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
26 Sep 2026
86 pages
+2450 −1734 lines
claude-code
code-review
±changed
+18−18
claude-codechanged
code-review
| Marker | Severity | Meaning |
| :----- | :----------- | :------------------------------------------------------------------ |
| 🔴 | Important | A bug that should be fixed before merging |
| 🟡 | Nit | A minor issue, worth fixing but not blocking |
| 🟣 | Pre-existing | A bug that exists in the codebase but was not introduced by this PR |
+18 −18 lines
Upstream edited 26 Sep 2026 01:09 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
code-review
±changed
+2−2
claude-codechanged
code-review
Review runs are best-effort. A failed run never blocks your PR, but it also doesn't retry on its own. This section covers how to recover from a failed run and where to look when th
Review runs are best-effort, and a failed run never blocks your PR. Code Review retries some interrupted reviews on its own. This section covers how to run a review again yourself
When the review infrastructure hits an internal error or exceeds its time limit, the check run completes with a title of **Code review encountered an error** or **Code review timed
When a review fails or exceeds its time limit, the check run completes with a title such as **Code review failed** or **Code review timed out**. The conclusion is still neutral, so
+2 −2 lines
Upstream edited 26 Sep 2026 01:09 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
"auto", # Model classifier approves or denies permission prompts
"auto", # A model classifier reviews actions such as shell commands and network requests
+1 −1 lines
Upstream edited 26 Sep 2026 01:08 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
* **Default**: unset, so Claude Code adds `Co-Authored-By: <name> <[email protected]>`. The name is the session's active model, such as `Claude Sonnet 5`.
* **Default**: unset, so Claude Code adds `Co-Authored-By: <name> <[email protected]>`. The name is the model in use when the commit is made, such as `Claude Sonnet 5`. When a
+1 −1 lines
Upstream edited 26 Sep 2026 01:08 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
accessibility
±changed
+22−22
claude-codechanged
accessibility
| Option | Type | What it changes
| :---------------------------------------------------------------------- | :------------------- | :--------------------------------------------------------------------------------
| [`--ax-screen-reader`](/docs/en/cli-reference#cli-flags) | Flag | Screen reader mode for one session.
| [`CLAUDE_AX_SCREEN_READER`](/docs/en/env-vars#variables) | Environment variable | Screen reader mode for sessions started from the shell where you set it.
| [`axScreenReader`](/docs/en/settings-reference#axscreenreader) | Setting | Screen reader mode for every session when `true`.
+22 −22 lines
Upstream edited 26 Sep 2026 01:07 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
accessibility
±changed
+1−1
claude-codechanged
accessibility
In screen reader mode, menus you'd normally navigate with the arrow keys, including permission prompts, become numbered lists. Claude Code announces each option as a numbered line,
In screen reader mode, menus you'd normally navigate with the arrow keys, including permission prompts, become numbered lists. Claude Code announces each option as a numbered line,
+1 −1 lines
Upstream edited 26 Sep 2026 01:07 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
debug-your-config
±changed
+29−29
claude-codechanged
debug-your-config
| Command | Shows
| :--------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------
| `/memory` | Memory file locations across user and project scopes with the option to open each in your editor, plus access to the auto memory folder and the auto memory tog
| `/skills` | Available skills from project, user, and plugin sources
| `/hooks` | Active hook configurations
+29 −29 lines
Upstream edited 26 Sep 2026 01:07 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
debug-your-config
±changed
+1−1
claude-codechanged
debug-your-config
| Permissions, hooks, or env set globally are ignored | Configuration was added to `~/.claude.json`
| Permissions or hooks set globally are ignored | Configuration was added to `~/.claude.json`
+1 −1 lines
Upstream edited 26 Sep 2026 01:07 UTC Recorded here 26 Sep 2026 01:37 UTC
claude-code
routines
±changed
+13−13
claude-codechanged
routines
| Event | Triggers when |
| :----------- | :---------------------------------------------------------------------------- |
| Event | Triggers when |
| :- | :- |
| Release | A release is created, published, edited, or deleted |
+13 −13 lines
Upstream edited 26 Sep 2026 01:06 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
routines
±changed
+2−1
claude-codechanged
routines
* The artifact isn't shared publicly, and isn't shared with specific people or your organization with the latest version chosen as the version viewers see
* The artifact isn't shared publicly
* If the artifact is shared with specific people or your organization, its viewers don't automatically see each new version
+2 −1 lines
Upstream edited 26 Sep 2026 01:06 UTC Recorded here 26 Sep 2026 01:07 UTC
claude-code
plugins/create
±changed
+2−0
claude-codechanged
plugins/create
To have Claude scaffold and check a larger plugin with you, [install](/docs/en/plugins/install#install-a-plugin) Anthropic's `plugin-dev` plugin from the `claude-plugins-official`
+2 −0 lines
Upstream edited 26 Sep 2026 01:05 UTC Recorded here 26 Sep 2026 01:07 UTC
claude-code
model-config
±changed
+11−7
claude-codechanged
model-config
Opus 5.5 [defaults to `medium`](#adjust-effort-level), one level below Opus 5's default of `high`. In Anthropic's testing, Opus 5.5 at `medium` matches or exceeds Opus 5 at `high`
On third-party providers, [Customize pinned model display and capabilities](#customize-pinned-model-display-and-capabilities) describes what a pinned model's row in the `/model` pi
| Environment variable | Description |
+11 −7 lines
Upstream edited 26 Sep 2026 00:33 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
llm-gateway-protocol
±changed
+4−0
claude-codechanged
llm-gateway-protocol
Deliver each response's full event sequence without dropping, duplicating, or reordering events. When an event references a content block whose `content_block_start` never arrived,
Relay each response through its final `message_delta` and `message_stop` events before ending the body. A body that ends after a `message_delta` carrying a `stop_reason`, with no c
+4 −0 lines
Upstream edited 26 Sep 2026 00:30 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
errors
±changed
+12−1
claude-codechanged
errors
| `Part of the response never arrived` / `The response stream was malformed`
| `API Error: Content block not found` / `API Error: Content block already closed`
API Error: Part of the response never arrived. The response above may be incomplete.
API Error: The response stream was malformed. The response above may be incomplete.
* `Connection lost mid-response`: the connection dropped.
+12 −1 lines
Upstream edited 26 Sep 2026 00:30 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
memory
±changed
+4−0
claude-codechanged
memory
If you point a `.claude/rules/` or `CLAUDE.md` symlink at a network path such as the UNC share `\\server\share` or a path under `/net` or `/Network`, the linked instructions don't
If one of your instruction files is over the recommended length, you see a warning at startup and when you run `/status`. You also see a warning when files that are each within tha
+4 −0 lines
Upstream edited 26 Sep 2026 00:30 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
prompt-caching
±changed
+29−14
claude-codechanged
prompt-caching
These actions cause the next request to miss part or all of the cache. You see a one-time slower, more expensive turn, after which the new prefix is cached. Most of them are avoida
These actions can cause the next request to miss part or all of the cache. You see a one-time slower, more expensive turn, after which the new prefix is cached. Most of them are av
* [Connecting or disconnecting an MCP server](#connecting-or-disconnecting-an-mcp-server)
* [Connecting or removing an MCP server](#connecting-or-removing-an-mcp-server)
### Connecting or disconnecting an MCP server
+29 −14 lines
Upstream edited 26 Sep 2026 00:29 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
cloud-environments
±changed
+38−38
claude-codechanged
cloud-environments
| Level | Outbound connections |
| :---------- | :------------------------------------------------------------------------------------------- |
| **None** | No outbound network access through the session's network |
| Level | Outbound connections |
| :- | :- |
+38 −38 lines
Upstream edited 26 Sep 2026 00:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
cloud-environments
±changed
+14−3
claude-codechanged
cloud-environments
In Anthropic-hosted environments, each session gets a fresh virtual machine (VM) running Ubuntu 24.04 on x86\_64, regardless of your own operating system and CPU architecture, with
In Anthropic-hosted environments, each session gets a fresh virtual machine (VM) running Ubuntu 24.04 on x86\_64, regardless of your own operating system and CPU architecture, with
### Time limits
In Anthropic-hosted environments, these time limits apply to long-running work in a cloud session, such as a build, an install, or a test run. Each entry links to the section that
+14 −3 lines
Upstream edited 26 Sep 2026 00:27 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
claude-code-on-the-web
±changed
+1−0
claude-codechanged
claude-code-on-the-web
* **Time limits**: commands Claude runs and SessionStart hooks have default timeouts you can change, and a setup script is cached only when it finishes in roughly five minutes. See
+1 −0 lines
Upstream edited 26 Sep 2026 00:27 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
skills
±changed
+80−80
claude-codechanged
skills
| Skill | Purpose |
| :--------------------- | :---------------------------------------------------------------------------------------------------------------- |
| `/run` | Launch and drive your app to see a change working |
| `/verify` | Build and run your app to confirm a code change does what it should, without falling back to tests or type checks |
| `/run-skill-generator` | Teach `/run` and `/verify` how to build and launch your project |
+80 −80 lines
Upstream edited 26 Sep 2026 00:27 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
skills
±changed
+4−2
claude-codechanged
skills
Claude Code watches skill directories for file changes, except in [bare mode](/docs/en/headless#start-faster-with-bare-mode). When you add, edit, or remove a skill under `~/.claude
Claude Code watches skill directories for file changes, except in [bare mode](/docs/en/headless#start-faster-with-bare-mode). When you add, edit, or remove a skill under `~/.claude
If you create a top-level skills directory that didn't exist when the session started, run [`/reload-skills`](/docs/en/commands#all-commands) to pick up the skills you put there. C
Claude Code loads a listing of skill names and descriptions into context so Claude knows what's available. The listing always contains every skill name, but if you have many skills
+4 −2 lines
Upstream edited 26 Sep 2026 00:27 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
goal
±changed
+5−5
claude-codechanged
goal
| Approach | Next turn starts when
| :------------------------------------------------------------------ | :-----------------------------------------------------------------------------------------------------------
| `/goal` | The previous turn finishes, or, in an interactive session, an [idle check-in](#background-work-defers-evalua
| [`/loop`](/docs/en/scheduled-tasks#run-a-prompt-repeatedly-with-%2Floop) | A time interval elapses
| [Stop hook](/docs/en/hooks-guide#prompt-based-hooks) | The previous turn finishes
+5 −5 lines
Upstream edited 26 Sep 2026 00:26 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
goal
±changed
+1−1
claude-codechanged
goal
* An authentication failure, when Claude Code manages its own credentials. When a host manages them for you, such as the desktop app, the VS Code extension, or a [cloud session](/d
* An authentication failure, when Claude Code manages its own credentials. When a host manages them for you, such as the desktop app or a [cloud session](/docs/en/claude-code-on-th
+1 −1 lines
Upstream edited 26 Sep 2026 00:26 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
statusline
±changed
+57−57
claude-codechanged
statusline
| Field | Description
| -------------------------------------------------------------------------------- | -----------------------------------------------------------------------------------------------
| `model.id`, `model.display_name` | Current model identifier and display name
| `cwd`, `workspace.current_dir` | Current working directory. Both fields contain the same value; `workspace.current_dir` is prefe
| `workspace.project_dir` | Directory where Claude Code was launched, which may differ from `cwd` if the working directory
+57 −57 lines
Upstream edited 26 Sep 2026 00:24 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
statusline
±changed
+2−2
claude-codechanged
statusline
<Note>The status line runs locally and does not consume API tokens. It temporarily hides during certain UI interactions, including autocomplete suggestions, the help menu, and perm
<Note>The status line runs locally and does not consume API tokens. It temporarily hides during certain UI interactions, including the help menu and permission prompts.</Note>
* Run `claude --debug` to log the exit code and stderr from the first status line invocation in a session
* Run `claude --debug` to log your script's stderr on every status line invocation, and its exit code on the first invocation in a session
+2 −2 lines
Upstream edited 26 Sep 2026 00:24 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models
| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for the [default Haiku model](/docs/en/prompt-caching#disable-prompt-caching), wher
+1 −1 lines
Upstream edited 26 Sep 2026 00:20 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
workflows
±changed
+41−41
claude-codechanged
workflows
| | Subagents | Skills | Agent teams | Workflows |
| :------------------------------ | :----------------------------- | :--------------------------- | :------------------------------------- | :----------------------------------- |
| What it is | A worker Claude spawns | Instructions Claude follows | A lead agent supervising peer sessions | A script the runtime executes |
| Who decides what runs next | Claude, turn by turn | Claude, following the prompt | The lead agent, turn by turn | The script |
| Where intermediate results live | Claude's context window | Claude's context window | A shared task list | Script variables |
+41 −41 lines
Upstream edited 26 Sep 2026 00:20 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
workflows
±changed
+3−1
claude-codechanged
workflows
When workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is
When workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is
No setting turns off [ultracode](#let-claude-decide-with-ultracode) alone. To keep workflows but rule out ultracode, set an [effort cap](/docs/en/model-config#organization-effort-l
+3 −1 lines
Upstream edited 26 Sep 2026 00:20 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/concepts/glossary
±changed
+6−6
claude-docschanged
claude-tag/concepts/glossary
| | Legacy (the earlier Claude in Slack) | New (Claude Tag) |
| :------------- | :------------------------------------------ | :------------------------------------------------------------------- |
| Identity | Each user links their own claude.ai account | One agent identity with org-level service credentials |
| Sessions | Spawned per request | One persistent session per thread, shared |
| Memory | None | Per-channel memory, plus workspace notes shared from public channels |
+6 −6 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/concepts/agent-identity
±changed
+17−17
claude-docschanged
claude-tag/concepts/agent-identity
| When the destination |
| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Matches a connection's rule, its [allowed websites](/docs/claude-tag/admins/add-connections#set-allowed-websites)
| Is on the [bundle](/docs/claude-tag/concepts/glossary#access-bundle)'s [Domains list](/docs/claude-tag/admins/add-connections#allow-a-host-without-a-credential) but matches no co
| Is allowed by the network access setting of the [environment](/docs/claude-tag/concepts/glossary#environment) the [scope](/docs/claude-tag/concepts/glossary#scope)'s sessions run
+17 −17 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/connections/google
±changed
+9−9
claude-docschanged
claude-tag/admins/connections/google
| Route | When to use |
| :-------------------------- | :---------------------------------------------------------------------------------------------------------------------------------- |
| **OAuth (Connect button)** | Fastest path. An admin signs in with a Google account that has access to the content Claude needs. |
| Route | When to use |
| :- | :- |
+9 −9 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/connections/amplitude
±changed
+7−7
claude-docschanged
claude-tag/admins/connections/amplitude
| Route | What Claude can do
| :------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------
| **API key and secret key** (**Use an API token**) | Run analytics queries, such as event segmentation, funnels, and retention, through Amplitude's [Dashboard REST API](https://a
| **Amplitude sign-in** (**Sign in with Amplitude**) | Work with charts, dashboards, cohorts, and experiments through Amplitude's MCP tools, which can create and edit content as we
| Route | What Claude can do | Amplitude data center | What you need |
+7 −7 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/troubleshooting
±changed
+1−1
claude-docschanged
claude-tag/users/troubleshooting
Where you message Claude determines which connectors apply. A channel session uses the connections an admin attached to it. With [personal connectors in channels](/docs/claude-tag/
Where you message Claude determines which connectors apply. A channel session uses the connections an admin attached to it. Claude can also [use your personal connectors there](/do
+1 −1 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/concepts/settings-map
±changed
+8−8
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
+8 −8 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+1−1
claude-docschanged
claude-tag/concepts/security-and-data
With [personal connectors in channels](/docs/claude-tag/concepts/personal-connectors), Claude uses a user's personal connectors in a channel only for that user's own tasks, after t
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 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+2−2
claude-docschanged
claude-tag/concepts/how-it-works
The short version: **team work → Claude Tag; personal work → Cowork or Claude Code.** Claude Tag's connections authenticate the agent itself with service accounts, not any person.
The short version: **team work → Claude Tag; personal work → Cowork or Claude Code.** Claude Tag's connections authenticate the agent itself with service accounts, not any person.
* **Personal connectors are separate from channel connections.** A connection an admin attaches to a channel is separate from a connector on your personal claude.ai account. Your o
* **Personal connectors are separate from channel connections.** A connection an admin attaches to a channel is separate from a connector on your personal claude.ai account. Your o
+2 −2 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/concepts/glossary
±changed
+2−2
claude-docschanged
claude-tag/concepts/glossary
A connection is not a connector. A connector belongs to your personal claude.ai account. A channel session uses the channel's connections. With [personal connectors in channels](/d
A connection is not a connector. A connector belongs to your personal claude.ai account. A channel session uses the channel's connections. Claude can also [use your connectors ther
A tool you add to your own claude.ai account, like Gmail, Google Drive, or a custom MCP server, listed under [Customize > Connectors](https://claude.ai/customize/connectors). Conne
A tool you add to your own claude.ai account, like Gmail, Google Drive, or a custom MCP server, listed under [Customize > Connectors](https://claude.ai/customize/connectors). Conne
+2 −2 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/concepts/agent-identity
±changed
+2−2
claude-docschanged
claude-tag/concepts/agent-identity
In Slack channels, Claude acts with its own service accounts, rather than as a specific user. An organization Owner [provisions this identity during setup](/docs/claude-tag/admins/
In Slack channels, Claude acts with its own service accounts, rather than as a specific user. An organization Owner [provisions this identity during setup](/docs/claude-tag/admins/
* **Personal connectors are separate.** A shared channel session uses only the service-account connections an admin attached. With [personal connectors in channels](#personal-conne
* **Personal connectors are separate.** A shared channel session uses only the service-account connections an admin attached. Claude [uses the connectors on your own claude.ai acco
+2 −2 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/admins/healthcare
±changed
+5−1
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, Claude works on the member's own Claude account
* **Block a connector for everyone.** A connector you restrict for your organization on the [**Connectors** admin page](https://claude.ai/admin-settings/connectors) stays restricte
* **Require human review.** On the Enterprise plan, turn on **Require human review of every message** in the **Personal connectors** section at [`claude.ai/admin-settings/claude-ta
+5 −1 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/admins/customize
±changed
+1−1
claude-docschanged
claude-tag/admins/customize
An Owner configures Claude's connections, plugins, and skills, and they apply per scope. They are separate from the connectors, skills, or MCP servers an individual user has set up
An Owner configures Claude's connections, plugins, and skills, and they apply per scope. They are separate from the connectors, skills, or MCP servers an individual user has set up
+1 −1 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/admins/connections/google
±changed
+1−1
claude-docschanged
claude-tag/admins/connections/google
This is an HTTP API connection, not a personal claude.ai connector. A member's own Google connector applies in DMs. With [personal connectors in channels](/docs/claude-tag/concepts
This is an HTTP API connection, not a personal claude.ai connector. A member's own Google connector applies in DMs. Claude can also [use it in a channel](/docs/claude-tag/concepts/
+1 −1 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/admins/connections/amplitude
±changed
+1−1
claude-docschanged
claude-tag/admins/connections/amplitude
For the API key route, pair the connection with a plugin that covers Amplitude so Claude knows how to call the REST API; see [Attach plugins](/docs/claude-tag/admins/add-connection
For the API key route, pair the connection with a plugin that covers Amplitude so Claude knows how to call the REST API; see [Attach plugins](/docs/claude-tag/admins/add-connection
+1 −1 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-docs
claude-tag/admins/add-connections
±changed
+1−1
claude-docschanged
claude-tag/admins/add-connections
Connections belong to the [agent identity](/docs/claude-tag/concepts/agent-identity), not to any person. Personal claude.ai connectors apply in DMs. With [personal connectors in ch
Connections belong to the [agent identity](/docs/claude-tag/concepts/agent-identity), not to any person. Personal claude.ai connectors apply in DMs. Claude can also [use a member's
+1 −1 lines
Upstream edited 26 Sep 2026 00:17 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
worktrees
±changed
+5−5
claude-codechanged
worktrees
| Message starts with | What happened and what to do
| :------------------------------------------------ | :-----------------------------------------------------------------------------------------------------------------------------
| `Your worktree <path> no longer exists` | The worktree directory was removed. The session continues in the current directory without isolation, and Claude Code clears t
| Message starts with | What happened and what to do |
| :- | :- |
+5 −5 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
sandbox-environments
±changed
+18−18
claude-codechanged
sandbox-environments
| Approach | What is isolated | Requires Docker | Setup effort
| :------------------------------------------ | :-------------------------------------------------------------------------- | :-------------- | :-----------------------------------
| [Sandboxed Bash tool](#sandboxed-bash-tool) | Bash, PowerShell, and Monitor commands and their child processes | No | Minimal on macOS; low on Linux and W
| [Sandbox runtime](#sandbox-runtime) | The whole Claude Code process, including file tools, MCP servers, and hooks | No | Low
| [Dev container](#dev-containers) | Full development environment | Yes | Medium
+18 −18 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
monitoring-usage
±changed
+190−190
claude-codechanged
monitoring-usage
| Environment Variable | Description
| --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------
| `CLAUDE_CODE_ENABLE_TELEMETRY` | Enables telemetry collection (required)
| `OTEL_METRICS_EXPORTER` | Metrics exporter types, comma-separated. Use `none` to disable
| `OTEL_LOGS_EXPORTER` | Logs/events exporter types, comma-separated. Use `none` to disable
+190 −190 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
github-enterprise-server
±changed
+28−28
claude-codechanged
github-enterprise-server
| Feature | GHES support | Notes |
| :------------------- | :-------------- | :----------------------------------------------------------------------------------------------------------------------------- |
| Cloud sessions | ?
| Code Review | ?
| Claude Security | ?
+28 −28 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
channels
±changed
+10−10
claude-codechanged
channels
| Setting | Purpose
| :---------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------
| `channelsEnabled` | Master switch. Must be `true` for any channel to deliver messages. Blocks all channels including the development flag when off. See [Enable channels for
| `allowedChannelPlugins` | Which plugins can register once channels are enabled. Replaces the Anthropic-maintained list when set.
| Setting | Purpose | When not configured |
+10 −10 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
worktrees
±changed
+3−3
claude-codechanged
worktrees
* **The worktree has work in it**: Claude prompts you to keep or remove the worktree. Keeping preserves the directory and branch so you can return later. Removing deletes the workt
* **The worktree has work in it**: Claude prompts you to keep or remove the worktree. Keeping preserves the directory and branch. To return later, run the `claude --worktree <name>
When you resume a session that was inside a worktree, Claude Code returns the session to that worktree. This holds for interactive resumes, for `--continue` and `--resume` in [non-
When you resume a session that ended inside a worktree without [exiting it](#clean-up-worktrees), Claude Code returns the session to that worktree. This holds for interactive resum
* **Launch directory**: resume from the main checkout or another directory of the repository. Claude Code re-enters a worktree it created with git under `.claude/worktrees/` even w
+3 −3 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
sandbox-environments
±changed
+1−1
claude-codechanged
sandbox-environments
mkdir -p ~/.claude && echo '{}' > ~/.claude.json
mkdir -p ~/.claude && { [ -f ~/.claude.json ] || echo '{}' > ~/.claude.json; }
+1 −1 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
monitoring-usage
±changed
+3−3
claude-codechanged
monitoring-usage
If nothing arrives, run `claude --debug` and check the debug log. Claude Code reports failures from the exporters you configure as `[3P telemetry]` errors, where 3P means third-par
If nothing arrives, start Claude Code with `claude --debug-file <path>` and check the log it writes to that path. Claude Code reports failures from the exporters you configure as `
When you set an `OTEL_EXPORTER_OTLP_*` variable in managed settings, Claude Code removes conflicting developer-set variables at startup and logs a warning you can see with `claude
When you set an `OTEL_EXPORTER_OTLP_*` variable in managed settings, Claude Code removes conflicting developer-set variables at startup and logs a warning in the debug log. What it
To confirm events arrive, submit a prompt in a session running under this configuration and check your SIEM for the `claude_code.user_prompt` event. If nothing arrives, run `claude
+3 −3 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
llm-gateway-connect
±changed
+1−1
claude-codechanged
llm-gateway-connect
curl -X POST "$ANTHROPIC_BASE_URL/v1/messages" \
curl -sS -w '\n%{http_code}\n' -X POST "$ANTHROPIC_BASE_URL/v1/messages" \
+1 −1 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
In addition to the [common input fields](#common-input-fields), Stop hooks receive `stop_hook_active`, `last_assistant_message`, `background_tasks`, and `session_crons`. The `stop_
In addition to the [common input fields](#common-input-fields), Stop hooks receive `stop_hook_active`, `last_assistant_message`, `background_tasks`, and `session_crons`. The `stop_
+1 −1 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
github-enterprise-server
±changed
+1−1
claude-codechanged
github-enterprise-server
Cloud sessions require a Team or Enterprise organization. Sign in with `/login` using your organization account. If you authenticate with an API key instead, cloud sessions fail ea
Sign in with `/login` using your organization account. If you authenticate with an API key instead, cloud sessions fail earlier with a message asking you to run `/login`.
+1 −1 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
channels
±changed
+1−1
claude-codechanged
channels
To test a channel you're building, use `--dangerously-load-development-channels`. See [Test during the research preview](/docs/en/channels-reference#test-during-the-research-previe
To test a channel you're building, pass it to `--dangerously-load-development-channels` in the `plugin:<name>@<marketplace>` or `server:<name>` form. See [Test during the research
+1 −1 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
* **As a deterministic gate**: a [Stop hook](/docs/en/hooks#stop) runs your check as a script and blocks the turn from ending until it passes. Claude Code overrides the hook and en
* **As a deterministic gate**: a [Stop hook](/docs/en/hooks#stop) runs your check as a script and blocks the turn from ending until it passes. [Stop input](/docs/en/hooks#stop-inpu
+1 −1 lines
Upstream edited 26 Sep 2026 00:15 UTC Recorded here 26 Sep 2026 00:37 UTC
claude-code
settings-reference
±changed
+51−4
claude-codechanged
settings-reference
| [`availableModelsMatch`](#availablemodelsmatch) | Make each `availableModels` model ID entry [permit only the version it nam
| [`deniedModels`](#deniedmodels) | [Block specific models](/docs/en/model-config#block-specific-models-or-ver
Restrict which models people can select for the main session, [subagents](/docs/en/sub-agents), [skills](/docs/en/skills), and the [advisor](/docs/en/advisor). A managed list const
Restrict which models people can select for the main session, [subagents](/docs/en/sub-agents), [skills](/docs/en/skills), and the [advisor](/docs/en/advisor). A managed list const
See [Restrict model selection](/docs/en/model-config#restrict-model-selection).
+51 −4 lines
Upstream edited 26 Sep 2026 00:04 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-code
model-config
±changed
+40−8
claude-codechanged
model-config
* [`availableModels`](#restrict-model-selection) or [organization model restrictions](#organization-model-restrictions) exclude the model
* Your organization's [model restrictions](#restrict-model-selection) exclude the model
Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/managed-settings) to restrict which models users can select. Entries match a model fami
Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/managed-settings) to restrict which models users can select. Entries match a model fami
On its own, `availableModels` leaves the Default option on the system's [runtime default](#default-model-setting) for the account until you also set [`enforceAvailableModels`](#enf
+40 −8 lines
Upstream edited 26 Sep 2026 00:04 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-code
managed-settings
±changed
+25−23
claude-codechanged
managed-settings
| Lists | Combines the entries from every source
| Locks | Applies the strictest value any source sets; a looser value applies only from the highest-ranked source
| Lists | Combines the entries from every source
| Locks | Applies the strictest value any source sets; a looser value applies only from the highest-ranked source
| Field | Behavior when present but invalid
+25 −23 lines
Upstream edited 26 Sep 2026 00:04 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-code
errors
±changed
+28−2
claude-codechanged
errors
| `Model ... is not available. Your organization restricts model selection.`
| `Claude Code can't start: your organization's managed settings block the default model` / `Claude Code can't start: your organization allows only the models listed in "availableM
* Check whether `ANTHROPIC_BASE_URL` is set by running `echo $ANTHROPIC_BASE_URL`, or `echo $env:ANTHROPIC_BASE_URL` in PowerShell, and look for it in the `env` block of your [sett
Your organization admin has disabled this model in the claude.ai admin console, or it is excluded by an [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlis
Your organization admin has disabled this model in the claude.ai admin console, or managed settings exclude it through an [`availableModels`](/docs/en/model-config#restrict-model-s
+28 −2 lines
Upstream edited 26 Sep 2026 00:04 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-code
agent-sdk/typescript
±changed
+37−18
claude-codechanged
agent-sdk/typescript
| Value | What stopped the session
| :------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------
| `org_pin_api_key_conflict` | Managed settings [require a first-party or Cloud gateway sign-in](/docs/en/authentication#restrict-login-to-your-organization), and an An
| `org_verify_failed` | The sign-in's organization couldn't be verified against the pin, for example because of a network failure or a revoked token
| `org_pin_mismatch` | The sign-in belongs to an organization the pin doesn't allow
+37 −18 lines
Upstream edited 26 Sep 2026 00:04 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
plugins/submit
±changed
+19−19
claude-docschanged
plugins/submit
To list a plugin in [Anthropic's directory](/docs/directory/publish.md), you submit it from a GitHub repository through the developer portal at [claude.ai/directory/manage](https:/
To list a plugin in [Anthropic's directory](https://claude.com/docs/directory/publish.md), you submit it from a GitHub repository through the developer portal at [claude.ai/directo
Use this page if your plugin is already in a GitHub repository and you want it listed. If the plugin references a remote MCP server you run, submit that server as an MCP connector
Use this page if your plugin is already in a GitHub repository and you want it listed. If the plugin references a remote MCP server you run, submit that server as an MCP connector
> * To build the plugin first, see [Plugin structure and testing](/docs/plugins/build.md)
+19 −19 lines
Upstream edited 26 Sep 2026 00:02 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
plugins/submit
±changed
+19−19
claude-docschanged
plugins/submit
To list a plugin in [Anthropic's directory](/docs/directory/publish), you submit it from a GitHub repository through the developer portal at [claude.ai/directory/manage](https://cl
To list a plugin in [Anthropic's directory](/docs/directory/publish.md), you submit it from a GitHub repository through the developer portal at [claude.ai/directory/manage](https:/
Use this page if your plugin is already in a GitHub repository and you want it listed. If the plugin references a remote MCP server you run, submit that server as an MCP connector
Use this page if your plugin is already in a GitHub repository and you want it listed. If the plugin references a remote MCP server you run, submit that server as an MCP connector
> * To build the plugin first, see [Plugin structure and testing](/docs/plugins/build)
+19 −19 lines
Upstream edited 26 Sep 2026 00:02 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
plugins/submit
±changed
+43−45
claude-docschanged
plugins/submit
<Note>
* To build the plugin first, see [Plugin structure and testing](/docs/plugins/build)
* To share it without a public listing, see [Share a plugin with teammates](/docs/plugins/share) or [Roll out a plugin to your whole organization](/docs/plugins/org-rollout)
* If you submitted through the earlier Claude Console form, see [Move an earlier submission to the developer portal](/docs/directory/publish#move-an-earlier-submission-to-the-dev
</Note>
+43 −45 lines
Upstream edited 26 Sep 2026 00:02 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
directory/publish
±changed
+5−5
claude-docschanged
directory/publish
| | Plugin bundle | MCP connector |
| :------------------ | :------------------------------------------------------------------------------ | :------------------------------------------------------------------ |
| What it is | A plugin folder with skills, commands, agents, hooks, and MCP server references | One remote MCP server that people connect to reach your app or data |
| Where it comes from | A GitHub repository, which must be public before the listing goes live | The server's URL, with no repository needed |
| How it's listed | As a plugin with all of its components | As a connector people connect to from the directory |
+5 −5 lines
Upstream edited 26 Sep 2026 00:02 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
plugins/submit
±changed
+4−3
claude-docschanged
plugins/submit
If another organization has already submitted the same repository and folder, the portal refuses **Submit for review** with **Already submitted by another organization**. If your o
If another organization has already submitted the same repository and folder, the portal refuses **Submit for review** with **Already submitted by another organization**. If your o
* **The reviewer publishes only the first version**: you select **Publish** for the first version and a reviewer publishes it. Later versions that pass go live by themselves unless
* **The reviewer publishes only the first version**: you select **Publish** for the first version and a reviewer publishes it. Later versions that pass go live by themselves unless
* **You publish the first version**: an Anthropic reviewer can apply this setting when they approve the plugin. You select **Publish** for the first version and it goes live. Later
+4 −3 lines
Upstream edited 26 Sep 2026 00:02 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
directory/publish
±changed
+6−1
claude-docschanged
directory/publish
The earlier Claude Console form for plugin submissions is no longer supported. To move a submission you made through it, submit it again at [claude.ai/directory/manage](https://cla
The earlier Claude Console form for plugin submissions is no longer supported. To move a submission you made through it, open [**Plugin submissions**](https://platform.claude.com/p
* **A submission with a Withdraw button**: select **Withdraw**. Then submit the plugin again at [claude.ai/directory/manage](https://claude.ai/directory/manage) from a claude.ai ac
* **A submission with no Withdraw button**: email `[email protected]` to have it moved to the developer portal instead of starting a new submission there. If you already save
+6 −1 lines
Upstream edited 26 Sep 2026 00:02 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/set-spend-limit
±changed
+12−12
claude-docschanged
claude-tag/admins/set-spend-limit
| Work |
| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Channel work |
| Reading a channel, [deciding whether to reply](/docs/claude-tag/users/when-claude-responds#what-claude-does-with-a-channel-message), and short replies from what Claude already kn
| A DM with Claude |
+12 −12 lines
Upstream edited 26 Sep 2026 00:00 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/overview
±changed
+7−0
claude-docschanged
claude-tag/overview
### Who needs a Claude seat
Slack users don't each need a Claude seat to work with Claude in channels.
* **In channels**: by default, anyone in the paired Slack workspace can tag `@Claude` in a channel, and an Owner can [restrict who can use Claude](/docs/claude-tag/admins/restrict-
+7 −0 lines
Upstream edited 26 Sep 2026 00:00 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/set-spend-limit
±changed
+5−1
claude-docschanged
claude-tag/admins/set-spend-limit
> Claude Tag draws from your organization's usage balance, not individual seats. See whether you need to fund usage, how to set the spend limit, and what happens when it's reached.
> 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.
## How Claude Tag usage is billed
+5 −1 lines
Upstream edited 26 Sep 2026 00:00 UTC Recorded here 26 Sep 2026 00:07 UTC
25 Sep 2026
517 pages
+55087 −56673 lines
claude-docs
claude-tag/users/use-cases/watch-monitors
±changed
+5−5
claude-docschanged
claude-tag/users/use-cases/watch-monitors
Check that the channel has the connections below. Ask `@Claude what can you access from this channel?` to check; an admin can [add a connection](/docs/claude-tag/admins/add-connect
Check that the channel has the connections below. Ask `@Claude what can you access from this channel?` to check; an admin can [add a connection](https://claude.com/docs/claude-tag/
Name the output format in the schedule, like "one line per service" above, so every post reads the same way. To list or cancel scheduled work later, see [Manage standing work](/doc
Name the output format in the schedule, like "one line per service" above, so every post reads the same way. To list or cancel scheduled work later, see [Manage standing work](http
Open the channel's [**Configure** page](/docs/claude-tag/users/good-habits.md#configure-claude-for-a-channel). In the **Channel instructions** field, list the alerts your team alre
+5 −5 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-tag/users/use-cases/watch-monitors
±changed
+5−5
claude-docschanged
claude-tag/users/use-cases/watch-monitors
Check that the channel has the connections below. Ask `@Claude what can you access from this channel?` to check; an admin can [add a connection](/docs/claude-tag/admins/add-connect
Check that the channel has the connections below. Ask `@Claude what can you access from this channel?` to check; an admin can [add a connection](/docs/claude-tag/admins/add-connect
Name the output format in the schedule, like "one line per service" above, so every post reads the same way. To list or cancel scheduled work later, see [Manage standing work](/doc
Name the output format in the schedule, like "one line per service" above, so every post reads the same way. To list or cancel scheduled work later, see [Manage standing work](/doc
Open the channel's [**Configure** page](/docs/claude-tag/users/good-habits#configure-claude-for-a-channel). In the **Channel instructions** field, list the alerts your team already
+5 −5 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-tag/users/use-cases/watch-monitors
±changed
+15−17
claude-docschanged
claude-tag/users/use-cases/watch-monitors
export const BetaNote = () => <Info>Claude Tag is in public beta. Features and behavior described here may change before general availability.</Info>;
<BetaNote />
> [!NOTE]
>
+15 −17 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-tag/users/use-cases/watch-monitors
±changed
+2−2
claude-docschanged
claude-tag/users/use-cases/watch-monitors
| Connection | Examples | Why it matters here |
| :--------- | :------------------------- | :----------------------------------------- |
| Connection | Examples | Why it matters here |
| :- | :- | :- |
+2 −2 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/memory
±changed
+4−4
claude-docschanged
claude-tag/users/memory
| Where Claude is working | Reads from | Saves to
| :---------------------- | :--------------------------------------------------------- | :------------------------------------------------------------------------------------------
| Public channel | That channel's notes and the workspace notes | That channel's notes, or the workspace notes for something that applies across the workspac
| Private channel | That channel's notes, plus the workspace notes (read-only) | That channel's notes only
| Where Claude is working | Reads from | Saves to |
+4 −4 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/concepts/data-lifecycle
±changed
+37−37
claude-docschanged
claude-tag/concepts/data-lifecycle
| What | What it contains
| :-------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------
| Session transcripts | The record of one thread's, channel's, or direct message's work. A transcript holds the messages Claude was shown in the conversation and who
| Memory | The notes Claude saves for each channel, the workspace notes it saves from public channels, and separate notes for each direct-message convers
| Routines | The scheduled and run-once tasks set up in channels or in direct messages, with their instructions and run history
+37 −37 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/migrate-from-earlier
±changed
+7−7
claude-docschanged
claude-tag/admins/migrate-from-earlier
| | Legacy (the earlier Claude in Slack) | New (Claude Tag) |
| :------------- | :------------------------------------------ | :------------------------------------------------------------------- |
| Identity | Each user links their own claude.ai account | One agent identity with org-level service credentials |
| Sessions | Spawned per request | One persistent session per thread, shared with the channel |
| Memory | None | Per-channel memory, plus workspace notes shared from public channels |
+7 −7 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/federated-access/gcp
±changed
+8−8
claude-docschanged
claude-tag/admins/federated-access/gcp
| Value | What it is
| :------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------
| Issuer | `https://identity.anthropic.com/agents`. The issuer URL of the provider you create in the pool.
| Value | What it is |
| :- | :- |
+8 −8 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/federated-access/connect-a-gateway
±changed
+9−9
claude-docschanged
claude-tag/admins/federated-access/connect-a-gateway
| Value | What to configure
| :-------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------
| Issuer | `https://identity.anthropic.com/agents`, matched exactly. The OIDC discovery document is at `https://identity.anthropic.com/agents/.well-known/openid-configurat
| Signing keys | The JSON Web Key Set (JWKS) named by `jwks_uri` in the discovery document, `https://identity.anthropic.com/agents/jwks.json`. Accept ES256 only. On an unknown k
| Audience | Your gateway address as the console stores it (the console converts the host to lowercase), for example `https://gateway.example.com`. The `aud` claim is a JSON
+9 −9 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/federated-access/aws
±changed
+4−4
claude-docschanged
claude-tag/admins/federated-access/aws
| Value | What it is
| :------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------
| Issuer | `https://identity.anthropic.com/agents`. The URL of the identity provider you create in AWS, including the `/agents` path.
| Audience | `sts.amazonaws.com`. The same for every organization, so it can't identify yours.
| Value | What it is |
+4 −4 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/federated-access/authorization-server
±changed
+8−8
claude-docschanged
claude-tag/admins/federated-access/authorization-server
| Value | What to configure
| :------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------
| Issuer | `https://identity.anthropic.com/agents`, matched exactly. The OpenID Connect (OIDC) discovery document is at `https://identity.anthropic.com/agents/.well-known/o
| JWKS URL | The JSON Web Key Set (JWKS) named by `jwks_uri` in the discovery document, `https://identity.anthropic.com/agents/jwks.json`. Accept ES256 only. Select the key b
| Audience | Your authorization server's issuer identifier, as you enter it in the **Issuer URL** field when you connect the server, for example `https://auth.example.com`. I
+8 −8 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/connections/gitlab
±changed
+10−10
claude-docschanged
claude-tag/admins/connections/gitlab
| Field | Value |
| :----------------------------- | :--------------------------------------------------------------------------------------------------------------- |
| Claude’s personal access token | The token from GitLab, starting with `glpat-`. Project and group access tokens work here too. |
| Allowed websites | `gitlab.com` (preset). For self-managed GitLab, open the **Advanced** tab and add your instance's hostname here. |
| Field | Value |
+10 −10 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/configure-gitlab
±changed
+3−3
claude-docschanged
claude-tag/admins/configure-gitlab
| Scope | When to grant it |
| :--------- | :------------------------------------------------------------------------------------------------------ |
| `api` | Read and write. Required for Claude to create and update issues, post comments, and act on pipelines. |
| Scope | When to grant it |
| :- | :- |
+3 −3 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/admins/attach-to-scope
±changed
+19−19
claude-docschanged
claude-tag/admins/attach-to-scope
| Scope | What it covers | Access |
| :------------------- | :---------------------------------------- | :---------------------------------------------------------------------- |
| Default Slack access | Every Slack workspace and channel | The baseline set every channel gets |
| Workspace | All channels in one Slack workspace | Inherits Default Slack access, plus workspace-level bundles |
| Channel | A single Slack channel, public or private | Inherits Default Slack access and workspace, plus channel-level bundles |
+19 −19 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
claude-tag/users/when-claude-responds
±changed
+4−2
claude-docschanged
claude-tag/users/when-claude-responds
When the scope's [**Channel member edits**](/docs/claude-tag/admins/attach-to-scope#restrict-who-can-set-channel-instructions) setting is **Block**, Claude declines to change **Res
Claude confirms the change, which is channel-wide, not just for you. You can make the same change with the toggle on the channel's Configure page, and an admin can make it from the
Claude confirms the change, which is channel-wide, not just for you. You can make the same change with the toggle on the channel's Configure page, and an admin can make it from the
If unprompted replies don't come back after Claude answers a mention, the channel's [**Respond automatically**](#turn-automatic-replies-on-or-off) setting is off. Answering a menti
+4 −2 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/users/use-cases/watch-monitors
±changed
+4−0
claude-docschanged
claude-tag/users/use-cases/watch-monitors
## Keep known false alarms out of Claude's checks
Open the channel's [**Configure** page](/docs/claude-tag/users/good-habits#configure-claude-for-a-channel). In the **Channel instructions** field, list the alerts your team already
+4 −0 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/users/troubleshooting
±changed
+1−1
claude-docschanged
claude-tag/users/troubleshooting
Claude has already read the original. An edit reaches it as a new update in the thread, so it may or may not act on the change, and it never undoes work already in progress. A dele
Claude has already read the original. An edit reaches it as a new update in the thread, so it may or may not act on the change, and it never undoes work already in progress. A dele
+1 −1 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/users/models
±changed
+1−1
claude-docschanged
claude-tag/users/models
Anthropic manages the list of models on offer, and your organization's settings narrow it. The options include Opus and Sonnet models, drawn from what's available to your organizat
Anthropic manages the list of models on offer, and your organization's settings narrow it. The options include Opus and Sonnet models, drawn from the models your organization allow
+1 −1 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/users/memory
±changed
+1−1
claude-docschanged
claude-tag/users/memory
* **You tell Claude.** Say "remember for this channel: reports go out as tables" and it saves the instruction.
* **You tell Claude.** Say "remember for this channel: reports go out as tables" and it saves the instruction. To save details from a document, [attach the file](/docs/claude-tag/u
+1 −1 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/users/getting-started
±changed
+9−9
claude-docschanged
claude-tag/users/getting-started
| What you give Claude | Can Claude read it?
| :---------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------
| Messages in this thread | Yes. Mentioning it mid-thread also gives it the thread's earlier messages
| A file you attach (image, screenshot, PDF, or another type) | Yes, up to a size limit that depends on the file type. See [Files you attach](#files-you-attach)
| Other public channels in your workspace | By searching only, the same way a person searches Slack; Claude can find a message by keyword but can't read a chann
+9 −9 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/users/commands
±changed
+1−1
claude-docschanged
claude-tag/users/commands
* **At a channel's top level**, `!restart` replaces the channel's session. The fresh session picks up from where the old one left off.
* **At a channel's top level**, `!restart` replaces the channel's session. The fresh session picks up from where the old one left off. In a channel without a session of its own, Cl
+1 −1 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+2−0
claude-docschanged
claude-tag/concepts/security-and-data
While a Slack guest is in a channel set to [**Channel only**](/docs/claude-tag/admins/restrict-access#how-channel-only-works), Claude doesn't publish artifacts there.
+2 −0 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+11−2
claude-docschanged
claude-tag/concepts/how-it-works
* **Deleting the thread's first message**: if the thread already has replies, Claude keeps working and the session stays open. If you delete it before anyone has replied, the sessi
* **Deleting the thread's first message**: Claude stops working in that thread and the session closes, whether or not the thread has replies. Anything Claude already pushed or post
The channel's own session, the one that handles top-level messages outside any thread, lives longer than a thread's. Claude replaces it with a fresh one when a top-level message ar
The channel's own session, the one that handles top-level messages outside any thread, lives longer than a thread's. Claude replaces it with a fresh one after about an hour with no
+11 −2 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/concepts/glossary
±changed
+1−1
claude-docschanged
claude-tag/concepts/glossary
Your admin chooses which generation answers `@Claude` in a given channel, so two channels in the same workspace can work differently. See [Migrate from the earlier Claude in Slack]
Your admin chooses which generation answers `@Claude` in a given channel, so two channels in the same workspace can work differently. See [Migrate from the earlier Claude in Slack]
+1 −1 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/concepts/data-lifecycle
±changed
+17−17
claude-docschanged
claude-tag/concepts/data-lifecycle
Sessions Claude stops using are archived, not deleted. That includes a thread's session after someone sends [`@Claude !restart`](/docs/claude-tag/users/commands#restart-a-stuck-or-
Sessions Claude stops using are archived, not deleted. That includes a thread's session after someone sends [`@Claude !restart`](/docs/claude-tag/users/commands#restart-a-stuck-or-
| Someone deletes a reply, or deletes a thread's first message after others have replied | Nothing is removed from the transcript, and Clau
| Someone deletes a thread's first message before anyone has replied | The session closes and is archived with its tran
| Someone deletes a reply in a thread | Nothing is removed from the transcript, and Clau
+17 −17 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/workspaces
±changed
+15−12
claude-docschanged
claude-tag/admins/workspaces
<Note>If your organization used the earlier Claude in Slack app, the dialog header reads **Switch to Claude Tag** instead of **Set up Claude Tag for your workspace**. The steps are
<Note>If your organization used the earlier Claude in Slack app, the new workspace is added alongside your existing one, not in place of it.</Note>
## Set the version for a scope
## Turn Claude Tag on or off and set the version for a scope
Every scope routes to one of four versions. On the Team plan, a single [**Enable Claude Tag** switch](#turn-claude-tag-on-or-off-on-the-team-plan) replaces the control this section
+15 −12 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+7−8
claude-docschanged
claude-tag/admins/troubleshooting
| Claude to respond in Slack | "Claude Tag is unavailable because Routines aren't enabled for your organ
| Claude to respond in Slack | "Claude Tag is unavailable because Routines aren't enabled for your organ
Nothing is misconfigured. If an auto-join pattern brought Claude in, review the patterns in the scope's **Advanced** section. If Claude shouldn't be in the channel, remove it with
Nothing is misconfigured. If an auto-join pattern brought Claude in, review the patterns in the scope's **Advanced** section. If Claude shouldn't be in the channel, remove it with
An admin enables Routines from the Claude Code page in admin settings, at [`claude.ai/admin-settings/claude-code`](https://claude.ai/admin-settings/claude-code). Once Routines is e
+7 −8 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+1−1
claude-docschanged
claude-tag/admins/setup-overview
| **Routines** enabled for your Claude organization | Until it is, Claude answers every mention and DM with a reply that it's unav
| **Routines** enabled for your Claude organization | Until it is, Claude answers every mention and DM with a reply that it's unav
+1 −1 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+33−30
claude-docschanged
claude-tag/admins/restrict-access
3. **Set the scope's Claude Tag version to Off.** Claude stops responding in that scope even if someone invites it back; an @-mention gets a disabled notice instead of a reply. Onl
4. **Remove the channel's scope.** Choose **Remove this scope** from the scope's options menu. Claude keeps answering in the channel with the access it inherits from its workspace,
3. **Turn the scope's Enable Claude Tag switch off.** Claude stops responding in that scope even if someone invites it back; an @-mention gets a disabled notice instead of a reply.
4. **Remove the channel's scope.** Choose **Remove this scope** from the scope's options menu. Claude keeps answering in the channel with the access it inherits from its workspace,
To let Claude respond only in channels you choose, for example during a pilot confined to one channel, turn the [version setting](/docs/claude-tag/admins/workspaces#set-the-version
+33 −30 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
claude-docs
claude-tag/admins/migrate-from-earlier
±changed
+2−2
claude-docschanged
claude-tag/admins/migrate-from-earlier
The **Claude Tag version** setting on each scope chooses whether the New or Legacy version answers there, or neither. Access bundles only apply where the New version answers. See [
The **Claude Tag version** setting on each scope chooses whether the New or Legacy version answers there, and the scope's **Enable Claude Tag** switch turns both off. Access bundle
The earlier Claude in Slack and Claude Tag are two versions of the same `@Claude` Slack app, not two apps, so there is nothing to uninstall. You choose which version answers per sc
The earlier Claude in Slack and Claude Tag are two versions of the same `@Claude` Slack app, not two apps, so there is nothing to uninstall. You choose which version answers per sc
+2 −2 lines
Upstream edited 25 Sep 2026 23:59 UTC Recorded here 26 Sep 2026 00:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.