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
821pages tracked
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
69 changed this week · last read 24 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
27 Sep 2026
17 pages
+703 −626 lines
claude-code
plugins/troubleshooting
±changed
+9−1
claude-codechanged
plugins/troubleshooting
A plugin's hooks don't run. Either the **Errors** tab shows a load failure for them, the hooks load and you see `<Event> hook error` notices in the transcript, or a hook loads with
A plugin's hooks don't run, or one blocks an action. Either the **Errors** tab shows a load failure for them, the hooks load and you see `<Event> hook error` notices or a blocking
If the stderr shows the plugin's path cut off at a space, the hook's shell-form command uses `${CLAUDE_PLUGIN_ROOT}` outside quotes and the install path contains a space. Wrap the
+9 −1 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
plugins/security
±changed
+1−1
claude-codechanged
plugins/security
* **Persistent data**: when that was the last scope the plugin was installed at, uninstalling also deletes the plugin's persistent data directory, unless you pass `--keep-data`.
* **Persistent data**: by default, when that was the last scope the plugin was installed at, uninstalling also deletes the plugin's persistent data directory. For `--keep-data` and
+1 −1 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
plugins/marketplace-reference
±changed
+3−1
claude-codechanged
plugins/marketplace-reference
* **Names that impersonate an official marketplace**: names such as `official-claude-plugins` or `claude-plugins-v2`, and any name containing a non-ASCII character. The error is `M
* **Names that impersonate an official marketplace**: names such as `official-claude-plugins` or `claude-plugins-v2`, and any name containing a non-ASCII character. The error is `M
When a registered marketplace stops loading because its name imitates an official one, `claude plugin list` and `/plugin` report `Claude Code refuses the marketplace name "<name>"`
+3 −1 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
plugins/manifest-reference
±changed
+8−1
claude-codechanged
plugins/manifest-reference
The command also checks each MCP server entry the plugin declares in `.mcp.json`, in a `.json` file that [`mcpServers`](#mcpservers) names, or inline in `plugin.json`. These MCP ch
* **Errors**: an entry Claude Code would drop when it loads the plugin, a `${user_config.KEY}` reference to an option the manifest doesn't declare, and a remote `url` that isn't a
* **Warnings**: an `http://` or `ws://` URL to a non-loopback host, and a header value that looks like a literal credential
+8 −1 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
plugins/loading
±changed
+9−9
claude-codechanged
plugins/loading
| Path | What it holds
| :----------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------
| `cache/<marketplace>/<plugin>/<version>/` | One directory per installed version of a marketplace plugin. `<plugin>` is the marketplace entry name and `<version>` is
| `data/<plugin-id>/` | The plugin's persistent directory, exposed as `${CLAUDE_PLUGIN_DATA}`. For how `<plugin-id>` is formed, see [Path variabl
| `marketplaces/<name>/` | The clone or download of a marketplace added from GitHub, another Git host, or a URL. A marketplace added from a local `f
+9 −9 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
plugins/create
±changed
+2−0
claude-codechanged
plugins/create
You can also pass a folder that keeps a `.claude-plugin/marketplace.json` beside its plugin folders. As long as that `.claude-plugin/` directory holds no `plugin.json`, the plugin
+2 −0 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
plugins/cli-reference
±changed
+18−2
claude-codechanged
plugins/cli-reference
If the failure line continues with `"formatter" was not uninstalled:`, Claude Code couldn't confirm that the scope's settings no longer switch the plugin on, so the plugin stays in
#### What an uninstall deletes and keeps
When you uninstall a plugin from the last scope it's installed at, Claude Code also deletes the plugin's stored [options and secrets](/docs/en/plugins/manifest-reference#user-confi
+18 −2 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
errors
±changed
+51−0
claude-codechanged
errors
| `Claude Code refuses the marketplace name "<name>"`
| `Marketplace name impersonates an official Anthropic/Claude marketplace`
| `"<plugin>" was not uninstalled: it is still switched on in <file>`
| `"<plugin>" was not uninstalled: <file> is there and could not be read`
<h3 id="claude-code-refuses-the-marketplace-name">
+51 −0 lines
Upstream edited 27 Sep 2026 16:27 UTC Recorded here 27 Sep 2026 16:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
* `"type": "mcp_tool"`: call a tool on an already-connected MCP server. See [MCP tool hooks](/docs/en/hooks#mcp-tool-hook-fields).
* `"type": "mcp_tool"`: call a tool on a configured MCP server. See [MCP tool hooks](/docs/en/hooks#mcp-tool-hook-fields).
+1 −1 lines
Upstream edited 27 Sep 2026 15:15 UTC Recorded here 27 Sep 2026 15:37 UTC
claude-code
hooks
±changed
+19−35
claude-codechanged
hooks
* **[MCP tool hooks](#mcp-tool-hook-fields)** (`type: "mcp_tool"`): call a tool on an already-connected [MCP server](/docs/en/mcp). The tool's text output is treated like command-h
* **[MCP tool hooks](#mcp-tool-hook-fields)** (`type: "mcp_tool"`): call a tool on a configured [MCP server](/docs/en/mcp). The tool's text output is treated like command-hook stdo
| Field | Required | Description
| :------- | :------- | :-----------------------------------------------------------------------------------------------------------------------------------------------------------
| `server` | yes | Name of a configured MCP server. For a [plugin-bundled server](/docs/en/mcp#plugin-provided-mcp-servers), this is the scoped name `plugin:<plugin-name>:<ser
+19 −35 lines
Upstream edited 27 Sep 2026 15:15 UTC Recorded here 27 Sep 2026 15:37 UTC
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
86 pages
+2450 −1734 lines
claude-code
cross-session-messaging
±changed
+10−10
claude-codechanged
cross-session-messaging
| Where the other session runs | How the message travels |
| :----------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------- |
| On this machine | Over a per-session socket on macOS and Linux, or a per-session named pipe on native Windows, never through Anthropic servers |
| On another of your machines | Through Anthropic servers, arriving over that machine's [Remote Control](/docs/en/remote-control) connection |
| In the [cloud](/docs/en/claude-code-on-the-web) | Through Anthropic servers, straight to the cloud session |
+10 −10 lines
Upstream edited 26 Sep 2026 16:50 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
cross-session-messaging
±changed
+20−57
claude-codechanged
cross-session-messaging
Claude uses two tools for this: `ListAgents` to discover which agents it can reach, and `SendMessage` to deliver a message to one of them by name. With the same `SendMessage` tool,
Use messaging between independent sessions that you start and steer yourself. Claude Code has a dedicated feature for each of the other ways to run or reach multiple sessions, so u
* To continue one conversation in another terminal, or share its context with a new session, [resume the session](/docs/en/sessions#resume-a-session)
+20 −57 lines
Upstream edited 26 Sep 2026 16:50 UTC Recorded here 26 Sep 2026 17:07 UTC
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
claude-docs
claude-tag/admins/workspaces
±changed
+9−9
claude-docschanged
claude-tag/admins/workspaces
| Label | Effect
| :---------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------
| **New** | Claude Tag. Access bundles, skills, and custom instructions apply
| **Legacy** | The earlier per-user Claude in Slack. Bundles and skills do not apply. Being deprecated; see [Migrate from the earlier app](/docs/claude-tag/admins/migrate-from-ear
| **Inherit** | Use the parent scope's value. Not shown at **Default Slack access**
+9 −9 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+23−23
claude-docschanged
claude-tag/admins/setup-overview
| Prerequisite | Why you need it
| :------------------------------------------------------------------------------------------------ | :---------------------------------------------------------------------------
| A **Team or Enterprise plan** on claude.ai | Claude Tag is available on Team and Enterprise plans, on Anthropic's first-p
| A Claude organization **without Zero Data Retention (ZDR) or customer-managed encryption (CMEK)** | Claude Tag stores channel memory and session transcripts, which ZDR doesn't
| **Routines** enabled for your Claude organization | Until it is, Claude answers every mention and DM with a reply that it's unav
+23 −23 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/workspaces
±changed
+33−4
claude-docschanged
claude-tag/admins/workspaces
> Connect more Slack workspaces or an Enterprise Grid to Claude Tag, choose which Claude version each channel uses, and disconnect a workspace.
> Connect more Slack workspaces or an Enterprise Grid to Claude Tag, choose which Claude Tag version each channel uses, and disconnect a workspace.
This page covers managing Slack workspace pairings after initial setup: adding more workspaces, choosing which Claude Tag version each one runs, turning Claude on or off on the Tea
This page covers managing Slack workspace pairings after initial setup: adding more workspaces, installing the app and pairing across a Slack Enterprise Grid, choosing which Claude
## Set up Claude Tag on Enterprise Grid
+33 −4 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+3−1
claude-docschanged
claude-tag/admins/setup-overview
On Slack Enterprise Grid, installing takes two Slack actions. See [Set up Claude Tag on Enterprise Grid](/docs/claude-tag/admins/workspaces#set-up-claude-tag-on-enterprise-grid
When a Grid org admin sends `@Claude connect`, the reply includes two codes: a `workspace_` code that pairs only that workspace, and an `enterprise_` code that pairs every worksp
When a Slack Org Owner or Org Admin sends `@Claude connect`, the reply includes two codes. One begins `workspace_` and pairs only the workspace the admin sent the command in, and
+3 −1 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/users/when-claude-responds
±changed
+9−9
claude-docschanged
claude-tag/users/when-claude-responds
| 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 menti
| 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` t
+9 −9 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/prompt-library
±changed
+11−11
claude-docschanged
claude-tag/users/prompt-library
| To do this | Paste this
| :-------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------
| [Triage requests](/docs/claude-tag/users/use-cases/triage-requests) | "remember for this channel: when someone tags you on a request, check whether it duplicates som
| [Catch up](/docs/claude-tag/users/use-cases/catch-up) | "what got decided in this thread, and what's still open?"
| [Create an artifact](/docs/claude-tag/users/use-cases/create-artifacts) | "turn this thread into a one-page decision doc"
+11 −11 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/connections/datadog
±changed
+9−9
claude-docschanged
claude-tag/admins/connections/datadog
| Picker entry | Site |
| :---------------- | :------------------------------------------ |
| **Datadog** | US1 (`api.datadoghq.com`), the default site |
| **Datadog (US5)** | US5 (`api.us5.datadoghq.com`) |
| **Datadog (EU)** | EU (`api.datadoghq.eu`) |
+9 −9 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/audit
±changed
+4−4
claude-docschanged
claude-tag/admins/audit
| Tab | What it shows
| :----------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------
| **Scheduled work** | Every routine across your organization, with a **Scope** filter and a per-row **⋮** menu (View details, Pause/Resume, Delete)
| **Memory** | Each scope's memory files, where you can read what Claude has saved for that workspace or channel. Owners can also edit or delete entries there.
| Tab | What it shows |
+4 −4 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/add-connections
±changed
+25−25
claude-docschanged
claude-tag/admins/add-connections
| Connect | Examples | R
| :----------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------- | :
| Knowledge and docs | Google Drive, [Notion](/docs/claude-tag/admins/connections/notion), [Confluence](/docs/claude-tag/admins/connections/atlassian)
| Code | GitHub, [GitLab](/docs/claude-tag/admins/connections/gitlab)
| Data warehouse | BigQuery, [Snowflake](/docs/claude-tag/admins/connections/snowflake), Redshift
+25 −25 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/when-claude-responds
±changed
+1−1
claude-docschanged
claude-tag/users/when-claude-responds
The setting is on by default, so a channel Claude was just added to replies without @-mentions from the start.
The setting is on by default.
+1 −1 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/users/troubleshooting
±changed
+79−11
claude-docschanged
claude-tag/users/troubleshooting
If `@Claude` still gets no reaction and no reply after all three, send your admin [the admin entries for a silent workspace](/docs/claude-tag/admins/troubleshooting#nothing-respond
If `@Claude` still gets no reaction and no reply after all three, send the [admin entries for a silent workspace](/docs/claude-tag/admins/troubleshooting#nothing-responds) to an ad
### Claude replies in a channel without an @-mention
**What you see**
+79 −11 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/users/prompt-library
±changed
+11−1
claude-docschanged
claude-tag/users/prompt-library
> Copy-paste prompts for Claude Tag in Slack, each with why it works. See first messages, forwarded-message handoffs, channel rules, memory checks, routines, and mid-thread steerin
> Copy-paste prompts for Claude Tag in Slack, each with why it works. See first messages, handoffs, channel rules, memory checks, routines, fan-out, and steering.
## Fan out work across threads
Give Claude a list of independent tasks in a channel thread, and ask it to open one thread per task. Claude posts a top-level message for each task in the same channel, works in th
+11 −1 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/users/proactivity
±changed
+13−5
claude-docschanged
claude-tag/users/proactivity
> Claude Tag runs routines you set up from the channel. See scheduled jobs, channel watching, pull request subscriptions, paste-ready routine recipes, and how to list or pause stan
> Claude Tag runs routines you set up from a channel. See scheduled jobs, channel watching, pull request subscriptions, where results post, and how to pause them.
## Where a routine posts its results
A routine you set up from inside a thread usually reports back in that thread each time it runs, for as long as the thread's [session](/docs/claude-tag/concepts/how-it-works#what-s
+13 −5 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+9−9
claude-docschanged
claude-tag/admins/restrict-access
* **Guest channels.** By default Claude is off in any channel that includes a Slack guest. If a chosen channel has guests, also set [Allow Claude to work in channels with guests](#
* **Guest channels.** By default Claude is off in any channel that includes a Slack guest. If a chosen channel has guests, also set [**How should Claude work in channels with guest
By default, Claude is disabled in any channel that includes a Slack guest. You can change this default per scope with the **Allow Claude to work in channels with guests** setting,
By default, Claude is disabled in any channel that includes a Slack guest. You can change this default per scope with the **How should Claude work in channels with guests** setting
| **Allow** | Replies with the full access the scope gives it. Bundles, connections, and instructions from the workspace and from **Default Slack access** apply, along
+9 −9 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/connections/datadog
±changed
+3−1
claude-docschanged
claude-tag/admins/connections/datadog
Datadog has a separate API host per site, and a key only works against its own. If your account is on a site without a picker entry, pick any Datadog entry and override Allowed web
Datadog has a separate API host per site, and a key only works against its own. If your account is on a site without a picker entry, pick any Datadog entry and override the **Allow
If you override the **Allowed websites** field, replace the prefilled host with your site's API host rather than adding yours alongside it, so that **Test connection** checks your
+3 −1 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/connections/custom
±changed
+11−11
claude-docschanged
claude-tag/admins/connections/custom
| Type | Use for |
| :---------------------------------------------- | :---------------------------------------------------------------------------------------------------------- |
| **Bearer** | An API key or token sent as `Authorization: Bearer <token>`. Most SaaS REST APIs. |
| **Basic** | HTTP Basic authentication (`Authorization: Basic <base64(user:password)>`) |
| **Body parameter** | A token the API expects in the request body or query string instead of a header |
+11 −11 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/audit
±changed
+6−6
claude-docschanged
claude-tag/admins/audit
<Note>The Audit page opens for Owners in your Claude organization; the other trails on this page are visible to anyone with access to the underlying surface.</Note>
The Audit page opens for Owners in your Claude organization. The other trails on this page are visible to anyone with access to the underlying surface.
| Tab | What it shows
| :----------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------
| **Scheduled work** | Every routine across your organization, with a **Scope** filter and a per-row **⋮** menu (View details, Pause/Resume, Delete)
+6 −6 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/add-connections
±changed
+15−11
claude-docschanged
claude-tag/admins/add-connections
| Credential type | Use for
| :------------------------------------------ | :-----------------------------------------------------------------------------------------------------------------------------------
| Bearer | API keys and OAuth bearer tokens. Most SaaS REST APIs.
| Basic | HTTP Basic authentication.
| Body parameter | A token the API expects in the request body or query string instead of a header.
+15 −11 lines
Upstream edited 26 Sep 2026 05:31 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-code
security
±changed
+2−1
claude-codechanged
security
* **Credential protection**: Authentication is handled through a secure proxy that uses a scoped credential inside the sandbox, which is then translated to your actual GitHub authe
* **Credential protection**: GitHub credentials are stored encrypted on Anthropic's servers and never enter the session VM. The VM holds a short-lived credential scoped to that ses
* **Deletion**: You can [delete a session](/docs/en/claude-code-on-the-web#delete-sessions) at any time. See [Cloud execution data flow](/docs/en/data-usage#cloud-execution-data-fl
+2 −1 lines
Upstream edited 26 Sep 2026 05:24 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-code
data-usage
±changed
+2−2
claude-codechanged
data-usage
* **Code and data storage:** Your repository is cloned to an isolated VM. Code and session data are subject to the retention and usage policies for your account type (see Data rete
* **Credentials:** GitHub authentication is handled through a secure proxy; your GitHub credentials never enter the sandbox
* **Code and data storage:** Your repository is cloned into the session's isolated VM. Anthropic stores the session transcript so you can return to the session later. Code and sess
* **Credentials:** GitHub credentials are stored encrypted on Anthropic's servers and never enter the VM. GitHub traffic from the VM goes through an Anthropic proxy that attaches t
+2 −2 lines
Upstream edited 26 Sep 2026 05:24 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-code
claude-code-on-the-web
±changed
+2−0
claude-codechanged
claude-code-on-the-web
In Anthropic-hosted environments, your GitHub credentials stay encrypted on Anthropic's servers and never enter a session's VM. GitHub operations from the VM go through the [GitHub
+2 −0 lines
Upstream edited 26 Sep 2026 05:24 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-code
errors
±changed
+208−16
claude-codechanged
errors
| `Opus is experiencing high load` / `Fable is experiencing high load`
| `Couldn't save your login`
| `Authentication required · Sign in again to continue`
| `Could not refresh your login because another Claude Code process is refreshing it`
| `Failed to refresh OAuth token: another Claude Code process is refreshing it or exited mid-refresh`
+208 −16 lines
Upstream edited 26 Sep 2026 05:19 UTC Recorded here 26 Sep 2026 05:37 UTC
claude-docs
claude-tag/admins/federated-access/limits
±changed
+40−40
claude-docschanged
claude-tag/admins/federated-access/limits
| Limit | Value
| :---------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------
| Token lifetime | 10 minutes. Tokens can't be revoked before they expire. When you remove a gateway, Claude stops using it at once; when you remove a cloud role or authorizatio
| Signing algorithm | ES256 only.
| Claims | See the [identity token reference](/docs/claude-tag/admins/federated-access/token-reference#claims); verifiers must ignore claims they don't recognize.
+40 −40 lines
Upstream edited 26 Sep 2026 05:05 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/federated-access/troubleshooting
±changed
+15−9
claude-docschanged
claude-tag/admins/federated-access/troubleshooting
Claude reports a 403 from an AWS or Google Cloud API, with the provider's own error body rather than a reason beginning "request blocked".
**What it means**
The token exchange worked and Claude called the API with the exchanged credential, but the role or identity lacks permission for that action. For Google Cloud, the exchange always
+15 −9 lines
Upstream edited 26 Sep 2026 05:05 UTC Recorded here 26 Sep 2026 05:07 UTC
claude-docs
claude-tag/admins/federated-access/limits
±changed
+8−8
claude-docschanged
claude-tag/admins/federated-access/limits
| Limit | Value
| :------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------
| **Workload identity provider** | The full resource name of a provider in a workload identity pool under a numeric project, `//iam.googleapis.com/projects/<number>/l
| **Service account to act as** | Optional. A service account, `<name>@<project>.iam.gserviceaccount.com`. Default compute and App Engine service accounts aren't acc
| **Allowed Google hosts** | `googleapis.com`, a subdomain of it, or a subdomain of `clients6.google.com`.
+8 −8 lines
Upstream edited 26 Sep 2026 05:05 UTC Recorded here 26 Sep 2026 05:07 UTC
claude-docs
government/tenant-admin/setup-wizard
±changed
+1−1
claude-docschanged
government/tenant-admin/setup-wizard
This step is optional. If your identity provider supports SCIM, which is a standard way for directory systems to push users and group memberships into other applications, you can c
This step is optional. If your identity provider supports SCIM, which is a standard way for directory systems to push users and group memberships into other applications, you can c
+1 −1 lines
Upstream edited 26 Sep 2026 03:45 UTC Recorded here 26 Sep 2026 04:07 UTC
claude-docs
government/tenant-admin/identity-and-access
±changed
+7−3
claude-docschanged
government/tenant-admin/identity-and-access
Claude for Government routes users to your tenant by the domain of their email address, so at least one domain must be registered before anyone can sign in. The **Domains** section
Claude for Government routes users to your tenant by the domain of their email address, so at least one domain must be registered before anyone can sign in. The **Domains** section
Every user signs in through your agency's identity provider (for example, Microsoft Entra, Okta, or ADFS). You register Claude for Government as an application in your identity pro
Every user signs in through your agency's identity provider (for example, Microsoft Entra, Okta, or ADFS). Your identity provider needs to support SAML 2.0 or OpenID Connect (OIDC)
+7 −3 lines
Upstream edited 26 Sep 2026 03:45 UTC Recorded here 26 Sep 2026 04:07 UTC
claude-code
remote-control
±changed
+187−224
claude-codechanged
remote-control
<Note>
Remote Control is available on all plans. On Team and Enterprise, it is off by default until an Owner enables the Remote Control toggle in [Claude Code admin settings](https://cl
</Note>
* **Survive interruptions**: if your laptop sleeps or your network drops, Claude Code reconnects automatically when your machine comes back online. While the connection is rebuildi
+187 −224 lines
Upstream edited 26 Sep 2026 03:22 UTC Recorded here 26 Sep 2026 03:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
If the server reports instead that the previous session is gone, you don't see this message. Claude Code starts a new session in its place or shows [`Previous session is unavailabl
If the server reports instead that the previous session is gone, you don't see this message. Claude Code starts a new session in its place or shows [`Previous session is unavailabl
+1 −1 lines
Upstream edited 26 Sep 2026 03:22 UTC Recorded here 26 Sep 2026 03:37 UTC
claude-code
mobile
±changed
+6−6
claude-codechanged
mobile
| Feature | What you connect to | When to use
| :--------------------------------------------- | :-------------------------------------------------------------------------------- | :--------------------------------------------
| [Cloud sessions](/docs/en/claude-code-on-the-web) | A session on cloud infrastructure, Anthropic-managed by default | Your repository is on GitHub and the tas
| [Projects](/docs/en/claude-projects) | A conversation where Claude coordinates parallel threads of work and reports back | You have a stream of related work rather
| [Remote Control](/docs/en/remote-control) | A Claude Code session running on your computer | The work needs your local filesystem, to
+6 −6 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
claude-projects
±changed
+44−44
claude-codechanged
claude-projects
| Group | What's in it
| :------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------
| **Ready for review** | Threads whose pull request is open and awaiting review
| **Waiting on you** | Threads that need your reply or approval, or that failed
| **Working** | Threads still running
+44 −44 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agents
±changed
+7−7
claude-codechanged
agents
| Approach | What it gives you
| :--------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------
| [Subagents](/docs/en/sub-agents) | Delegated workers inside one session that do a side task in their own context and return a summary
| [Agent view](/docs/en/agent-view) | One screen to dispatch and monitor sessions running in the background, opened with `claude agents`. Research preview
| [Agent teams](/docs/en/agent-teams) | Multiple coordinated sessions with a shared task list and inter-agent messaging, managed by a lead. Experimental and disabled by default
+7 −7 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
Use Remote Control when you're in the middle of local work and want to keep going from another device. Use a cloud session when you want to start a task without any local setup, wo
Use Remote Control when you're in the middle of local work and want to keep going from another device. Use a cloud session when you want to start a task without any local setup, wo
+1 −1 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
permission-modes
±changed
+61−39
claude-codechanged
permission-modes
On Pro, Max, and Team plans, the built-in starting permission mode is auto mode. [Which mode a session starts in](#which-mode-a-session-starts-in) covers the surfaces and settings
With Claude Code v2.1.283 or later, auto mode is the built-in starting permission mode for interactive terminal and VS Code sessions. On earlier versions, it's the built-in startin
| Work hands-off in auto mode | `claude --permission-mode auto`, the [built-in starting permission mode](#which-mode-a-session-starts-in) on Pro, Max,
| Work hands-off in auto mode | `claude --permission-mode auto`, the [built-in starting permission mode](#which-mode-a-session-starts-in) with v2.1.283
The built-in default depends on how you run Claude Code, on your plan, and on whether Claude Code could fetch its feature flags. The first row that matches your session applies. Th
+61 −39 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
mobile
±changed
+6−6
claude-codechanged
mobile
| Feature | What you connect to | When to use
| :--------------------------------------------- | :------------------------------------------------------------------------- | :---------------------------------------------------
| [Cloud sessions](/docs/en/claude-code-on-the-web) | A session on cloud infrastructure, Anthropic-managed by default | Your repository is on GitHub and the task shoul
| [Projects](/docs/en/claude-projects) | A conversation where Claude coordinates parallel cloud sessions as threads | You have a stream of related work rather than o
| [Remote Control](/docs/en/remote-control) | A Claude Code session running on your computer | The work needs your local filesystem, tools, or
+6 −6 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
claude-projects
±changed
+44−6
claude-codechanged
claude-projects
Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web): Claude Code running in the cloud rather than on your machine. When a task needs something only your compu
Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web): Claude Code running in the cloud rather than on your machine. When a task needs something only your compu
* **A build or migration bigger than a session**: "Build what `docs/spec.md` describes" or "Move the app off the deprecated ORM." The work splits into threads that each take a part
* **A build or migration bigger than a session**: "Build what `docs/spec.md` describes" or "Move the app off the deprecated ORM." The work splits into threads that each take a part
Cloud threads work on GitHub repositories and on the files, folders, and Google Drive folders you upload to the project, not on files or tools that exist only on your machine. If a
+44 −6 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
agents
±changed
+7−7
claude-codechanged
agents
| Approach | What it gives you
| :--------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------
| [Subagents](/docs/en/sub-agents) | Delegated workers inside one session that do a side task in their own context and return a summary
| [Agent view](/docs/en/agent-view) | One screen to dispatch and monitor sessions running in the background, opened with `claude agents`. Research preview
| [Agent teams](/docs/en/agent-teams) | Multiple coordinated sessions with a shared task list and inter-agent messaging, managed by a lead. Experimental and disabled by default
+7 −7 lines
Upstream edited 26 Sep 2026 03:05 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
tools-reference
±changed
+66−66
claude-codechanged
tools-reference
| Tool | Description
| :--------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------
| `Agent` | Spawns a [subagent](/docs/en/sub-agents) with its own context window to handle a task. With [agent teams](/docs/en/agent-teams) enabled, a call that carr
| `Artifact` | Publishes an HTML or Markdown file as an [artifact](/docs/en/artifacts): a private, interactive page on claude.ai. You can share it with a public link, o
| `AskUserQuestion` | Asks multiple-choice questions to gather requirements or clarify ambiguity. Questions stay open until you answer them by default. See [AskUserQuestion to
+66 −66 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
quickstart
±changed
+12−12
claude-codechanged
quickstart
| Command | What it does | Example |
| ------------------- | ------------------------------------------------------ | ----------------------------------- |
| `claude` | Start interactive mode | `claude` |
| `claude "task"` | Start interactive mode with an initial prompt | `claude "fix the build error"` |
| `claude -p "query"` | Run one-off query, then exit | `claude -p "explain this function"` |
+12 −12 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
best-practices
±changed
+25−25
claude-codechanged
best-practices
| Strategy | Before | After
| ------------------------------------- | ------------------------------------------------------- | --------------------------------------------------------------------------------
| **Provide verification criteria** | *"implement a function that validates email addresses"* | *"write a validateEmail function. example test cases: [[email protected]](mailto:
| **Verify UI changes visually** | *"make the dashboard look better"* | *"\[paste screenshot] implement this design. take a screenshot of the result and
| **Address root causes, not symptoms** | *"the build is failing"* | *"the build fails with this error: \[paste error]. fix it and verify the build s
+25 −25 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
vs-code
±changed
+2−2
claude-codechanged
vs-code
* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch permission modes. On Pro, Max, and Team plans, Auto is the built-in starting permission m
* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch permission modes. With Claude Code v2.1.283 or later, Auto is the built-in starting permi
* **Claude Code settings** in `~/.claude/settings.json`: shared between the extension and CLI. Use it for allowed commands, environment variables, hooks, and MCP servers. On Pro, M
* **Claude Code settings** in `~/.claude/settings.json`: shared between the extension and CLI. Use it for allowed commands, environment variables, hooks, and MCP servers. With Clau
+2 −2 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
On Pro, Max, and Team plans, Claude Code starts sessions in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), where a classifier decides most of these prom
In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), a classifier decides most permission prompts instead of you. The `Permission required` column shows wh
+1 −1 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
Set `permissionMode` to choose the permission mode a subagent runs in. Use the modes' config values, so Manual mode is `default`. If you leave it unset, the subagent inherits the m
Set `permissionMode` to choose the permission mode a subagent runs in. Use the modes' config values, so Manual mode is `default`. If you leave it unset, the subagent inherits the m
+1 −1 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
settings-reference
±changed
+4−3
claude-codechanged
settings-reference
Choose whether Claude Code uses the auto mode classifier to review shell commands in plan mode. With the default `true`, the classifier reviews each command during planning when au
Choose whether Claude Code uses the auto mode classifier to review shell commands in plan mode. With the default `true`, the classifier reviews each command during planning when au
* `true`: the same as unset; when auto mode is available, the classifier reviews each shell command during planning instead of prompting you for it. A `false` in any of these fil
* `true`: the same as unset; when auto mode is available, the classifier reviews each shell command during planning instead of prompting you for it, except [critical-path removal
Set the [permission mode](/docs/en/permission-modes) new sessions start in. When you leave it unset, sessions start in the [built-in default](/docs/en/permission-modes#which-mode-a
+4 −3 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
quickstart
±changed
+6−6
claude-codechanged
quickstart
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme=
```batch theme={null}
+6 −6 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
how-claude-code-works
±changed
+1−1
claude-codechanged
how-claude-code-works
* **Auto**: a classifier reviews most actions in the background and blocks the risky ones instead of asking you. On Pro, Max, and Team plans, it's the [built-in starting permission
* **Auto**: a classifier reviews most actions in the background and blocks the risky ones instead of asking you. With Claude Code v2.1.283 or later, it's the [built-in starting per
+1 −1 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks
A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks
+1 −1 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and th
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and th
+1 −1 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
env-vars
±changed
+3−3
claude-codechanged
env-vars
| `CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT` | Set to `1` to turn off the time limit on [critical-path removal](/docs/en/permission-modes#critical-paths) prompts. In `
| `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT` | Set to `1` to turn off the [critical-path](/docs/en/permission-modes#critical-paths) check for a recursive `rm` whose ta
* [Start sessions in auto mode by default](/docs/en/permission-modes#which-mode-a-session-starts-in) on Pro, Max, and Team plans
* Have the VS Code extension [read settings files for the starting permission mode](/docs/en/permission-modes#switch-permission-modes)
In your first session after you install Claude Code, or upgrade to a version that adds a feature, a [flag-gated feature](#features-that-need-feature-flag-fetching) can be missing,
+3 −3 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
best-practices
±changed
+3−3
claude-codechanged
best-practices
On Pro, Max, and Team plans, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal and VS Code s
In Manual mode, the built-in starting permission mode on other plans, Claude Code asks before actions that might modify your system: file writes, Bash commands, MCP tools. That's s
With Claude Code v2.1.283 or later, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal and VS
+3 −3 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
admin-setup
±changed
+1−1
claude-codechanged
admin-setup
| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built
| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built
+1 −1 lines
Upstream edited 26 Sep 2026 02:54 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
auto-mode-config
±changed
+1−1
claude-codechanged
auto-mode-config
Set `autoMode.classifyAllShell` to `true` to suspend every Bash and PowerShell allow rule while auto mode is active, so the classifier evaluates every shell command regardless of y
Set `autoMode.classifyAllShell` to `true` to suspend every Bash and PowerShell allow rule while auto mode is active, so the classifier evaluates every shell command regardless of y
+1 −1 lines
Upstream edited 26 Sep 2026 02:53 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
agent-sdk/permissions
±changed
+6−2
claude-codechanged
agent-sdk/permissions
Check `allow` rules (from `allowed_tools` and settings.json). If a rule matches, the tool is approved. A call the tool approves on its own is resolved at this step too, with no
Check `allow` rules (from `allowed_tools` and settings.json). If a rule matches, the tool is approved. A call the tool approves on its own is resolved at this step too, with no
`rm` and `rmdir` removals targeting a [critical path](/docs/en/permission-modes#critical-paths) are never approved by an allow rule. Whether they then reach your callback depen
**Auto-approved tools never reach `canUseTool`.** A tool call approved at any earlier step, by `acceptEdits` or `bypassPermissions`, or by an allow rule, skips your `canUseTool`
+6 −2 lines
Upstream edited 26 Sep 2026 02:53 UTC Recorded here 26 Sep 2026 03:07 UTC
claude-code
auto-mode-classifier-billing
+new page
+55−0
claude-codenew page
auto-mode-classifier-billing
No line of the body moved in this read.
+55 −0 lines
Upstream edited 26 Sep 2026 02:50 UTC Recorded here 10 Oct 2026 18:07 UTC
claude-code
sub-agents
±changed
+8−4
claude-codechanged
sub-agents
The `--agents` flag accepts JSON with a `prompt` field plus these [frontmatter](#supported-frontmatter-fields) fields: `description`, `tools`, `disallowedTools`, `model`, `permissi
Each top-level key in the JSON is the agent's name. Don't start a name with `-`.
In [non-interactive mode](/docs/en/headless), `--agents` also accepts the path to a JSON file holding the same object, for definitions too large to pass on the command line. For ex
+8 −4 lines
Upstream edited 26 Sep 2026 01:36 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
errors
±changed
+9−2
claude-codechanged
errors
| `Error: --agents takes a JSON object, or a file path only with --print (-p)`
| `Error: --agents file not found`
The value you passed to `--agents` is invalid, so `claude` exits with code 1 instead of starting the session. When you pass `--safe-mode`, `--resume`, or `--continue`, or set [`CLA
The value you passed to `--agents` is invalid, so `claude` exits with code 1 instead of starting the session. When you pass `--safe-mode` or set [`CLAUDE_CODE_SAFE_MODE`](/docs/en/
1. When the value doesn't parse as JSON, Claude Code prints one `invalid JSON:` line carrying the JSON parser's own message
+9 −2 lines
Upstream edited 26 Sep 2026 01:36 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-t
| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-t
+1 −1 lines
Upstream edited 26 Sep 2026 01:36 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
jetbrains
±changed
+3−3
claude-codechanged
jetbrains
| Tool name (as seen by hooks) | What it does
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------
| `mcp__ide__getDiagnostics` | Returns the IDE's inspection diagnostics, the errors and warnings shown in the editor. Each call covers one file: the file Claude specifies, or the
| Tool name (as seen by hooks) | What it does | Read-only |
| - | - | - |
+3 −3 lines
Upstream edited 26 Sep 2026 01:12 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
vs-code
±changed
+10−2
claude-codechanged
vs-code
Browse or search your cloud sessions. Click any session to download it and continue the conversation locally.
Browse or search the sessions. Click one to continue the conversation locally.
Only cloud sessions started with a GitHub repository appear in the Web tab. Resuming loads the conversation history locally; changes are not synced back to claude.ai.
When the folder you have open is a GitHub repository, the Web tab shows only sessions from that repository.
+10 −2 lines
Upstream edited 26 Sep 2026 01:12 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
jetbrains
±changed
+5−1
claude-codechanged
jetbrains
**Selection and open-file context.** While connected, the CLI includes your current editor selection and the path of the active file as context on each prompt you send. The transcr
**Selection and open-file context.** While connected, the CLI includes your current editor selection and the path of the active file as context on each prompt you send. The transcr
If you [queue a message while Claude works](/docs/en/interactive-mode#queue-messages-while-claude-works), it keeps the selection you had when you pressed `Enter`, whatever you sele
+5 −1 lines
Upstream edited 26 Sep 2026 01:12 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
interactive-mode
±changed
+3−1
claude-codechanged
interactive-mode
Type a message and press `Enter` while Claude is working. Claude Code queues the message instead of interrupting the turn, and lists the queued entries above the input box until it
Type a message and press `Enter` while Claude is working. Claude Code queues the message instead of interrupting the turn, and lists the queued entries in the conversation until it
If you queue a message with a selection attached from a [connected IDE](/docs/en/vs-code#the-built-in-ide-mcp-server) or the [diff panel](#diff-panel), it keeps the selection you h
+3 −1 lines
Upstream edited 26 Sep 2026 01:12 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
how-claude-code-works
±changed
+1−1
claude-codechanged
how-claude-code-works
* **Type a correction and press `Enter`** without stopping Claude. The message shows as queued above the input box. If Claude is running tool calls, it reads the message as soon as
* **Type a correction and press `Enter`** without stopping Claude. The message shows as queued in the conversation. If Claude is running tool calls, it reads the message as soon as
+1 −1 lines
Upstream edited 26 Sep 2026 01:12 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
checkpointing
±changed
+1−1
claude-codechanged
checkpointing
When a message you [queue while Claude works](/docs/en/interactive-mode#queue-messages-while-claude-works) reaches Claude within the running turn, it joins that turn instead of sta
When a message you [queue while Claude works](/docs/en/interactive-mode#queue-messages-while-claude-works) reaches Claude within the running turn, it joins that turn instead of sta
+1 −1 lines
Upstream edited 26 Sep 2026 01:12 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
voice-dictation
±changed
+26−26
claude-codechanged
voice-dictation
| Command | Effect |
| :------------ | :-------------------------------------------- |
| `/voice` | Toggle on or off, keep the current mode |
| `/voice hold` | Enable in [hold mode](#hold-to-record) |
| `/voice tap` | Enable in [tap mode](#tap-to-record-and-send) |
+26 −26 lines
Upstream edited 26 Sep 2026 01:10 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
voice-dictation
±changed
+2−2
claude-codechanged
voice-dictation
Run `/voice` to enable dictation. The first time you enable it, Claude Code runs a microphone check. On macOS, this triggers the system microphone permission prompt for your termin
Run `/voice` to enable dictation. When you enable it, Claude Code runs a microphone check. On macOS, this triggers the system microphone permission prompt for your terminal if it h
* **`Voice input is failing repeatedly and has been paused`**: voice dictation hit three capture failures within 10 seconds. Claude Code pauses dictation until 10 seconds have pass
* **`Voice input is failing repeatedly and has been paused`**: voice dictation hit three failures within 10 seconds. Claude Code pauses dictation until 10 seconds have passed since
+2 −2 lines
Upstream edited 26 Sep 2026 01:10 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
agent-sdk/typescript
±changed
+8−2
claude-codechanged
agent-sdk/typescript
Generic text banner emitted by the loop. Carries non-error status lines, hook feedback such as a `UserPromptSubmit` hook's block reason, and command output. On Claude Code v2.1.227
Generic text banner emitted by the loop. Carries warnings, notices, and other non-error status lines Claude Code raises, and hook feedback such as a `UserPromptSubmit` hook's block
On Claude Code v2.1.227 or later, a hook's [`systemMessage`](/docs/en/hooks#json-output) can arrive as this message, with each line prefixed by the hook's name, such as `PostToolUs
+8 −2 lines
Upstream edited 26 Sep 2026 01:10 UTC Recorded here 26 Sep 2026 01:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.