count as DMs even though neither looks like one, so this message can appear when you thought you were using a channel.
claude-tag/users/when-claude-responds Changed · +20 / -7 lines
## Messages from other apps and bots
from line 12
Whether Claude replies to a message without an @-mention depends on where you send it. -| Where you write | Replies without an @-mention? | -| :---------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| A DM with Claude | Always. Every message is addressed to Claude already | -| A thread Claude is already in | Yes, unless you've [quieted the thread](#quiet-one-conversation). Once Claude has joined, every reply there reaches it without another mention | -| A channel, top-level | Sometimes. [What Claude does with a channel message](#what-claude-does-with-a-channel-message) describes how it decides. Include `@Claude` to guarantee a reply, or [turn unprompted replies off](#quiet-the-whole-channel) | +| Where you write | Replies without an @-mention? | +| :---------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| A DM with Claude | Always. Every message is addressed to Claude already | +| A thread Claude is already in | Yes, unless you've [quieted the thread](#quiet-one-conversation). Once Claude has joined, every reply there reaches it without another mention | +| A channel, top-level | Sometimes. [What Claude does with a channel message](#what-claude-does-with-a-channel-message) describes how it decides. Include `@Claude` to guarantee a reply, or [turn unprompted replies off](#quiet-the-whole-channel) | +| A message another app or bot posted | No guaranteed reply. Claude reads it as context. `@Claude` in a bot's message doesn't wake a quiet channel; in an active channel Claude may pick it up. See [Messages from other apps and bots](#messages-from-other-apps-and-bots) | When you @-mention Claude in a channel, it reacts to your message with an emoji within a few seconds to show that it picked the message up. It then answers in a thread under your message, or starts a [working session](/docs/claude-tag/concepts/how-it-works) in that thread when the request needs investigation, tools, or a longer exchange. Once a working session starts, Claude shows an "is thinking…" line under your message. A reaction with no line under it means Claude picked your message up and is either still deciding or answering directly in the thread, not that it missed you.
from line 36
## Turn automatic replies on or off -The **Respond automatically** setting controls whether Claude replies to a channel's messages without an @-mention. Each channel has its own. When it's on, Claude may reply to a message it judges warrants one, as [What Claude does with a channel message](#what-claude-does-with-a-channel-message) describes. When it's off, Claude replies in that channel only when someone @-mentions it. +The **Respond automatically** setting controls whether Claude replies to a channel's messages without an @-mention. When it's on, Claude may reply to a message it judges warrants one, as [What Claude does with a channel message](#what-claude-does-with-a-channel-message) describes. When it's off, Claude replies in that channel only when someone @-mentions it. +The setting is on by default, so a channel Claude was just added to replies without @-mentions from the start. + +Each channel has its own copy of the setting, and there is no workspace- or organization-wide version. To make Claude mention-only across many channels, turn it off in each one. + All three places below change the same setting, so a change you make in one appears in the others. | Where | How | | :-------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | In Slack | Ask Claude in the channel, for example "@Claude only respond in this channel when someone @-mentions you" or "@Claude respond to messages here even when nobody mentions you." Claude confirms the change. | -| The channel's Configure page | Open the **Configure** link in the footer of any Claude reply and switch the **Respond automatically** toggle. See [Configure Claude for a channel](/docs/claude-tag/users/good-habits#configure-claude-for-a-channel). | +| The channel's Configure page | Open the **Configure** link in the footer of any Claude reply in the channel and switch the **Respond automatically** toggle. See [Configure Claude for a channel](/docs/claude-tag/users/good-habits#configure-claude-for-a-channel). | | The Claude Tag admin page (admins only) | At [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag), on the **Slack** tab under **Claude Tag's access**, open the channel's scope and switch **Respond automatically** in its **Advanced** settings. | The setting covers the channel's messages, not DMs. To quiet a single thread instead of the whole channel, [ask Claude in that thread](#quiet-one-conversation). + +Until Claude has joined a channel, you see "@-mention Claude in this channel to activate" in place of the toggle on the Configure page and the admin page. You see the same line in a channel shared across workspaces that all belong to your Claude organization, because Claude runs there with your organization's default settings only. [Messages that never get a reply](#messages-that-never-get-a-reply) covers shared channels in more detail. + +## Messages from other apps and bots + +Claude reads a message that another Slack app or bot posted as channel context, but a bot's message never gets the guaranteed reply that a person's @-mention gets. If the channel's [Respond automatically](#turn-automatic-replies-on-or-off) setting is off, or Claude has [stopped reading the channel](#when-claude-stops-reading-a-channel), a bot's `@Claude` doesn't wake it. In a channel where Claude is active, a bot's `@Claude` reaches Claude as a hand-off it may pick up or leave, and it may answer in a thread. Claude treats alerts an integration posts, messages a Slack workflow posts, and messages from any other bot the same way. + +Because Claude reads those messages, when a person asks about an alert a bot posted, Claude can answer from it. To have Claude act on what an integration posts, mention it in the channel or in the message's thread. For example, reply to a bot-posted alert with `@Claude triage this`. To have Claude check the channel on a schedule and post what needs attention, set up a [routine](/docs/claude-tag/users/proactivity). ## The name on a reply