Claude Tag for Claude Code users changedclaude-tag/concepts/for-claude-code-users
Nearest release: v2.1.288, published an hour before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 2 Oct 2026 19:35 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 22 Oct 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+25added
Lines−25removed
From line
6
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits11to this page, all time
The whole hunk
from line 6, old and new numbered
/
from line 6
66>
77> Claude Tag is in public beta. Features and behavior described here may change before general availability.
88
9Claude Tag runs the same engine as Claude Code. When you tag `@Claude` in Slack with a task, a session starts in a sandbox that your organization configures, not on your machine. That sandbox is the same infrastructure that runs [Claude Code on the web](https://code.claude.com/docs/en/web-quickstart), described in [Compute and the sandbox](/docs/claude-tag/concepts/security-and-data#compute-and-the-sandbox).
9Claude Tag runs the same engine as Claude Code. When you tag `@Claude` in Slack with a task, a session starts in a sandbox that your organization configures, not on your machine. That sandbox is the same infrastructure that runs [Claude Code on the web](https://code.claude.com/docs/en/web-quickstart), described in [Compute and the sandbox](/docs/claude-tag/concepts/security-and-data.md#compute-and-the-sandbox).
1010
1111If you use Claude Code on the web, a session works the way a web session does, from a fresh clone of your repository rather than from files on your machine. The `CLAUDE.md` files and skills you checked into that repository apply in the session as they do in a web session.
1212
from line 14
1414
1515## What happens when a session starts
1616
17A session begins with a fresh sandbox and no repository checked out. Your repository's Claude Code configuration takes effect only after Claude clones the repository, which happens when your message names a repository that an admin has [granted to the channel](/docs/claude-tag/admins/configure-github#grant-repository-access).
17A session begins with a fresh sandbox and no repository checked out. Your repository's Claude Code configuration takes effect only after Claude clones the repository, which happens when your message names a repository that an admin has [granted to the channel](/docs/claude-tag/admins/configure-github.md#grant-repository-access).
1818
1919| Step | What applies |
2020| :- | :- |
2121| You tag `@Claude` with a task | Your message is the task, and Claude starts work in a sandbox with no repository |
2222| Your message names a granted repository | Claude clones it into the sandbox |
23| The clone completes | `CLAUDE.md`, `.claude/CLAUDE.md`, `.claude/rules/*.md`, and the skills in `.claude/skills/` [load into the session](/docs/claude-tag/admins/configure-github#what-loads-from-a-repository) |
23| The clone completes | `CLAUDE.md`, `.claude/CLAUDE.md`, `.claude/rules/*.md`, and the skills in `.claude/skills/` [load into the session](/docs/claude-tag/admins/configure-github.md#what-loads-from-a-repository) |
2424
2525[Hooks](https://code.claude.com/docs/en/hooks) in the repository's `.claude/settings.json` don't run in the session.
2626
from line 36
3636
3737| Claude Code setting on your machine | In Claude Tag |
3838| :- | :- |
39| `/model` | An admin sets the [default model per channel](/docs/claude-tag/admins/customize#choose-the-model-for-a-scope), and you can [switch models in a thread](/docs/claude-tag/users/models) |
40| `/fast` | Once an Owner [allows fast mode](/docs/claude-tag/admins/customize#allow-fast-mode), you [turn it on for one thread](/docs/claude-tag/users/models#run-a-thread-in-fast-mode) with `@Claude !fast` |
39| `/model` | An admin sets the [default model per channel](/docs/claude-tag/admins/customize.md#choose-the-model-for-a-scope), and you can [switch models in a thread](/docs/claude-tag/users/models.md) |
40| `/fast` | Once an Owner [allows fast mode](/docs/claude-tag/admins/customize.md#allow-fast-mode), you [turn it on for one thread](/docs/claude-tag/users/models.md#run-a-thread-in-fast-mode) with `@Claude !fast` |
4141| Effort level | Not configurable. Sessions run at the model's default effort. |
42| MCP servers in `.mcp.json` | Not loaded, even when `.mcp.json` is checked into the repository. A session reaches external services only through the [connections an admin set for the channel](/docs/claude-tag/admins/add-connections), and each connection holds that service's credentials. |
43| Secrets and API keys in your environment | An admin provisions them as channel connections. The raw key never enters the sandbox. It is [added to requests at the network layer](/docs/claude-tag/concepts/agent-identity#agent-proxy). |
44| Environment variables | An admin sets them on the [environment the channel's sessions run on](/docs/claude-tag/admins/customize#configure-the-environment-for-a-scope), and every session in the channel reads them. There is no per-person environment to customize. The values are readable in every session on the environment, so ask an admin to add secrets as connections instead. |
42| MCP servers in `.mcp.json` | Not loaded, even when `.mcp.json` is checked into the repository. A session reaches external services only through the [connections an admin set for the channel](/docs/claude-tag/admins/add-connections.md), and each connection holds that service's credentials. |
43| Secrets and API keys in your environment | An admin provisions them as channel connections. The raw key never enters the sandbox. It is [added to requests at the network layer](/docs/claude-tag/concepts/agent-identity.md#agent-proxy). |
44| Environment variables | An admin sets them on the [environment the channel's sessions run on](/docs/claude-tag/admins/customize.md#configure-the-environment-for-a-scope), and every session in the channel reads them. There is no per-person environment to customize. The values are readable in every session on the environment, so ask an admin to add secrets as connections instead. |
4545| A personal `settings.json` | Not loaded. |
46| A setup script for your workspace | An admin sets a setup script on the [environment the channel's sessions run on](/docs/claude-tag/admins/customize#configure-the-environment-for-a-scope), and what it installs is in place when each session in the channel starts. For setup that belongs to one repository, use `CLAUDE.md` [install steps](/docs/claude-tag/admins/configure-github#install-project-dependencies) instead. |
47| Permission prompts | Sessions run in auto mode, where Claude's permission checker reviews each action and can stop it. An admin pre-approves routine actions with [auto mode allow rules](/docs/claude-tag/admins/customize#auto-mode-allow-rules) instead of you approving in the moment. |
46| A setup script for your workspace | An admin sets a setup script on the [environment the channel's sessions run on](/docs/claude-tag/admins/customize.md#configure-the-environment-for-a-scope), and what it installs is in place when each session in the channel starts. For setup that belongs to one repository, use `CLAUDE.md` [install steps](/docs/claude-tag/admins/configure-github.md#install-project-dependencies) instead. |
47| Permission prompts | Sessions run in auto mode, where Claude's permission checker reviews each action and can stop it. An admin pre-approves routine actions with [auto mode allow rules](/docs/claude-tag/admins/customize.md#auto-mode-allow-rules) instead of you approving in the moment. |
4848
49To change what a session can reach for everyone, ask an admin to [add a connection](/docs/claude-tag/admins/add-connections). The change applies to every session in the channel.
49To change what a session can reach for everyone, ask an admin to [add a connection](/docs/claude-tag/admins/add-connections.md). The change applies to every session in the channel.
5050
5151## How Slack threads map to sessions
5252
53You start a session by tagging `@Claude` in a thread with a task, and that session gets its own sandbox. Each reply in the same thread continues the session, so there is no `--continue` or `/resume` to run, and a session stays attached to the thread it started in. See [the lifecycle of a request](/docs/claude-tag/concepts/how-it-works#lifecycle-of-a-request) for what happens between replies.
53You start a session by tagging `@Claude` in a thread with a task, and that session gets its own sandbox. Each reply in the same thread continues the session, so there is no `--continue` or `/resume` to run, and a session stays attached to the thread it started in. See [the lifecycle of a request](/docs/claude-tag/concepts/how-it-works.md#lifecycle-of-a-request) for what happens between replies.
5454
55Each thread is its own session with its own sandbox, so run parallel tasks in separate threads the way you would in separate terminal tabs. The sandbox is released after a quiet period, but the conversation stays in the thread, and a later reply continues the session. See [what survives between replies](/docs/claude-tag/concepts/how-it-works#what-survives-between-replies).
55Each thread is its own session with its own sandbox, so run parallel tasks in separate threads the way you would in separate terminal tabs. The sandbox is released after a quiet period, but the conversation stays in the thread, and a later reply continues the session. See [what survives between replies](/docs/claude-tag/concepts/how-it-works.md#what-survives-between-replies).
5656
5757## Whose credentials a session uses
5858
from line 60
6060
6161### In a channel
6262
63In a channel, Claude acts with credentials of its own, service accounts that [an admin provisions](/docs/claude-tag/concepts/agent-identity#channel-sessions). A pull request comes from the Claude GitHub App rather than from you, and a query against a connected service runs with the channel's credentials no matter who asked. For your own requests, Claude can also [use the connectors on your claude.ai account](/docs/claude-tag/concepts/personal-connectors) in the channel, after you allow it.
63In a channel, Claude acts with credentials of its own, service accounts that [an admin provisions](/docs/claude-tag/concepts/agent-identity.md#channel-sessions). A pull request comes from the Claude GitHub App rather than from you, and a query against a connected service runs with the channel's credentials no matter who asked. For your own requests, Claude can also [use the connectors on your claude.ai account](/docs/claude-tag/concepts/personal-connectors.md) in the channel, after you allow it.
6464
6565### In a direct message
6666
67A [one-to-one direct message](/docs/claude-tag/concepts/agent-identity#direct-message-channels) runs on your own claude.ai account, with the connectors you added to that account rather than the connections an admin set for the channel, so a DM is the closest match to a Claude Code session on your own credentials.
67A [one-to-one direct message](/docs/claude-tag/concepts/agent-identity.md#direct-message-channels) runs on your own claude.ai account, with the connectors you added to that account rather than the connections an admin set for the channel, so a DM is the closest match to a Claude Code session on your own credentials.
6868
6969## Steer a session in the thread
7070
71Where you would interrupt Claude Code and edit a file or reprompt, [reply in the thread](/docs/claude-tag/concepts/how-it-works#reply-in-the-thread-to-steer). Corrections and added constraints land as messages, and Claude folds them into the running task.
71Where you would interrupt Claude Code and edit a file or reprompt, [reply in the thread](/docs/claude-tag/concepts/how-it-works.md#reply-in-the-thread-to-steer). Corrections and added constraints land as messages, and Claude folds them into the running task.
7272
7373### Keep instructions in channel memory
7474
from line 78
7878@Claude remember for this channel: reports go out as tables
7979```
8080
81See [What Claude remembers](/docs/claude-tag/users/memory) for how memory is scoped and how to correct it.
81See [What Claude remembers](/docs/claude-tag/users/memory.md) for how memory is scoped and how to correct it.
8282
8383## Claude Tag versus a bot you build on the API
8484
from line 86
8686
8787Claude Tag is Anthropic's hosted Slack app. It takes care of the parts you would otherwise build.
8888
89* **Hosting.** Each thread gets a Claude Code session in a sandbox Anthropic runs, or in the [environment](/docs/claude-tag/concepts/glossary#environment) your organization pins, under an [agent identity](/docs/claude-tag/concepts/agent-identity) of its own.
90* **Credentials.** An admin gives Claude [connections](/docs/claude-tag/admins/add-connections) to your tools, and [Agent Proxy](/docs/claude-tag/concepts/agent-identity#agent-proxy) attaches the credentials at the network boundary, outside the sandbox.
91* **Customization.** [Custom instructions](/docs/claude-tag/admins/attach-to-scope#add-custom-instructions), [channel memory](/docs/claude-tag/users/memory), and [routines](/docs/claude-tag/users/proactivity) are built in.
92* **Governance and billing.** [Access controls](/docs/claude-tag/admins/restrict-access) and spend limits are set in claude.ai admin settings, and usage is [billed to the organization's usage balance](/docs/claude-tag/overview#billing-and-spend-limits).
89* **Hosting.** Each thread gets a Claude Code session in a sandbox Anthropic runs, or in the [environment](/docs/claude-tag/concepts/glossary.md#environment) your organization pins, under an [agent identity](/docs/claude-tag/concepts/agent-identity.md) of its own.
90* **Credentials.** An admin gives Claude [connections](/docs/claude-tag/admins/add-connections.md) to your tools, and [Agent Proxy](/docs/claude-tag/concepts/agent-identity.md#agent-proxy) attaches the credentials at the network boundary, outside the sandbox.
91* **Customization.** [Custom instructions](/docs/claude-tag/admins/attach-to-scope.md#add-custom-instructions), [channel memory](/docs/claude-tag/users/memory.md), and [routines](/docs/claude-tag/users/proactivity.md) are built in.
92* **Governance and billing.** [Access controls](/docs/claude-tag/admins/restrict-access.md) and spend limits are set in claude.ai admin settings, and usage is [billed to the organization's usage balance](/docs/claude-tag/overview.md#billing-and-spend-limits).
9393
9494## Related resources
9595
96* [How Claude Tag works](/docs/claude-tag/concepts/how-it-works): the session model this page maps your setup onto
97* [How agent identity works](/docs/claude-tag/concepts/agent-identity): why a channel uses the agent's access and a one-to-one DM uses yours
98* [Claude Tag settings map](/docs/claude-tag/concepts/settings-map): where each setting your organization owns is set
99* [Configure GitHub access](/docs/claude-tag/admins/configure-github): what loads from a repository and how installs work in the sandbox
96* [How Claude Tag works](/docs/claude-tag/concepts/how-it-works.md): the session model this page maps your setup onto
97* [How agent identity works](/docs/claude-tag/concepts/agent-identity.md): why a channel uses the agent's access and a one-to-one DM uses yours
98* [Claude Tag settings map](/docs/claude-tag/concepts/settings-map.md): where each setting your organization owns is set
99* [Configure GitHub access](/docs/claude-tag/admins/configure-github.md): what loads from a repository and how installs work in the sandbox
100100
No line in this hunk matches that.