One read of Claude Documentationclaude-docs-20261104T200715Z
5 pages moved out of 281 read.
Pages moved
5
significant first
Pages read
281
in this capture
Captured
20:07 UTC
Corpus hash
2e12bd20c860
corpus-hash
What this read moved
1-5 of 5plugins/admin Changed · +3 / -9 lines
from line 38
3838
3939### Policy
4040
41The [**Policy**](https://claude.ai/admin-settings/skills?tab=policy) tab holds the switches for what members can do themselves: [create and add their own](#control-what-members-add-themselves), [share with each other](#let-members-share-plugins-with-each-other), and [publish to the organization](#review-plugins-that-members-publish). It also holds the **Skills and plugins scanning** switch, which turns on the security scan whose result the **Inventory** tab shows, and the switch that [turns plugins and skills off for everyone](#turn-plugins-and-skills-off-for-everyone).
41The [**Policy**](https://claude.ai/admin-settings/skills?tab=policy) tab holds the switches for what members can do themselves: [create and add their own](#control-what-members-add-themselves), [share with each other](#let-members-share-plugins-with-each-other), and [publish to the organization](#review-plugins-that-members-publish). It also holds the **Skill and plugin security scanning** switch, which turns on the security scan whose result the **Inventory** tab shows, and the switch that [turns plugins and skills off for everyone](#turn-plugins-and-skills-off-for-everyone).
4242
4343## Review your organization's inventory
4444
from line 48
4848
4949* **Name**: the item's name, marked **Skill** or **Plugin**
5050* **Source**: the marketplace or repository the item comes from, or **Member** for an item a member created
51* **Security scan**: the result of the item's security scan. You see this column when **Skills and plugins scanning** is on in the [**Policy**](https://claude.ai/admin-settings/skills?tab=policy) tab. Otherwise the column is **Version**
51* **Security scan**: the result of the item's security scan. You see this column when **Skill and plugin security scanning** is on in the [**Policy**](https://claude.ai/admin-settings/skills?tab=policy) tab. Otherwise the column is **Version**.
5252* **Capabilities**: the connectors and tools the item uses
5353* **Audience**: who can use the item, such as everyone or specific groups
5454* **Users (30d)**: how many people in your organization used the item in the last 30 days
from line 259
259259If nobody in your organization has chosen a **Publishing** value, your plan's default applies:
260260
261261* **Team**: **Open**
262* **Enterprise**: **Requires review**
263
264> [!NOTE]
265>
266> Starting November 4, 2026, the Enterprise default changes to **Open** for organizations that have security scanning on. Published skills and plugins are then listed in the organization's library once they pass the automatic security scan, without waiting for admin approval. Members whose custom role doesn't allow publishing to the whole organization still need review.
267>
268> To keep reviewing every submission, select **Requires review** before then. Your choice is saved when the label beside the setting changes from **Default** to **Set by admin**. Organizations that already chose a setting keep it.
262* **Enterprise**: **Open** if your organization has [security scanning](#policy) on, and **Requires review** otherwise. Where **Open** is the default, members whose custom role doesn't allow publishing to the whole organization still need review.
269263
270264#### Review a request
271265
third-party/claude-desktop/network-proxy Changed · +4 / -3 lines
from line 6
66
77Three parts of the product make network connections, and they do not all resolve the proxy the same way:
88
9* **The app**: the Claude Desktop window itself, including sign-in, the connection test, Web Fetch in Chat and Cowork sessions, managed MCP servers the app connects to, and sync of the plugin marketplaces you configure.
9* **The app**: the Claude Desktop window itself, including sign-in, the connection test, Web Fetch in Chat and Cowork sessions, remote managed MCP servers, and sync of the plugin marketplaces you configure.
1010* **The agent**: the Claude Code engine the app runs for every Chat, Cowork, and Code session. It sends inference requests and makes its own remote MCP connections, for example to [a server that a marketplace plugin or a user-added plugin bundles](https://claude.com/docs/third-party/claude-desktop/extensions.md#remote-mcp-servers-in-plugins). In Code sessions, it also makes its own web fetches and plugin installs.
1111* **Cowork's sandboxed shell**: the isolated environment where commands the agent runs in a Cowork session (`curl`, `pip`, `npm`, and so on) execute.
1212
from line 78
7878| - | - |
7979| App window, in-app sign-in, connection test, model list | App proxy |
8080| Inference requests from Chat, Cowork, and Code sessions | The single proxy resolved for the inference endpoint (from the pinned key or the OS), or Claude Code managed settings if deployed |
81| Agent web fetch, remote MCP servers, and plugin installs in Code sessions | Same single proxy as inference |
81| Agent web fetch, plugin installs, and the agent's own remote MCP connections in Code sessions | Same single proxy as inference |
8282| The agent's remote MCP connections in Chat and Cowork sessions, to servers that a marketplace plugin or a user-added plugin bundles | Same single proxy as inference |
83| Web Fetch and managed MCP servers in Chat and Cowork sessions | App proxy (the app makes these connections) |
83| Web Fetch in Chat and Cowork sessions, and remote managed MCP servers | App proxy (the app makes these connections) |
84| Local (`stdio`) servers in [`managedMcpServers`](https://claude.com/docs/third-party/claude-desktop/configuration#managedmcpservers) | The app gives the server no proxy variables. Set `HTTPS_PROXY` in the entry's `env`, or have its `envHelper` script print it. In the admin console, use the **Environment helper script** field. |
8485| Sync of the plugin marketplaces you configure, and `aws` CLI calls the app makes for Bedrock sign-in | App proxy, resolved for the specific host |
8586| Cowork sandbox download from `downloads.claude.ai` | App proxy |
8687| Telemetry and crash reports to Anthropic, if enabled | App proxy |
claude-tag/admins/troubleshooting Changed · +1 / -1 lines
from line 735
735735
736736**What it means**
737737
738One-to-one DMs run on the user's own claude.ai account and need a qualifying seat, which this user doesn't have. A seat that includes Claude Code always qualifies; on the Enterprise plan, a **Standard** or **Usage-Based Chat** seat also qualifies when the user has Cowork. Mentioning `@Claude` in a channel doesn't depend on the sender's seat.
738One-to-one DMs run on the user's own claude.ai account and need a qualifying seat, which this user doesn't have. To qualify, the user needs either a seat that includes Claude Code or, on the Enterprise plan, Cowork access on a **Standard** seat or a usage-based **Chat** seat. Mentioning `@Claude` in a channel doesn't depend on the sender's seat.
739739
740740**How to resolve**
741741
claude-tag/overview Changed · +1 / -1 lines
from line 41
4141
4242* **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](https://claude.com/docs/claude-tag/admins/restrict-access.md#restrict-who-can-use-claude) to people in your Claude organization or, on Enterprise, to specific roles. Channel work bills by usage to your organization's usage balance, under a [spend limit](https://claude.com/docs/claude-tag/admins/set-spend-limit.md) an Owner sets.
4343* **In group DMs**: the same restriction on who can use Claude applies, and the work bills to your organization's usage balance. See [Group DMs](https://claude.com/docs/claude-tag/admins/restrict-access.md#group-dms).
44* **In one-to-one DMs**: a DM from a member who has connected a Claude account runs on that account and bills to that person's seat. The seat must include Claude Code, or, on the Enterprise plan, be a **Standard** or **Usage-Based Chat** seat held by someone who also has Cowork. A [DM from a member who hasn't connected a Claude account](https://claude.com/docs/claude-tag/admins/restrict-access.md#direct-messages-from-members-without-a-claude-account) can bill to your organization for a limited time.
44* **In one-to-one DMs**: a DM from a member who has connected a Claude account runs on that account and bills to that person's seat. For the DM to work, that person needs either a seat that includes Claude Code or, on the Enterprise plan, Cowork access on a **Standard** seat or a usage-based **Chat** seat. A [DM from a member who hasn't connected a Claude account](https://claude.com/docs/claude-tag/admins/restrict-access.md#direct-messages-from-members-without-a-claude-account) can bill to your organization for a limited time.
4545
4646## Where Claude Tag runs
4747
claude-tag/users/troubleshooting Changed · +2 / -2 lines
from line 651
651651
652652## DMs aren't working
653653
654One-to-one 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 **Usage-Based Chat** seat when the member also has Cowork), and they use your personal connectors rather than the channel connections. If channels work but DMs don't, first check that your Claude account is connected; DM `@Claude` and it prompts you to connect if it isn't.
654One-to-one DMs run on your own Claude account rather than the organization's agent. To use them, you need either a seat that includes Claude Code or, on the Enterprise plan, Cowork access on a **Standard** seat or a usage-based **Chat** seat. DMs also use the connectors on your own Claude account rather than the channel connections. If channels work but DMs don't, first check that your Claude account is connected; DM `@Claude` and it prompts you to connect if it isn't.
655655
656656### I get an environment error in a DM
657657
from line 684
684684
685685**What it means**
686686
687Your seat doesn't qualify for one-to-one DMs. A seat that includes Claude Code always qualifies; on the Enterprise plan, a **Standard** or **Usage-Based Chat** seat also qualifies when you have Cowork. Mentioning `@Claude` in a real channel doesn't depend on your seat type and keeps working.
687Your seat doesn't qualify for one-to-one DMs. To qualify, you need either a seat that includes Claude Code or, on the Enterprise plan, Cowork access on a **Standard** seat or a usage-based **Chat** seat. Mentioning `@Claude` in a real channel doesn't depend on your seat type and keeps working.
688688
689689**How to resolve**
690690