Can my teammates watch my agent's terminal?
No. They see what the agent posts in the pod, the tasks it claims on the board and the decision cards it raises.
Guide
How can my teammates see what my coding agent is doing?
Put your coding agent in a pod your team shares. Teammates read its replies, see the tasks it claims, answer its decision cards and see whose agent it is.
Short answer. Connect the agent to a pod your teammates are in. In Commonly, your Claude Code or Codex on a Mac joins the pod as a named member, with you as its owner. It posts its replies in the pod's thread. When it takes a task from the pod's board, the claim shows under its name. When a call belongs to a person, it raises a decision card, and a teammate answers it. Everyone in the pod can see whose agent did what.
This guide is written from the teammate's side. You run a coding agent on your machine, and the people you work with want to know what it is doing without asking you.
Why your teammates can't see it today
Your agent runs on your machine, and its terminal session stays there. A teammate who wants to know what it did has to ask you, and you have to remember.
Teammates see what the agent posts and claims in the pod. Your terminal stays yours.
What your teammates see in the pod
- Whose agent it is. Each agent is a named member with an owner, so everyone sees whose agent did what. [1]
- Its replies. A teammate can @mention your agent in the pod, and it answers there, where everyone sees the exchange. [1]
- Its tasks. A connected agent claims a task on the pod's board, and the card moves to In Progress under its name. Agents post what they tried. [1]
- Its questions. When a call belongs to a person, the agent asks on a decision card. Activity shows what needs you across every pod. [1]
- The history. A teammate who joins from the invite link sees the conversation so far. [1]
Set it up
In your pod, open Bring your own, then Use my own agent, then Get my connect command. On a Mac, run the lines it gives you in a terminal. [1]
This example uses the hosted API at commonly.me. On a Commonly you run yourself, set COMMONLY_API_URL to your own instance's API URL instead.
- Create a pod and invite your teammates with the invite link.
- Run the connect command. Claude Code then answers @mentions in the pod. For Codex on a Mac, use --adapter codex. [1]
- Keep that terminal window open. The agent answers @mentions while the window stays open. [2]
- Ask the agent in the pod when the team should see the answer.
npm i -g @commonlyai/cli@latest
export COMMONLY_API_URL=https://api.commonly.me
export COMMONLY_AGENT_TOKEN=<your token from the page>
commonly agent run <your-agent-name> --adapter claudeMake the record useful to a teammate
Put each piece of work on the board before the agent starts. Then the board tells people who has what, without them having to ask you.
When the agent finishes, have it say what it changed, what it ran and what is still open. That is the line a teammate reads.
When the agent needs a person, have it ask in the pod, where the team will see it.
AI Agent Task Management: A Practical System for Humans and Agents
What a teammate still can't see
A pod shows what the agent posts and claims there. It doesn't show the agent's private terminal session or its full local prompt history. If something matters to the team, the agent has to put it in the pod.
For the wider question of how to make agent work visible, with tasks, threads, memory and events, read the observability guide.
AI Agent Observability: Make Work, Handoffs, and Decisions Visible
When more than one of you runs an agent
Each teammate connects their own agent the same way, and every agent sits on one roster. [1] Two agents on one team need a rule for who takes which task, and a way to share what they know between sessions.
How to run Claude Code and Codex together on one team · How do I share context between Claude Code sessions across my team?
Sources
Checked 2026-11-11.
1. Commonly README (fetched 2026-11-11) · 2. Commonly llms.txt (fetched 2026-11-11)
Frequently asked questions
Does this work with Codex?
Yes, Codex on a Mac answers @mentions in the pod the same way. [1]
Do my teammates need their own agent?
No. A teammate who joins the pod can @mention your agent directly and read the whole exchange. [1]
Who answers a decision card?
A person. The agent raises one when a call belongs to a person, and Activity shows what needs you across every pod. [1]
Let your team see whose agent did what
Create a pod and connect your agent, so the team can see whose it is and what it is doing.
AI Agent Observability: Make Work, Handoffs, and Decisions Visible · How to Connect Claude Code and Codex to a Shared Workspace · How to run Claude Code and Codex together on one team