HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
2,445 of the ledger's changes in claude-docs. Show every change
ReadSourcePageWhatLines
29 Sep 2026
28 pages
+518 −154 lines
claude-docs
claude-science/overview
±changed
+4−1
claude-docschanged
claude-science/overview
* A country or region where Anthropic offers claude.ai. See [Supported countries and regions](https://www.anthropic.com/supported-countries).
* **Without usage credits or extra usage, when the reset is less than 8 hours away.** The session pauses, and the composer shows when it will resume. Your conversation, files, and
* **Without usage credits or extra usage, when the reset is less than 8 hours away.** The session pauses, and the composer shows when it will resume. As long as Claude Science stay
In each of these cases, your conversation and artifacts are kept.
+4 −1 lines
Upstream edited 29 Sep 2026 14:30 UTC Recorded here 29 Sep 2026 14:37 UTC
claude-docs
claude-science/network-requirements
±changed
+1−1
claude-docschanged
claude-science/network-requirements
| `storage.googleapis.com` | When automatic updates are on | Update manifests and installers |
| `storage.googleapis.com` | During installation on Linux, and for updates | Update manifests and installers |
+1 −1 lines
Upstream edited 29 Sep 2026 14:30 UTC Recorded here 29 Sep 2026 14:37 UTC
claude-docs
claude-science/literature-access
±changed
+3−1
claude-docschanged
claude-science/literature-access
Claude retrieves open-access full text without credentials. To reach paywalled text you're entitled to, add publisher keys or your library's proxy in the Claude Science app: select
Claude retrieves open-access full text without credentials. To reach paywalled text you're entitled to, add publisher keys or your library's proxy in the Claude Science app. A key
To add a key or proxy, open the account menu (the gear icon at the bottom of the sidebar inside a project, or the account icon at the top right of the home screen), choose **Settin
+3 −1 lines
Upstream edited 29 Sep 2026 14:30 UTC Recorded here 29 Sep 2026 14:37 UTC
claude-docs
claude-science/get-started
±changed
+20−5
claude-docschanged
claude-science/get-started
When the app opens, sign in with your Claude account. On Windows, click the **Sign in on the web** button and confirm with **Continue**; the app opens claude.ai in your default bro
When the app opens, sign in with your Claude account. On Windows, click the **Sign in on the web** button and confirm with **Continue**; the app opens claude.ai in your default bro
If you approve the sign-in in your browser but Claude Science doesn't continue (for example, on a remote server when the sign-in can't return through the SSH tunnel), sign in with
+20 −5 lines
Upstream edited 29 Sep 2026 14:30 UTC Recorded here 29 Sep 2026 14:37 UTC
claude-docs
claude-science/comments
±changed
+8−0
claude-docschanged
claude-science/comments
On an image, you can click **Ask** instead of **Save** to send the comment to a side chat, a separate conversation that starts from the current one. The new comment goes with any o
* If the conversation has messages and no side chat is open, a side chat starts and the comments are sent right away.
* If a side chat is already open, the comments appear above the side chat's message box and are sent with your next message there.
* If the conversation has no messages yet, no side chat starts, and the comments are sent with your next message.
+8 −0 lines
Upstream edited 29 Sep 2026 14:30 UTC Recorded here 29 Sep 2026 14:37 UTC
claude-docs
claude-science/remote-compute-clusters
±changed
+1−1
claude-docschanged
claude-science/remote-compute-clusters
On Team and Enterprise plans, your organization can turn SSH hosts off. When it has, **Add SSH host** isn't available, hosts you added earlier stay listed but refuse new commands a
On Team and Enterprise plans, your organization can turn SSH hosts off. When it has, **Add SSH host** isn't available, hosts you added earlier stay listed but refuse new commands a
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/monitor-usage
±changed
+1−1
claude-docschanged
claude-science/monitor-usage
Claude Science uses the same seat as the rest of claude.ai, and its usage counts the same way as Claude Code and Cowork usage (see [Plans and usage](/docs/claude-science/overview#p
Claude Science uses the same seat as the rest of claude.ai, and its usage counts the same way as Claude Code and Cowork usage (see [Plans and usage](/docs/claude-science/overview.m
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/artifacts
±changed
+1−1
claude-docschanged
claude-science/artifacts
* **Review**: findings from [the reviewer](/docs/claude-science/the-reviewer).
* **Review**: findings from [the reviewer](/docs/claude-science/the-reviewer.md).
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/remote-compute-clusters
±changed
+3−3
claude-docschanged
claude-science/remote-compute-clusters
<Warning>
Remote jobs run outside the sandbox, as your user on the host, with access to everything your account can read and write there.
</Warning>
> [!WARNING]
>
+3 −3 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-science/artifacts
±changed
+3−3
claude-docschanged
claude-science/artifacts
<Note>
If you use artifacts in a claude.ai chat rather than the Claude Science app, see [What are artifacts and how do I use them?](https://support.claude.com/en/articles/17153992-what-
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-science/troubleshooting
+new page
+64−0
claude-docsnew page
claude-science/troubleshooting
No line of the body moved in this read.
+64 −0 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/run-on-remote-linux-server
±changed
+28−2
claude-docschanged
claude-science/run-on-remote-linux-server
Claude runs code inside a sandbox, and the sandbox needs two system packages: bubblewrap and socat. On Ubuntu or Debian:
Claude runs code inside a sandbox, and the sandbox needs two system packages: bubblewrap and socat. Installing them takes administrator (`sudo`) access. Without it, see [Run Claude
On Fedora, RHEL, or Arch, use the command for your distribution from the Linux tab of [Install](/docs/claude-science/get-started#install). On Ubuntu or Debian, run:
+28 −2 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/remote-compute-clusters
±changed
+3−3
claude-docschanged
claude-science/remote-compute-clusters
Adding a host runs a read-only probe that records CPUs, memory, GPUs, CUDA driver, presence of conda/modules/Apptainer, scratch directories, and whether `sbatch` exists. On SLURM c
Adding a host runs a probe that records CPUs, memory, GPUs, CUDA driver, presence of conda/modules/Apptainer, scratch directories, and whether `sbatch` exists. On Slurm clusters it
Workstations run jobs as detached processes. SLURM clusters receive jobs via `sbatch`. Jobs survive connection loss.
On a host with Slurm's `sbatch` command, Claude Science submits jobs to Slurm by default. On a host without it, such as a workstation, jobs run as detached processes directly on th
On the host's detail page, set **Scratch directory** (must be on a shared filesystem for SLURM) and **Concurrent job limit** (default 100).
+3 −3 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/overview
±changed
+33−1
claude-docschanged
claude-science/overview
Claude Science is a desktop application that pairs Claude with an analysis environment on your computer. Available in beta on macOS, Windows, and Linux.
Claude Science is a desktop application that pairs Claude with an analysis environment on your computer. Available in beta on macOS, Windows, and Linux. You install it separately f
## Use Claude Science outside the life sciences
Claude Science isn't limited to the life sciences. Besides biology, chemistry, and clinical and medical research, it supports computer science and machine learning, engineering, ma
+33 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/monitor-usage
±changed
+2−2
claude-docschanged
claude-science/monitor-usage
> Claude Science usage counts against each member's standard weekly quota and uses the same seat as the rest of claude.ai.
> Claude Science uses the same seat as the rest of claude.ai. Track its adoption and usage in Analytics and through the Admin API.
Claude Science usage counts against each member's standard weekly quota and uses the same seat as the rest of claude.ai. You can track adoption in Analytics and through the Admin A
Claude Science uses the same seat as the rest of claude.ai, and its usage counts the same way as Claude Code and Cowork usage (see [Plans and usage](/docs/claude-science/overview#p
+2 −2 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/get-started
±changed
+90−12
claude-docschanged
claude-science/get-started
Install Claude Science on your computer, sign in with your Claude account, and run your first analysis. You need a Claude Pro, Max, Team, or Enterprise plan, and on Team and Enterp
Download the installer from [claude.com/product/claude-science](https://claude.com/product/claude-science) and double-click to install. On first launch, the app sets up its run
Download the installer from [claude.com/product/claude-science](https://claude.com/product/claude-science) and double-click to install. On first launch, the app sets up its run
**Uninstall.** Quit Claude Science from its notification-area icon first, because the uninstaller refuses to run while the app is running. Then uninstall **Claude Science** fro
+90 −12 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/corporate-networks
±changed
+1−1
claude-docschanged
claude-science/corporate-networks
* On macOS, the menu-bar app reads `~/.claude-science/env`, a file of `KEY=VALUE` lines (`export KEY=VALUE` also works), when it launches. Put the three variables there, then quit
* On macOS, the Claude Science app reads a file named `env` in its data folder (`~/.claude-science/env` unless you moved the data folder) when it launches. The file holds `KEY=VALU
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/connectors-and-skills
±changed
+1−1
claude-docschanged
claude-science/connectors-and-skills
Claude Science includes Featured connectors to public life-sciences databases. They're on by default and can be turned off individually in **Settings > Connectors**. On Team and En
Claude Science includes Featured connectors to public research databases, most of them in the life sciences. They're on by default and can be turned off individually in **Settings
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/compute-providers
±changed
+1−1
claude-docschanged
claude-science/compute-providers
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/comments
±changed
+6−2
claude-docschanged
claude-science/comments
> Comments let you pin notes to specific parts of an artifact instead of describing a location in prose.
> Comments in Claude Science pin a note to a specific part of an artifact, such as selected text or a point on a figure, and send the note to Claude.
Comments let you pin notes to specific parts of an artifact instead of describing a location in prose. Select text in a Markdown, plain-text, LaTeX, or code file; select text in a
In Claude Science, comments let you pin notes to specific parts of an artifact instead of describing a location in prose. Select text in a Markdown, plain-text, LaTeX, or code file
+6 −2 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/artifacts
±changed
+8−4
claude-docschanged
claude-science/artifacts
# Artifacts
# Artifacts in Claude Science
> An artifact is a file Claude saves into the project: a figure, processed dataset, report, notebook, or other output.
> Artifacts in Claude Science are files Claude saves into a project, such as figures, datasets, and reports. Open, version, trace, and delete them.
An artifact is a file Claude saves into the project: a figure, processed dataset, report, notebook, or other output. Artifacts are stored on your computer in the app's data folder
+8 −4 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
claude-docs
claude-science/admin-controls
±changed
+1−1
claude-docschanged
claude-science/admin-controls
| Usage > Extra usage and Spend limits | Supported in Claude Science | Claude Science usage counts toward each member's 5-hour and weekly usage limits, in the same pool as Claude C
| Usage > Extra usage and Spend limits | Supported in Claude Science | Claude Science usage counts the same way as Claude Code and Cowork usage. See [Plans and usage](/docs/claude-
+1 −1 lines
Upstream edited 29 Sep 2026 07:02 UTC Recorded here 29 Sep 2026 07:07 UTC
28 Sep 2026
35 pages
+1142 −1702 lines
claude-docs
claude-tag/users/when-claude-responds
±changed
+19−5
claude-docschanged
claude-tag/users/when-claude-responds
| 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
| A message another app or bot posted | No. Claude reads it as context. To get a reply, have the app include `@Claude` in its message. [Messages from other apps and bots](#messages
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. The message goes to the channel's own [s
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. The message goes to the channel's own [s
+19 −5 lines
Upstream edited 28 Sep 2026 23:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/users/troubleshooting
±changed
+5−5
claude-docschanged
claude-tag/users/troubleshooting
Claude added a reaction to your message, or an "is thinking…" line appeared under it, but no reply arrived.
**What it means**
A reaction or an "is thinking…" line without a reply usually means Claude is still working, not that your message was dropped.
+5 −5 lines
Upstream edited 28 Sep 2026 23:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/users/getting-started
±changed
+1−1
claude-docschanged
claude-tag/users/getting-started
An "is thinking…" line appears at the bottom of the thread when Claude picks the task up, and it replies with results; a multi-step task also gets a checklist it updates as it work
A working indicator appears at the bottom of the thread when Claude picks the task up, and it replies with results; a multi-step task also gets a checklist it updates as it works.
+1 −1 lines
Upstream edited 28 Sep 2026 23:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+4−2
claude-docschanged
claude-tag/concepts/how-it-works
2. **Claude acknowledged, then went quiet.** The "is thinking…" line and the checklist are the progress surface; the silence between 9:02 and 9:06 was the work happening. [How the
2. **Claude acknowledged, then went quiet.** The working indicator and the checklist are the progress surface; the silence between 9:02 and 9:06 was the work happening. [How the ch
Once your message sends, an "is thinking…" line at the bottom of the thread means Claude picked it up. What happens next depends on the size of the ask. Questions and one-off reque
Once your message sends, a working indicator at the bottom of the thread means Claude picked it up. In a channel thread the indicator carries a **Stop** button; in a DM it reads "i
+4 −2 lines
Upstream edited 28 Sep 2026 23:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+32−16
claude-docschanged
claude-tag/admins/troubleshooting
When the reason Claude can't verify the membership is that the channel is shared with a workspace in your Enterprise Grid where the Claude app isn't installed, the reply reads inst
> This channel is shared with a workspace Claude hasn't been added to, so Claude can't check the channel for guests and can't respond here. A Slack org admin can add Claude to that
Use a channel that belongs to a single workspace. Setting the scope's guest setting to **Full access** removes the guest check that posts this message, but a Grid-shared channel st
+32 −16 lines
Upstream edited 28 Sep 2026 23:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/overview
±changed
+2−2
claude-docschanged
claude-tag/overview
* **In DMs**: a DM with Claude runs on the sender's own Claude account and bills to that person's seat. The seat must include Claude Code, or, on the Enterprise plan, be a **Standa
* **In DMs**: a DM from a member who has connected a Claude account runs on that account and bills to that person's seat. The seat must include Claude Code, or, on the Enterprise p
Direct messages don't draw from this balance. A DM runs on the sender's own claude.ai account and follows that seat's usual usage limits, so the organization spend limit doesn't ap
Direct messages from members who have connected a Claude account don't draw from this balance. Such a DM runs on the sender's own claude.ai account and follows that seat's usual us
+2 −2 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+2−2
claude-docschanged
claude-tag/concepts/security-and-data
DMs run on the user's own claude.ai account instead and are covered separately on [How agent identity works](/docs/claude-tag/concepts/agent-identity#direct-message-channels).
DMs from members who have connected a Claude account run on the member's own claude.ai account instead and are covered separately on [How agent identity works](/docs/claude-tag/con
DMs with `@Claude` run on the user's own claude.ai account instead, with that user's personal connectors, and work there is attributed to them, except pull requests, which the Clau
DMs with `@Claude` from a member who has connected a Claude account run on that member's own claude.ai account instead, with that member's personal connectors, and work there is at
+2 −2 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/concepts/agent-identity
±changed
+1−1
claude-docschanged
claude-tag/concepts/agent-identity
In direct messages (DMs) between a user and `@Claude`, the provisioned identity does not apply. DMs are one-to-one only; group DMs aren't supported. A DM has no channel to scope it
In direct messages (DMs) between `@Claude` and a user who has connected a Claude account, the provisioned identity does not apply. DMs are one-to-one only; group DMs aren't support
+1 −1 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/workspaces
±changed
+3−3
claude-docschanged
claude-tag/admins/workspaces
The **Enable Claude Tag** switch sits at the top of the scope's panel. While the switch is off, Claude doesn't respond to @-mentions in the scope. Direct messages are unaffected. T
The **Enable Claude Tag** switch sits at the top of the scope's panel. While the switch is off, Claude doesn't respond to @-mentions in the scope. Direct messages from members who
Go to [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag) → **Claude Tag's access** → **Slack** → **Default Slack** → **Enable Claude Tag** and tur
Go to [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag) → **Claude Tag's access** → **Slack** → **Default Slack** → **Enable Claude Tag** and tur
In the **Connected workspaces** list, select **Disconnect** on the workspace's row, then confirm in the dialog. Claude stops responding in that workspace's channels immediately, an
+3 −3 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+1−1
claude-docschanged
claude-tag/admins/setup-overview
Channel work draws from your organization's usage balance, not from individual seats; the spend limit caps how much of that balance Claude Tag can use each month. DMs run on the us
Channel work draws from your organization's usage balance, not from individual seats; the spend limit caps how much of that balance Claude Tag can use each month. DMs from members
+1 −1 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/set-spend-limit
±changed
+5−4
claude-docschanged
claude-tag/admins/set-spend-limit
> Claude Tag channel work bills to your organization's usage balance, and DMs to the sender's seat. Set the spend limit and see what happens when it's reached.
> Claude Tag channel work bills to your organization's usage balance. Set the spend limit and see what happens when it's reached.
| A DM with Claude | The sender's own seat | The seat's usual limits, not the spend limit |
| A DM from a member who has connected a Claude account | The sender's own seat | The seat's usual limits, not the spend limit |
| A [DM from a member who hasn't connected a Claude account](/docs/claude-tag/admins/restrict-access#direct-messages-from-members-without-a-claude-account) | Your organization's us
+5 −4 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+62−5
claude-docschanged
claude-tag/admins/restrict-access
In channels, Claude Tag responds only where it's been added and addressed, and the controls on this page narrow that further. DMs are a separate surface that runs on the user's own
In channels, Claude Tag responds only where it's been added and addressed, and the controls on this page narrow that further. DMs are a separate surface. A DM from a member who has
The toggle applies to channels and DMs alike.
The toggle applies to channels and DMs alike. While the toggle is off, a [DM from a member who hasn't connected a Claude account](#direct-messages-from-members-without-a-claude-acc
* **DMs.** The per-scope switches don't cover them. To close those off too, turn off the [**Allow direct messages**](#allow-or-disable-direct-messages) toggle.
+62 −5 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/healthcare
±changed
+1−1
claude-docschanged
claude-tag/admins/healthcare
Members' own claude.ai connectors, such as their email or calendar, are a separate path to tools outside Slack. In a direct message, Claude works on the member's own Claude account
Members' own claude.ai connectors, such as their email or calendar, are a separate path to tools outside Slack. In a direct message from a member who has connected a Claude account
+1 −1 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/federated-access/overview
±changed
+1−1
claude-docschanged
claude-tag/admins/federated-access/overview
Federated connections work in Slack channels, where Claude acts under your organization's agent identity. They don't work in direct messages, which run under [the individual's own
Federated connections work in Slack channels, where Claude acts under your organization's agent identity. They don't work in direct messages from members who have connected a Claud
+1 −1 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/attribute-costs
±changed
+1−1
claude-docschanged
claude-tag/admins/attribute-costs
`products[]=claude-tag` limits the report to Claude's work in Slack channels, which bills to your organization's usage balance. DMs with Claude bill to the sender's own seat and ar
`products[]=claude-tag` limits the report to the work that bills to your organization's usage balance: Claude's work in Slack channels, and [DMs from members who haven't connected
+1 −1 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/attach-to-scope
±changed
+1−1
claude-docschanged
claude-tag/admins/attach-to-scope
DMs run under the user's own claude.ai account, so bundles attached here apply only in channels. See [how DMs work in this model](/docs/claude-tag/concepts/agent-identity#direct-me
DMs from members who have connected a Claude account run under the member's own claude.ai account, so bundles attached here don't apply to them. See [how DMs work in this model](/d
+1 −1 lines
Upstream edited 28 Sep 2026 23:11 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-docs
claude-tag/admins/connections/datadog
±changed
+12−10
claude-docschanged
claude-tag/admins/connections/datadog
In the bundle, click **Connect** next to Datadog. The picker has three Datadog entries, one per site. Pick the one that matches your Datadog account's site.
In the bundle, click **Connect** next to Datadog. The picker has one Datadog entry per Datadog site. Datadog has a separate API host per site, and a key only works against its own,
| Picker entry | Site |
| Picker entry | Site and API host |
| **Datadog** | US1 (`api.datadoghq.com`), the default site |
+12 −10 lines
Upstream edited 28 Sep 2026 22:53 UTC Recorded here 28 Sep 2026 23:07 UTC
claude-docs
cowork/guide/plugins
±changed
+18−23
claude-docschanged
cowork/guide/plugins
A plugin is a package that extends what Claude can do in Cowork. Installing one can add skills, MCP connectors, subagents, commands, or hooks in a single step. Plugins come from th
A plugin is a package that extends what Claude can do in Cowork. Installing one can add skills, MCP connectors, subagents, slash commands, or hooks in a single step. Plugins come f
A plugin you install is saved to your account, so its skills and connectors are also available in chat and in Claude Code. [Plugins](/docs/plugins/overview) covers what each surfac
To get started, [install a plugin](#install-a-plugin) from **Customize**, or [add a Git repository as a marketplace](#use-a-git-repository-as-a-marketplace) to share plugins withou
+18 −23 lines
Upstream edited 28 Sep 2026 22:52 UTC Recorded here 28 Sep 2026 23:07 UTC
claude-docs
connectors/github/index
±changed
+6−6
claude-docschanged
connectors/github/index
| Retrieved | Not retrieved |
| -------------- | ------------------- |
| File names | Commit history |
| File contents | Pull requests |
| Branch content | Issues |
+6 −6 lines
Recorded here 28 Sep 2026 22:07 UTC
claude-docs
connectors/building/index
±changed
+4−4
claude-docschanged
connectors/building/index
| Limit | claude.ai and Desktop | Claude Code |
| ------------------------ | ------------------------- | -------------------------------------------------------- |
| Maximum tool result size | \~150,000 characters | 25,000 tokens, configurable with `MAX_MCP_OUTPUT_TOKENS` |
| Tool call timeout | 240 seconds per tool call | Configurable with `MCP_TOOL_TIMEOUT` |
| Limit | claude.ai and Desktop | Claude Code |
+4 −4 lines
Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-science/changelog
±changed
+10−0
claude-docschanged
claude-science/changelog
<Update label="0.1.54" description="September 28, 2026">
* Sessions on Claude Sonnet 5.5 now default to Extra high reasoning effort
* Windows: after an update, the app window reopens on the new version by itself
* Pinned artifacts (formerly starred) and pinned projects now show a pushpin instead of a star
+10 −0 lines
Upstream edited 28 Sep 2026 22:00 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
cowork/changelog
±changed
+1−0
claude-docschanged
cowork/changelog
* Added support for Claude Sonnet 5.5.
+1 −0 lines
Upstream edited 28 Sep 2026 20:37 UTC Recorded here 28 Sep 2026 21:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+207−207
claude-docschanged
third-party/claude-desktop/configuration-changelog
| MDM key | Type | Description |
| ------------------------------------------------------------------------------------------------------------------------ | --------- | ------------------------------------- |
| [`inferenceIdpAuthFlow`](/docs/third-party/claude-desktop/configuration#inferenceidpauthflow) | `enum` | Identity provider sign-in flow
| [`inferenceIdpOidc`](/docs/third-party/claude-desktop/configuration#inferenceidpoidc) | `object` | Identity provider (OIDC)
| MDM key | Type | Description |
+207 −207 lines
Upstream edited 28 Sep 2026 20:19 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
cowork/guide/plugins
±changed
+11−11
claude-docschanged
cowork/guide/plugins
| Component | What it adds |
| ---------- | ---------------------------------------------------------- |
| Skills | Reusable instructions that teach Claude a workflow |
| Component | What it adds |
| - | - |
+11 −11 lines
Upstream edited 28 Sep 2026 20:19 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+4−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.9939.4" description="2026-09-27">
No configuration changes in this release.
</Update>
+4 −0 lines
Upstream edited 28 Sep 2026 20:19 UTC Recorded here 28 Sep 2026 20:37 UTC
claude-docs
cowork/guide/plugins
±changed
+2−2
claude-docschanged
cowork/guide/plugins
Select **Discover** to see available plugins. The default marketplace
is Anthropic's official catalog; you can add other marketplaces by URL.
Select **Discover** to see available plugins. The default marketplace is
Anthropic's official catalog; you can add other marketplaces by URL.
+2 −2 lines
Upstream edited 28 Sep 2026 20:19 UTC Recorded here 28 Sep 2026 20:37 UTC
claude-docs
cowork/changelog
±changed
+20−0
claude-docschanged
cowork/changelog
<Update label="v2.9939.4" description="2026-09-27">
Bundled Claude Code version: 2.1.284.
**General**
+20 −0 lines
Upstream edited 28 Sep 2026 20:19 UTC Recorded here 28 Sep 2026 20:37 UTC
claude-docs
government/deploy-desktop/windows-checklist
±changed
+5−5
claude-docschanged
government/deploy-desktop/windows-checklist
| Identifier | Value |
| ---------------------- | ---------------------- |
| Package name | `Claude` |
| Package family name | `Claude_pzs8sxrjxfjjc` |
| Publisher display name | Anthropic, PBC |
+5 −5 lines
Upstream edited 28 Sep 2026 20:10 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
government/security/security-and-data-handling
±changed
+6−4
claude-docschanged
government/security/security-and-data-handling
The desktop application and the sandbox honor the operating system's proxy settings, and a single allowlist controls outbound network access from Claude's tools. You manage the all
The desktop application follows the operating system's proxy settings, and a single allowlist controls outbound network access from Claude's tools. You manage the allowlist with th
For configuration and model inference, the application reaches the Claude for Government service hostname provided to your agency during onboarding. Sign-in happens in the user
For configuration and model inference, the application reaches the Claude for Government service hostname provided to your agency during onboarding. Sign-in happens in the user
Yes. Both the desktop application and the sandbox honor the operating system's proxy settings, including PAC URLs, and route all outbound traffic through your proxy. TLS inspec
+6 −4 lines
Upstream edited 28 Sep 2026 20:10 UTC Recorded here 28 Sep 2026 20:37 UTC
claude-docs
government/deploy-desktop/windows-checklist
±changed
+1−1
claude-docschanged
government/deploy-desktop/windows-checklist
* **`www.claudeusercontent.com`.** This host serves the frame that displays artifact previews.
* **Hosts for icons, previews, and widgets.** For connector icons, the artifact preview frame, and the interactive widgets that some connectors display, the app reaches the hosts l
+1 −1 lines
Upstream edited 28 Sep 2026 20:10 UTC Recorded here 28 Sep 2026 20:37 UTC
claude-docs
claude-tag/admins/federated-access/troubleshooting
±changed
+60−60
claude-docschanged
claude-tag/admins/federated-access/troubleshooting
| Message
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| "The check can't run right now. Try again later, or skip the check and record why."
| "Too many checks in a short time." followed by how long to wait
| "Too many attempts in a short time." in the **Connect an authorization server** dialog
+60 −60 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/connections/custom
±changed
+28−28
claude-docschanged
claude-tag/admins/connections/custom
| Field | What to enter
| :--------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------
| **Name** | A label for this connection (for example "Internal billing API")
| **Credential type** | Pick the type that matches how the API authenticates; see [Credential types](#credential-types)
| **Allowed websites** | The API's host (for example `api.example.com`). A wildcard is allowed as the leftmost label. You can't enter `*` alone here; a credential is always
+28 −28 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/federated-access/troubleshooting
±changed
+9−9
claude-docschanged
claude-tag/admins/federated-access/troubleshooting
* **An S3 upload sent in chunks.** The AWS CLI (2.23.0 and later) and the AWS SDKs that compute upload checksums by default can send S3 uploads in chunks with a checksum trailer. A
**How to resolve**
| Cause | Do this
+9 −9 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 20:07 UTC
claude-docs
claude-tag/admins/connections/custom
±changed
+1−1
claude-docschanged
claude-tag/admins/connections/custom
Claude can call the endpoint with `curl`, an AWS SDK, or the AWS CLI. The sandbox holds no real AWS credentials, so a CLI or SDK signs the request with placeholder values; Agent Pr
Claude can call the endpoint with `curl`, an AWS SDK, or the AWS CLI. The sandbox holds no real AWS credentials, so a CLI or SDK signs the request with placeholder values; Agent Pr
+1 −1 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 20:07 UTC
claude-docs
claude-tag/users/models
±changed
+2−0
claude-docschanged
claude-tag/users/models
For how your organization's model settings apply in Slack, see [Models your organization allows](/docs/claude-tag/admins/customize#models-your-organization-allows).
+2 −0 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 20:07 UTC
claude-docs
claude-tag/admins/customize
±changed
+31−31
claude-docschanged
claude-tag/admins/customize
| Layer | What it is | W
| :---------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------- | :
| **Connections** | Credentials for the systems Claude can reach (GitHub, Drive, Datadog, your APIs) | O
| **Plugins and skills** | Instructions that teach Claude how to use a tool or follow a process. A plugin bundles one or more [skills](https://code.claude.com/docs/en/skills). | O
| **Custom instructions** | Standing guidance read in every session at a scope (team conventions, output formats). Outranks channel memory. | O
+31 −31 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/customize
±changed
+2−2
claude-docschanged
claude-tag/admins/customize
## Settings no one can change
## Name, handle, and avatar of the Claude app
* The Claude app's name, @-handle, and avatar in Slack are the same in every workspace; there is no rename or rebrand setting.
The Claude app's name, @-handle, and avatar in Slack are the same in every workspace; there is no rename or rebrand setting.
+2 −2 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 20:07 UTC
claude-docs
claude-tag/overview
±changed
+1−1
claude-docschanged
claude-tag/overview
<p className="tm-hero-lede">Anyone in a channel can tag Claude into a problem and hand it work: reproduce a bug and open a pull request, turn a decision thread into a doc, asse
<p className="tm-hero-lede">Anyone in a Slack channel can tag Claude into a problem and hand it work: reproduce a bug and open a pull request, turn a decision thread into a doc
+1 −1 lines
Upstream edited 28 Sep 2026 20:03 UTC Recorded here 28 Sep 2026 20:07 UTC
claude-docs
claude-tag/concepts/settings-map
±changed
+7−7
claude-docschanged
claude-tag/concepts/settings-map
| Surface | Who changes it
| :--------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------
| [Claude Tag admin page](https://claude.ai/admin-settings/claude-tag) | An Owner in your Claude organization
| [Usage page](https://claude.ai/admin-settings/usage/claude-tag) | An admin
| [Analytics page](https://claude.ai/analytics/claude-tag) | Anyone who can view the Analytics dashboard
+7 −7 lines
Upstream edited 28 Sep 2026 17:30 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+5−5
claude-docschanged
claude-tag/concepts/security-and-data
| Checkpoint | The guarantee
| :----------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------
| The sandbox | Holds no credentials
| Agent Proxy | Injects credentials from the credential store at request time, and blocks a request that no [connection](/docs/claude-tag/admins/add-connections#set-allowed-websit
| Your systems | See the agent's own accounts, so its actions there are attributable
+5 −5 lines
Upstream edited 28 Sep 2026 17:30 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/concepts/settings-map
±changed
+3−2
claude-docschanged
claude-tag/concepts/settings-map
| [Claude Tag admin page](https://claude.ai/admin-settings/claude-tag) | An Owner in your Claude organization
| [Claude Tag admin page](https://claude.ai/admin-settings/claude-tag) | An Owner in your Claude organization
Everything an Owner configures for channels lives at [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag). Settings there apply per scope (a channel
Everything an Owner configures for channels lives at [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag). Most settings there apply per scope (a ch
* **Personal connectors**: on the Enterprise plan, whether Claude holds every result of a member's connector task for that member's review before posting it, and the topics an Owne
+3 −2 lines
Upstream edited 28 Sep 2026 17:30 UTC Recorded here 28 Sep 2026 17:37 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+1−1
claude-docschanged
claude-tag/concepts/security-and-data
Claude uses a user's [personal connectors in a channel](/docs/claude-tag/concepts/personal-connectors) only for that user's own tasks, after the user allows it. The work runs with
Claude uses a user's [personal connectors in a channel](/docs/claude-tag/concepts/personal-connectors) only for that user's own tasks, after the user allows it. The work runs with
+1 −1 lines
Upstream edited 28 Sep 2026 17:30 UTC Recorded here 28 Sep 2026 17:37 UTC
claude-docs
claude-tag/concepts/personal-connectors
±changed
+2−2
claude-docschanged
claude-tag/concepts/personal-connectors
* **Require human review of every message.** On the Enterprise plan, an admin can turn this switch on so that Claude holds every result for the requester's review, not only the one
* **Sensitive information requiring review.** Lists what the check looks for. An Owner can add topics of your own under **Additional topics**, for example "Board meeting notes are
* **Require human review of every message.** On the Enterprise plan, an admin can turn this switch on so that Claude holds every result for the requester's review, not only the one
* **Sensitive information requiring review.** Shows examples of what the check looks for. An Owner can add topics of their own under **Additional topics**, for example "Board meeti
+2 −2 lines
Upstream edited 28 Sep 2026 17:30 UTC Recorded here 28 Sep 2026 17:37 UTC
claude-docs
connectors/github/index
±changed
+57−15
claude-docschanged
connectors/github/index
> Add files and folders from your GitHub repositories to a conversation or project so Claude can read your code
> Add a GitHub repository to a conversation, or files and folders from a repository to a project, so Claude can read your code
The GitHub integration lets you add files and folders from your GitHub repositories to a conversation or a project, so Claude can read your code and answer development questions wi
The GitHub integration lets you add a GitHub repository to a conversation, or files and folders from a repository to a project, so Claude can read your code and answer development
You can add repository content to a single conversation, or to a [project](https://support.claude.com/en/articles/9517075-what-are-projects), a workspace in Claude where a set of c
+57 −15 lines
Recorded here 28 Sep 2026 01:07 UTC
claude-docs
plugins/quickstart
±changed
+16−16
claude-docschanged
plugins/quickstart
By the end of this quickstart, you have a working example plugin with one skill and, optionally, one remote MCP connector, tested in Claude Code, validated, and pushed to GitHub, w
By the end of this quickstart, you have a working example plugin with one skill and, optionally, one remote MCP connector, tested in Claude Code, validated, and pushed to GitHub, w
> * If you want to make a plugin from a conversation without writing files, see [Create a plugin with Claude](/docs/plugins/create-with-claude)
> * If you want to distribute a plugin only inside your own organization, see [Roll out a plugin to your whole organization](/docs/plugins/org-rollout)
> * If you want to look up the folder layout, the manifest fields, or what each surface loads, see [Plugin structure and testing](/docs/plugins/build)
+16 −16 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
plugins/build
±changed
+17−17
claude-docschanged
plugins/build
[Build your first plugin](/docs/plugins/quickstart) walks you through making one end to end.
[Build your first plugin](/docs/plugins/quickstart.md) walks you through making one end to end.
> * If you want a plugin for your own use without writing files, see [Create a plugin with Claude](/docs/plugins/create-with-claude), which makes one from a conversation
> * If you want a plugin for your own use without writing files, see [Create a plugin with Claude](/docs/plugins/create-with-claude.md), which makes one from a conversation
> * If you're deciding which pieces your plugin needs, see [Decide what to include in your plugin](/docs/connectors/building/what-to-build)
+17 −17 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
plugins/quickstart
±changed
+91−95
claude-docschanged
plugins/quickstart
<Note>
* If you want to make a plugin from a conversation without writing files, see [Create a plugin with Claude](/docs/plugins/create-with-claude)
* If you want to distribute a plugin only inside your own organization, see [Roll out a plugin to your whole organization](/docs/plugins/org-rollout)
* If you want to look up the folder layout, the manifest fields, or what each surface loads, see [Plugin structure and testing](/docs/plugins/build)
</Note>
+91 −95 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
plugins/build
±changed
+143−510
claude-docschanged
plugins/build
export const Piece = ({id, children}) => <div className="pe-piece" data-piece={id}>{children}</div>;
export const PluginExplorer = ({children, variant}) => {
const SKILL_PIECES = [{
id: 'skillmd',
+143 −510 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
plugins/pre-submission-checklist
±changed
+49−49
claude-docschanged
plugins/pre-submission-checklist
| What to do
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| Submit a folder that contains `.claude-plugin/plugin.json`
| Submit one plugin at a time. In a [marketplace repository](https://code.claude.com/docs/en/plugins/create-marketplace) with several plugins, validate and submit each plugin folde
| Keep every file that a hook, an MCP server command, or a script uses inside the plugin folder, and point every component path in `plugin.json` inside it
+49 −49 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
plugins/quickstart
±changed
+1−1
claude-docschanged
plugins/quickstart
The directory requires the manifest, and the example has the fields that every surface and the directory read:
The example has the fields that every surface and the directory read:
+1 −1 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 28 Sep 2026 01:07 UTC
claude-docs
plugins/pre-submission-checklist
±changed
+11−11
claude-docschanged
plugins/pre-submission-checklist
| What to do
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| Submit a folder that contains `.claude-plugin/plugin.json`
| Submit one plugin at a time. In a [marketplace repository](https://code.claude.com/docs/en/plugins/create-marketplace) with several plugins, validate and submit each plugin folde
| Keep every file that a hook, an MCP server command, or a script uses inside the plugin folder, and point every component path in `plugin.json` inside it
+11 −11 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 28 Sep 2026 01:07 UTC
claude-docs
plugins/build
±changed
+9−9
claude-docschanged
plugins/build
href: '/skills/how-to#create-a-skillmd-file',
linkText: 'Go to Create a SKILL.md file'
href: 'https://agentskills.io/specification',
linkText: 'Go to the Agent Skills specification'
href: '/skills/how-to#add-resources',
+9 −9 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 28 Sep 2026 01:07 UTC
claude-docs
skills/how-to
±changed
+6−6
claude-docschanged
skills/how-to
* **Live data from another service**: that's what an [MCP connector](/docs/connectors/getting-started) provides. A skill can tell Claude how to use a connector, but it can't reach
* **Live data from another service**: that's what an [MCP connector](/docs/connectors/getting-started.md) provides. A skill can tell Claude how to use a connector, but it can't rea
Don't put API keys, passwords, or other credentials in a script or anywhere else in the skill: everyone you share the skill with receives its files. When a script needs to reach an
Don't put API keys, passwords, or other credentials in a script or anywhere else in the skill: everyone you share the skill with receives its files. When a script needs to reach an
* **Share or publish one skill**: on Team and Enterprise plans, open the skill from **Customize > Skills** and use the same **Share** and **Publish to org** controls that a plugin
+6 −6 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
skills/how-to
±changed
+119−488
claude-docschanged
skills/how-to
export const Piece = ({id, children}) => <div className="pe-piece" data-piece={id}>{children}</div>;
export const PluginExplorer = ({children, variant}) => {
const SKILL_PIECES = [{
id: 'skillmd',
+119 −488 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
skills/how-to
±changed
+3−3
claude-docschanged
skills/how-to
| Field | Type | Description
| :------------ | :----- | :--------------------------------------------------------------------------------------------------------------------------------------------------------
| `name` | string | Lowercase letters, numbers, and hyphens only, up to 64 characters. Must match the skill's directory name
| Field | Type | Description |
| :- | :- | :- |
+3 −3 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
skills/how-to
±changed
+20−9
claude-docschanged
skills/how-to
href: '/skills/how-to#create-a-skillmd-file',
linkText: 'Go to Create a SKILL.md file'
href: 'https://agentskills.io/specification',
linkText: 'Go to the Agent Skills specification'
href: '/skills/how-to#add-resources',
+20 −9 lines
Upstream edited 28 Sep 2026 00:41 UTC Recorded here 28 Sep 2026 01:07 UTC
27 Sep 2026
7 pages
+106 −99 lines
claude-docs
claude-tag/admins/restrict-access
±changed
+29−29
claude-docschanged
claude-tag/admins/restrict-access
| Plan | Toggle | Off (default) | On
| :--------- | :------------------------------------------- | :------------------------------------------------------------------------------------ | :-----------------------------
| Plan | Toggle | Off (default) | On |
| :- | :- | :- | :- |
| Team | **Restrict to your organization** | Anyone in the connected Slack workspace can use Claude, even without a Claude account | Only Slack users with a Claude
+29 −29 lines
Upstream edited 27 Sep 2026 15:11 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+2−0
claude-docschanged
claude-tag/admins/restrict-access
About once a week, Claude sends the person who connected the workspace a direct message suggesting public channels to add it to. To stop those messages, select **Stop these suggest
+2 −0 lines
Upstream edited 27 Sep 2026 15:11 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-docs
claude-tag/admins/for-slack-admins
±changed
+4−1
claude-docschanged
claude-tag/admins/for-slack-admins
* Select a channel in a weekly suggestion message. About once a week, Claude sends the person who connected the workspace a direct message that suggests public channels to add it t
Claude picks the channels to suggest from public channel names, topics, and purposes, and from public-channel search. Claude doesn't join a channel to evaluate it.
When a member selects **Add to channel** or **Approve and post**, or an auto-join pattern matches, Claude adds itself to that channel using its `channels:join` scope. Slack's audit
When a member selects **Add to channel** or **Approve and post**, picks a channel in a suggestion message, or an auto-join pattern matches, Claude adds itself to that channel using
+4 −1 lines
Upstream edited 27 Sep 2026 15:11 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-docs
claude-tag/users/getting-started
±changed
+14−14
claude-docschanged
claude-tag/users/getting-started
| If you see | It means
| :------------------------------------------------------------------------------------ | :-----------------------------------------------------------------------------------------
| Typing `@Claude` doesn't show **Claude** with an **APP** badge in the suggestion list | The Claude app isn't installed in your workspace
| The mention sends but Claude doesn't reply | Setup isn't finished for this channel
| Claude replies "I couldn't find a Claude Code environment for your account" | Claude couldn't resolve an environment for this DM; DMs run on your account rather than th
+14 −14 lines
Upstream edited 27 Sep 2026 15:10 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/concepts/for-claude-code-users
±changed
+15−15
claude-docschanged
claude-tag/concepts/for-claude-code-users
| Step | What applies
| :-------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------
| You tag `@Claude` with a task | Your message is the task, and Claude starts work in a sandbox with no repository
| Your message names a granted repository | Claude clones it into the sandbox
| The clone completes | `CLAUDE.md`, `.claude/CLAUDE.md`, `.claude/rules/*.md`, and the skills in `.claude/skills/` [load into the session](/docs/claude-tag/adm
+15 −15 lines
Upstream edited 27 Sep 2026 15:10 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/getting-started
±changed
+1−1
claude-docschanged
claude-tag/users/getting-started
| 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
| A link you paste, like a Google Doc or a webpage | If your admin allowed that site for this channel, or, for a file behind your own login, if you've [allowed Claude to
+1 −1 lines
Upstream edited 27 Sep 2026 15:10 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-docs
claude-tag/overview
±changed
+5−3
claude-docschanged
claude-tag/overview
* **In DMs**: a DM with Claude runs on the sender's own Claude account and bills to that person's seat, so DMs need a seat that includes Claude Code.
* **In DMs**: a DM with Claude runs on the sender's own Claude account and bills to that person's seat. The seat must include Claude Code, or, on the Enterprise plan, be a **Standa
You extend what Claude can reach, like your repositories, ticketing systems, data warehouses, and custom tools, through [connections](/docs/claude-tag/admins/add-connections), [plu
You extend what Claude can reach, like your repositories, ticketing systems, data warehouses, and custom tools, through [connections](/docs/claude-tag/admins/add-connections), [plu
What it can reach depends on the channel you're in, not on who you are. The fastest way to find out is to ask it: `@Claude what can you access from this channel?` Or, if you're sig
+5 −3 lines
Upstream edited 27 Sep 2026 15:10 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-docs
claude-tag/concepts/for-claude-code-users
±changed
+2−2
claude-docschanged
claude-tag/concepts/for-claude-code-users
To change what a session can reach, ask an admin to [add a connection](/docs/claude-tag/admins/add-connections). The change applies to every session in the channel.
To change what a session can reach for everyone, ask an admin to [add a connection](/docs/claude-tag/admins/add-connections). The change applies to every session in the channel.
In a channel, Claude acts with credentials of its own, service accounts that [an admin provisions](/docs/claude-tag/concepts/agent-identity#channel-sessions). A pull request comes
In a channel, Claude acts with credentials of its own, service accounts that [an admin provisions](/docs/claude-tag/concepts/agent-identity#channel-sessions). A pull request comes
+2 −2 lines
Upstream edited 27 Sep 2026 15:10 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+26−26
claude-docschanged
claude-tag/admins/troubleshooting
| You expected | But got
| :----------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------
| The setup page at [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag) | A page titled **Set up Claude Tag** with **View setup guide** and **Go to
| A pairing code from `@Claude connect` | “Only Slack workspace admins (or Enterprise Grid org admins) can link thi
| A pairing code | “…installation is out of date”
+26 −26 lines
Upstream edited 27 Sep 2026 15:09 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/troubleshooting
±changed
+2−2
claude-docschanged
claude-tag/users/troubleshooting
DMs run on your own Claude account rather than the organization's agent. They need a seat that includes Claude Code, and they use your personal connectors rather than the channel c
DMs run on your own Claude account rather than the organization's agent. They need a qualifying seat (a seat that includes Claude Code, or on the Enterprise plan a **Standard** or
Your seat type doesn't include the Claude Code engine that powers DMs. Mentioning `@Claude` in a real channel doesn't depend on your seat type and keeps working.
Your seat doesn't qualify for DMs. A seat that includes Claude Code always qualifies; on the Enterprise plan, a **Standard** or **Usage-Based Chat** seat also qualifies when you ha
+2 −2 lines
Upstream edited 27 Sep 2026 15:09 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+6−6
claude-docschanged
claude-tag/admins/troubleshooting
This message doesn't point at a service you connected. When a connected service's credential fails, Claude reports that as a tool error inside its reply, not with this notice. A DM
This message doesn't point at a service you connected. When a connected service's credential fails, Claude reports that as a tool error inside its reply, not with this notice. A DM
DMs run on the user's own claude.ai account and need a seat that includes Claude Code; this user's seat doesn't include it. Mentioning `@Claude` in a channel doesn't depend on the
**How to resolve**
+6 −6 lines
Upstream edited 27 Sep 2026 15:09 UTC Recorded here 27 Sep 2026 15:37 UTC
26 Sep 2026
33 pages
+714 −453 lines
claude-docs
claude-tag/admins/network-requirements
±changed
+4−4
claude-docschanged
claude-tag/admins/network-requirements
| | IP allowlist | Allowed websites |
| :-------------------- | :----------------------------------- | :-------------------------------------- |
| **Who configures it** | Your team, on your service | You, on the connection in Claude |
| **What it decides** | Which networks may reach the service | Which hosts a credential may be sent to |
| | IP allowlist | Allowed websites |
+4 −4 lines
Upstream edited 26 Sep 2026 05:34 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/connections/bigquery
±changed
+6−6
claude-docschanged
claude-tag/admins/connections/bigquery
| Field | Value
| :----------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------
| Credential type | **GCP access token (with Service Account Key)**
| GCP service account key (JSON) | The JSON key file from Google Cloud Console
| Scopes (optional) | `https://www.googleapis.com/auth/bigquery`. The field is labeled optional, but leave it empty and the token defaults to a broader scope. BigQuery
+6 −6 lines
Upstream edited 26 Sep 2026 05:34 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/network-requirements
±changed
+2−0
claude-docschanged
claude-tag/admins/network-requirements
<Note>If your Google Cloud project uses VPC Service Controls, an IP-based access level doesn't admit Claude's queries through the [BigQuery connection](/docs/claude-tag/admins/conn
+2 −0 lines
Upstream edited 26 Sep 2026 05:34 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/connections/bigquery
±changed
+20−0
claude-docschanged
claude-tag/admins/connections/bigquery
## Allow the connection through a VPC Service Controls perimeter
If the Google Cloud project that holds your BigQuery data is inside a [VPC Service Controls](https://cloud.google.com/vpc-service-controls/docs/overview) perimeter, Claude's querie
If you allowlist [Anthropic's published egress IP range](/docs/claude-tag/admins/network-requirements) in an access level, Claude's queries still fail, because they reach your peri
+20 −0 lines
Upstream edited 26 Sep 2026 05:34 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/users/good-habits
±changed
+20−20
claude-docschanged
claude-tag/users/good-habits
| End condition | Who closes it | Example |
| :----------------------------- | :----------------- | :---------------------------------------------------- |
| An objective check passes | Claude, on its own | "Done when CI is green" |
| You approve a prepared result | You, one click | "Draft the status memo and post it here for approval" |
| You choose between options | You, one word | "Research approaches A and B and recommend one" |
+20 −20 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+31−31
claude-docschanged
claude-tag/concepts/how-it-works
| Working in… | Access | Attribution | Best for |
| :---------- | :----------------------------------------- | :----------------------- | :--------------------------------- |
| A channel | The channel's connections, set by an admin | The agent's own accounts | Shared work the team should see |
| A DM | Your own claude.ai connectors | You | Personal tasks using your own data |
| Working in… | Access | Attribution | Best for |
+31 −31 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/good-habits
±changed
+13−1
claude-docschanged
claude-tag/users/good-habits
### Mentioning a user group
Ask Claude to notify a user group, such as an on-call rotation. Claude mentions the group, and Slack notifies its members. If Claude writes the group's @handle as plain text instea
+13 −1 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+3−1
claude-docschanged
claude-tag/concepts/security-and-data
When you ask Claude in one channel to post into another, Claude works with the access bundles and instructions of the channel you asked in, not the target channel's. From a private
A session can publish an artifact, a web page hosted on claude.ai with the link posted in the thread, and the page stays available after the sandbox is released. Anyone with access
A session can publish an artifact, a web page hosted on claude.ai with the link posted in the thread, and the page stays available after the sandbox is released. Anyone with access
+3 −1 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+20−2
claude-docschanged
claude-tag/concepts/how-it-works
* [Lifecycle of a request](#lifecycle-of-a-request): the five-step loop, [the checklist](#how-the-checklist-updates), [per-channel access](#channel-access), and [scheduled tasks](#
* [Lifecycle of a request](#lifecycle-of-a-request): the five-step loop, [the checklist](#how-the-checklist-updates), [per-channel access](#channel-access), [other channels](#what-
A hosted page stays available after the session ends, and Claude updates it when you ask in the thread. Anyone with access to the channel can open it; [artifact visibility](/docs/c
A hosted page stays available after the session ends, and Claude updates it when you ask in the thread. Anyone with access to the channel can open it. [Artifact visibility](/docs/c
+20 −2 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+81−27
claude-docschanged
claude-tag/admins/troubleshooting
| Your Claude account to connect after you select **Connect Claude account** | The browser page refuses the connection, and Claude DMs you "This workspa
**Allow Claude to work in channels with guests** is set to **Restrict** or **Channel only** for this channel's [scope](/docs/claude-tag/concepts/glossary#scope), so Claude checks t
The **How should Claude work in channels with guests** setting is set to **Restrict** or **Channel only** for this channel's [scope](/docs/claude-tag/concepts/glossary#scope), so C
Either a member selected **Add to channel** on a channel Claude suggested in a direct message, or the channel's name matches an [auto-join channel pattern](/docs/claude-tag/admins/
+81 −27 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/for-slack-admins
±changed
+4−3
claude-docschanged
claude-tag/admins/for-slack-admins
A member can add Claude to a channel in one of two ways:
A member can add Claude to a channel in any of these ways:
* Select **Approve and post** on a message Claude drafts in a direct message for a public channel it isn't a member of. When the member approves, Claude posts the message and joins
When a member selects **Add to channel** or an auto-join pattern matches, Claude adds itself to that channel using its `channels:join` scope. Slack's audit log records the join as
When a member selects **Add to channel** or **Approve and post**, or an auto-join pattern matches, Claude adds itself to that channel using its `channels:join` scope. Slack's audit
+4 −3 lines
Upstream edited 26 Sep 2026 05:33 UTC Recorded here 26 Sep 2026 05:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.