Docs search: kind / page 5 of 6 / Claude Code source intelligence

Orchestrate subagents at scale with dynamic workflows Claude Code CLI · in the page workflows …ut's [`origin`](/docs/en/agent-sdk/typescript#sdkmessageorigin) as `{ kind: "human" }`. It doesn't start a workflow when it reaches the session another way: * a prompt passed with `-p` * a prompt an…

Admin controls Claude Documentation · in the page claude-science/admin-controls …cience/update-claude-science.md) has the member's next steps for each kind of install; projects and settings on the computer are kept. Each member's app also has to reach claude.ai regularly to confi…

Core concepts Claude Documentation · in the page claude-science/core-concepts …mission card appears in the conversation each time Claude needs a new kind of access. The card names exactly what's being requested. You can allow or deny each one. | Action | Card title | Scope opti…

Use Claude Science on a corporate network Claude Documentation · in the page claude-science/corporate-networks …cience/network-requirements.md) it needs. Claude Science makes three kinds of outbound connections, each passing through a different part of your network policy: * The app's own connections (sign-in…

Claude Science in its own window on macOS Claude Documentation · in the page claude-science/mac-app-window …on again, go to **System Settings > Privacy & Security**, choose the kind of access, and turn on the **Claude Science** toggle. If **Claude Science** isn't listed, click the add button (+) and choose…

Configure per-channel access Claude Documentation · in the page claude-tag/admins/attach-to-scope …*, **Repository**, **Plugin**, or **Skill**. The dialog opens on that kind's tab, and its **Connectors**, **Plugins**, **Skills**, and **Repositories** tabs switch between kinds. To let Claude reach a…

Attribute costs to users Claude Documentation · in the page claude-tag/admins/attribute-costs …ai/analytics/claude-tag) in claude.ai you see spend by channel and by kind of work, not by user. For spend by user, use the cost report. ## Get spend per user Call the cost report with `claude_tag_u…

Connect a Google Cloud identity Claude Documentation · in the page claude-tag/admins/federated-access/gcp …ntents of /tmp/resp.txt. ``` A status of 200 with a JSON body whose `kind` is `storage#bucket` means the token exchange and the API call both worked. For log evidence, enable Data Access audit logs b…

Troubleshoot federated agent access Claude Documentation · in the page claude-tag/admins/federated-access/troubleshooting …because Claude was reusing credentials from an earlier sign-in. Other kinds of request with the same connection may still work. The failure repeats for one kind of request, for example every call to o…

Manage a channel's instructions from another channel Claude Documentation · in the page claude-tag/admins/managed-by …tructions for #it-help with this text: ... ``` Claude posts the same kind of card, and the file exists once someone confirms it. Deleting works the same way. Ask Claude to delete the managed channel'…

Restrict where Claude Tag operates Claude Documentation · in the page claude-tag/admins/restrict-access …pend by channel with a CSV export, DM versus channel spend, [spend by kind of work](/docs/claude-tag/admins/set-spend-limit.md#see-spend-by-kind-of-work), and any promotional credit. Billed figures ar…

Set a spend limit Claude Documentation · in the page claude-tag/admins/set-spend-limit …count) can bill to the organization's usage balance. ## See spend by kind of work On the analytics page at [`claude.ai/analytics/claude-tag`](https://claude.ai/analytics/claude-tag), you see channel…

Glossary Claude Documentation · in the page claude-tag/concepts/glossary ….md#add-a-domain), plugins, and instructions that Claude uses for one kind of work, such as support triage. An Owner or a [Claude Tag admin](#claude-tag-admin) creates bundles on the **Bundles** tab u…

Claude Tag settings map Claude Documentation · in the page claude-tag/concepts/settings-map …live on claude.ai, split across a few pages that each own a different kind of setting. Which page you need depends on what you're changing. The table maps each surface to what it controls. | Surface…

Good habits for working with Claude Tag Claude Documentation · in the page claude-tag/users/good-habits …write determines who can close the thread, and the table matches each kind of condition to who closes it. | End condition | Who closes it | Example | | :- | :- | :- | | An objective check passes | Cl…

What Claude Tag remembers Claude Documentation · in the page claude-tag/users/memory …imeframe or topic. ## Channel and workspace memory Claude keeps two kinds of notes in a workspace. Channel notes hold what applies to one channel, such as its conventions, who owns what, and decisio…

Troubleshoot Claude Tag in channels and DMs Claude Documentation · in the page claude-tag/users/troubleshooting …is on by default. In a channel where someone has [told Claude which kinds of untagged messages to answer](/docs/claude-tag/users/when-claude-responds.md#what-claude-does-with-a-channel-message), it…

Control when Claude Tag responds Claude Documentation · in the page claude-tag/users/when-claude-responds …le channel](#turn-automatic-replies-on-or-off), or [tell Claude which kinds of untagged messages to answer](#what-claude-does-with-a-channel-message). ## What Claude does with a channel message Clau…

Enterprise Managed Auth for connectors Claude Documentation · in the page connectors/building/enterprise-managed-auth …r redirect or a consent screen, and your MCP server receives the same kind of bearer token it would after the interactive OAuth flow. The diagram shows the exchange between Claude, your authorization…

Build an MCP server for Claude Claude Documentation · in the page connectors/building/index …s to it from every Claude app, and a remote server is the recommended kind for a directory listing. A local server runs on the user's computer. To package one for the Claude desktop app, see [Build a…

Get started with connectors Claude Documentation · in the page connectors/getting-started …work Connectors work across the Claude apps. Each app supports these kinds: * **claude.ai on the web**: remote connectors, including MCP Apps that display interactive content in the conversation * *…

Changelog Claude Documentation · in the page cowork/changelog …ckslashes, when a value mixes quotes and backslashes or contains both kinds of quote. **Cowork** * Changed MCP tools that their server marks as needing a person to ask only on the in-app card, so th…

Publish to the directory Claude Documentation · in the page directory/publish …plugin or MCP connector to Anthropic's directory: the two submission kinds, who can submit, what review involves, and where to start. The [directory](https://claude.ai/directory) is Anthropic's cata…

Track your directory submission Claude Documentation · in the page directory/submission-status …ory/publish.md). Find your status in the table for your submission's kind: [plugin bundle](#plugin-bundle-statuses) or [MCP connector](#mcp-connector-statuses). If nothing is waiting on you and you s…

Sessions Claude Documentation · in the page government/account/sessions …are ordered with the most recent first. * **Client** tells you which kind of application the sign-in is for. * **via …** tells you how that session was established. **Single sign-on** means you authe…

How Config works Claude Documentation · in the page government/config/overview …nant view) which organizations have set their own value. ### Setting kinds Settings combine across the chain in one of three ways, and the kind is fixed per setting (you don't choose it): * A **sim…

Connect Claude Desktop to Claude for Government Claude Documentation · in the page government/deploy-desktop/configure …the app cannot sign in through such an alias. With any alias of this kind, the app still offers **Sign in with your organization**, but sign-in fails as soon as the user chooses it; see [Troubleshoot…

Analytics Claude Documentation · in the page government/org-admin/analytics …only in the **Self-managed** view. If your organization has only one kind of tier, the control does not appear and the page shows only the matching view. If all of your seat tiers are Anthropic-manag…

Organization administration Claude Documentation · in the page government/org-admin/overview …s they can use and how much they can use them. Seat tiers come in two kinds: * **Anthropic-managed tiers** that are supplied to you as a fixed number of seats. * **Self-managed tiers** that your orga…

Seats Claude Documentation · in the page government/org-admin/seats …low only appears when your organization has at least one tier of that kind. If you have neither, the page shows a message explaining that seats are distributed by your tenant administrators. **Anthro…

Identity and access Claude Documentation · in the page government/tenant-admin/identity-and-access …ple who have arrived but aren't in an organization yet. There are two kinds of entry: * **Rejected sign-ins** are people from one of your verified domains who tried to sign in but matched no rule and…

Data storage and retention Claude Documentation · in the page office-agents/data-storage …retention The table below shows how long Claude for M365 keeps each kind of local data. Users can also delete their saved conversations at any time, as described after the table. | Store | Retentio…

Create a plugin with Claude Claude Documentation · in the page plugins/create-with-claude …equest** Start a chat, or a Cowork task in the desktop app, with the kind of request the plugin is for, and check that Claude follows the plugin's skills. ## Use, disable, or remove your plugin The…

Plugins Claude Documentation · in the page plugins/overview …ains, open it from **Customize > Plugins**, where its page lists each kind on its own tab. You can run a plugin's skill or command in chat, Cowork, and Claude Code: * **Chat in claude.ai or the desk…

Submit your plugin Claude Documentation · in the page plugins/submit …cklist](/docs/plugins/pre-submission-checklist.md) explains what each kind of finding means. A validation result applies to one commit. If you push to the branch after validating, validate again befo…

Create custom skills Claude Documentation · in the page skills/how-to …skill folder This example skill, `brand-guidelines`, has one of each kind of file a skill can carry. Select a file to read what it's for and see a minimal example. Skill folder brand-guidelines/ S…

Deploy with Enterprise Admin Console Claude Documentation · in the page third-party/claude-desktop/admin-console …n wherever your provider offers one. It is the recommended credential kind for a deployment managed from the console. Users sign in inside the app with their own accounts, and there is no shared crede…

Deploy Claude Desktop on 3P with Amazon Bedrock Claude Documentation · in the page third-party/claude-desktop/bedrock …al helper, bearer token. To remove ambiguity, set `inferenceCredentialKind` explicitly (see the [Configuration reference](/docs/third-party/claude-desktop/configuration.md#inferencecredentialkind)).…

Deploy with a bootstrap server Claude Documentation · in the page third-party/claude-desktop/bootstrap …ewayBaseUrl` shares the `bootstrapUrl` origin and `inferenceCredentialKind` is `interactive`, so the user signs in once for both. **1. Publish RFC 8414 discovery metadata** Serve a metadata document…

Code in Claude Desktop on 3P Claude Documentation · in the page third-party/claude-desktop/code …ird-party/claude-desktop/ssh-remote-sessions.md) lists the credential kinds that work on a remote host and which of the keys above apply there. ## Further reading * [Claude Code settings reference](…

Configuration reference Claude Documentation · in the page third-party/claude-desktop/configuration …l, and a session host's route is its operator's to set | | Credential kind `inferenceCredentialKind` | `enum` | MDM + Bootstrap Added in 1.8555.0 | — | Selects the credential source. When set, only th…

Configuration changelog Claude Documentation · in the page third-party/claude-desktop/configuration-changelog …ing): * `inferenceGatewayAuthScheme: "sso"`: use `inferenceCredentialKind: "interactive"` instead. If `inferenceCredentialKind` is not set, this release and later keep reading the original spelling a…

User identity and local data Claude Documentation · in the page third-party/claude-desktop/data-storage …etentiondays) to a number of days from 1 to 3650. Each key covers one kind of session, and a kind you leave unset is kept until the user deletes it. Idle time counts from the session's last activity,…

MCP, plugins, skills, and hooks Claude Documentation · in the page third-party/claude-desktop/extensions …ktop syncs the marketplace, it doesn't fetch a plugin with a `source` kind other than `archive`, or with an archive on a different origin. That plugin doesn't appear in the [**Organization** tab](#plu…

Deploy Claude Desktop on 3P with Microsoft Foundry Claude Documentation · in the page third-party/claude-desktop/foundry …page. When the tenant and client IDs are set and `inferenceCredentialKind` is `interactive`, the app shows a **Sign in with Microsoft** page at first launch. Clicking the button starts a sign-in agai…

Deploy Claude Desktop on 3P with an LLM gateway Claude Documentation · in the page third-party/claude-desktop/gateway …* section, set **Inference provider** to **Gateway** and **Credential kind** to **Interactive sign-in**. This hides the API-key field and reveals **Gateway SSO IdP (OIDC)**: | Field | Value | | - | -…

Network proxy Claude Documentation · in the page third-party/claude-desktop/network-proxy …at is and is not routed The table summarizes which proxy source each kind of traffic follows. "App proxy" means the pinned key if one is set, otherwise the OS settings, with PAC rules applied per req…

SSH remote sessions in Claude Desktop on 3P Claude Documentation · in the page third-party/claude-desktop/ssh-remote-sessions …ives the failure as the call's result, and a further call of the same kind waits again, which delays the `Stop` hook. For a task that makes these calls, have the user keep the device awake and connect…