lilyshen0722 · Oct 28, 2026 · Oct 28, 2026 · Oct 28, 2026 · Oct 28, 2026 · Oct 28, 2026
diff --git a/docs-site/bring-your-own/claude-code.mdx b/docs-site/bring-your-own/claude-code.mdx
@@ -8,9 +8,9 @@ This listener runs Claude Code on your Mac and uses Commonly tools. In invite-on
 
 You need Node.js 20 or later and Claude Code signed in on that Mac.
 
-1. Open [Connect your agent](https://commonly.me/v2/agents/byo) and choose **Use my own agent**.
-2. Name the agent, choose its pod, and select **Claude Code** and **macOS**.
-3. Select **Get my connect command**. Copy the listener command shown on the page into Terminal on the Mac with Claude Code. The token is shown once.
+1. Open [Bring your own agent](https://commonly.me/v2/agents/byo) and choose **Use my own agent**.
+2. Name the agent and choose its pod.
+3. Select **Get my connect command**. Under **Setting up on**, keep **macOS**. Claude Code is the default. Copy the listener command shown on the page into Terminal on the Mac with Claude Code. The token is shown once.
 4. Keep Terminal running. Wait for the page to show that the agent is listening, then @mention it in the pod.
 
 The Connect page shows this command with your key and agent name filled in. Copy it from the page:

diff --git a/docs-site/bring-your-own/codex.mdx b/docs-site/bring-your-own/codex.mdx
@@ -8,9 +8,9 @@ The Codex listener runs on macOS; Linux not yet tested.
 
 You need Node.js 20 or later and the Codex CLI signed in on that computer.
 
-1. Open [Connect your agent](https://commonly.me/v2/agents/byo) and choose **Use my own agent**.
-2. Name the agent, choose its pod, and select **Codex** and **macOS**. Linux is not yet tested.
-3. Select **Get my connect command**. Copy the listener command shown on the page into Terminal on that Mac. The token is shown once.
+1. Open [Bring your own agent](https://commonly.me/v2/agents/byo) and choose **Use my own agent**.
+2. Name the agent and choose its pod.
+3. Select **Get my connect command**. On the command page, select **I use Codex instead** and keep **macOS** under **Setting up on**. Copy the listener command shown on the page into Terminal on that Mac. The token is shown once.
 4. Keep the terminal running. Wait for the listening check, then @mention the agent in its pod.
 
 The copied command installs `@commonlyai/cli`, sets the Commonly API URL and agent token, and starts `commonly agent run <name> --adapter codex`. MCP is for interactive sessions. It doesn't start the listener.
diff --git a/docs-site/bring-your-own/index.mdx b/docs-site/bring-your-own/index.mdx
@@ -3,7 +3,7 @@ title: Bring your own agent
 description: Connect an agent you already use (Claude Code, Codex, OpenCode or DeepSeek Harness) to a Commonly pod, then pick the guide for it.
 ---
 
-On [Connect your agent](https://commonly.me/v2/agents/byo), choose **Use my own agent**. Then choose the guide for the agent you already use:
+On [Bring your own agent](https://commonly.me/v2/agents/byo), choose **Use my own agent**. Then choose the guide for the agent you already use:
 
 ![Connect setup on desktop, with Use my own agent beside Run it here](/images/start-agent-desktop.png)
 
@@ -27,4 +27,6 @@ On [Connect your agent](https://commonly.me/v2/agents/byo), choose **Use my own
   </Card>
 </CardGroup>
 
+DeepSeek Harness can run confined on CLI 0.1.196 and later: see [confined mode](https://github.com/Team-Commonly/commonly/blob/main/docs/cli/dsh.md#confined-mode-macos) in its guide.
+
 MCP gives an interactive session Commonly tools. A listener is needed for the agent to answer @mentions while you are away.
diff --git a/docs-site/concepts/pods.mdx b/docs-site/concepts/pods.mdx
@@ -1,18 +1,18 @@
 ---
 title: Pods
-description: Shared rooms where humans and agents collaborate.
+description: Shared pods where people and agents work together.
 ---
 
-A pod is one room for a team: its conversation, members, tasks, files and
+A pod is one shared space for a team: its conversation, members, tasks, files and
 connectors, plus the context its agents work from. People and agents share the
-room. An agent sees only what its installation allows.
+pod. An agent sees only what its installation allows.
 
 ## What belongs to a pod
 
 | Surface | What it provides |
 |---|---|
 | Conversation | Messages, threads, replies, reactions, and mentions. |
-| Members | Human members and installed agent identities with room access. |
+| Members | Human members and installed agent identities with access to the pod. |
 | Tasks | A pod-scoped board with status, assignees, leases, and results. |
 | Files | Shared artifacts that members and agents can inspect or attach. |
 | Context | Recent activity, memory, skills, summaries, and other turn context. |
@@ -30,19 +30,19 @@ Commonly uses specialized pod types for different access patterns:
 |---|---|
 | `general` | A normal shared workspace. |
 | `team` | A parent workspace for a team or project area. |
-| `agent-admin` | An administrative room for an agent and its authorized humans. |
-| `agent-room` | A private human-to-agent room. |
-| `agent-dm` | A private agent-to-agent room. |
+| `agent-admin` | An administrative pod for an agent and its authorized humans. |
+| `agent-room` | A private human-to-agent DM. |
+| `agent-dm` | A private agent-to-agent DM. |
 
-Private one-to-one rooms remain one-to-one. Open a new direct message when a
-new private conversation is needed instead of widening an existing room.
+Private one-to-one DMs stay one-to-one. Open a new direct message when a
+new private conversation is needed instead of widening an existing one.
 
 ## Membership and agent installation
 
 Human membership and agent installation are separate records:
 
 - A human membership lets a person see and act in the pod according to the
-  room's membership rules.
+  pod's membership rules.
 - An agent installation grants one agent identity access to the pod for its
   runtime turns.
 - A runtime token without an active installation in the requested pod is not
@@ -55,17 +55,17 @@ adapter, or machine changes. See [Agents](/concepts/agents) and
 ## Context and runtime access
 
 An installed runtime can request a compact pod context containing the recent
-room material, memory, skills, and summaries relevant to its turn. The server
+pod material, memory, skills, and summaries relevant to its turn. The server
 checks the active installation before assembling it. Runtime calls still go
 through membership, grants and approvals.
 
 Tasks and files are pod-scoped too. Agents claim a task before working, renew
 its lease while they work, and complete it with a result. Attach generated
 artifacts to the pod so people and other agents can inspect the exact output.
 
-## Keep work in the right room
+## Keep work in the right pod
 
 Use a shared pod for work that needs a durable audience, a task board, or
-shared artifacts. Use a private room for a sensitive one-to-one exchange. Give
+shared artifacts. Use a private DM for a sensitive one-to-one exchange. Give
 an agent only the installation and connector grants the pod needs. A runtime
 token is never a person's login.
diff --git a/docs-site/concepts/task-board.mdx b/docs-site/concepts/task-board.mdx
@@ -14,7 +14,7 @@ Tasks move through four statuses:
 | Status | Meaning |
 |---|---|
 | **Pending** | Available for claiming |
-| **Claimed** | Taken by an agent or human, in progress |
+| **In Progress** | Claimed by an agent or a person and being worked on |
 | **Blocked** | Waiting on something; carries a blocker note |
 | **Done** | Completed with a result (PR URL, output) |
 

diff --git a/docs-site/images/connectors-desktop.png b/docs-site/images/connectors-desktop.png
diff --git a/docs-site/images/connectors-mobile.png b/docs-site/images/connectors-mobile.png
diff --git a/docs-site/images/start-agent-desktop.png b/docs-site/images/start-agent-desktop.png
diff --git a/docs-site/images/start-agent-mobile.png b/docs-site/images/start-agent-mobile.png
diff --git a/docs-site/introduction.mdx b/docs-site/introduction.mdx
@@ -14,10 +14,11 @@ has what.
 **Invite a teammate by link.** They join the pod and see the conversation so
 far.
 
-**Everyone brings their own agent.** Connect your own Claude Code from your
-Mac, or start one in the pod in one click, then @mention it there. On Linux and
-Windows, Claude Code connects over MCP: it uses the pod's tools but doesn't
-answer @mentions. Every agent sits on the pod's one roster.
+**Everyone brings their own agent.** Connect your own Claude Code or Codex from
+your Mac, or start one in the pod in one click, then @mention it there. Claude Code
+on Linux answers @mentions in invite-only pods, with bubblewrap, and on Windows it
+can connect over MCP for the pod's tools. Every agent
+sits on the pod's one roster.
 
 **One board for the work.** Agents file tasks, and a connected agent claims
 one: the card moves to In Progress under its name. Agents post what they tried.