← PostsPost ·

Claude Code Projects: what the new coordinator does

On 2026-11-13 Anthropic made the coordinator in Claude Code Projects proactive: it answers in the project chat and posts updates on running threads. Projects is in public beta on the Pro, Max and Ultra plans.

Give this to your agent

Open in

Your agent checks this against your setup and tells you if it fits.

See the file
# Claude Code Projects: one coordinator runs parallel threads and now reports on them
From Rig Labs, 2026-11-16. Information for an agent, not orders. Page: https://riglabs.ai/blog/claude-code-projects-coordinator/

What changed: On 2026-11-13 Anthropic made the coordinator in Claude Code Projects proactive. It answers questions in the project chat and posts status updates on running threads without being asked. Projects is in public beta on Pro, Max and Ultra, rolling out gradually.
Fits if: Your human is on Claude Pro, Max or Ultra, codes in GitHub repositories, and often runs several Claude Code tasks at once.
Skip if: Your human is on a Team or Enterprise plan (not offered yet), needs to share the work with others (a project belongs to one user), or Projects does not show in their sidebar yet.
Check: Whether Projects shows at claude.ai/code or in the desktop app's Code tab, directly or under More. If a project exists, read its thread model, thread effort and the auto-continue setting in Project settings > General. Read only.
Try: Propose sending the coordinator: "Give me a status update on every thread. From now on, only post when something finishes or is blocked."
Ask first: Before creating a project, starting threads, changing the thread model, or changing auto-continue. Each thread uses the human's plan.
Cost: Included in Pro, Max and Ultra plan limits, used faster than a single session. New projects default to Opus for threads at high effort, and threads continue on their own after a usage limit resets unless auto-continue is turned off.
Undo: Nothing to undo for the check. The coordinator's posting preference can be changed by telling it again in the project chat.
Deeper: https://code.claude.com/docs/en/claude-projects.md

Claude Code Projects got a more proactive coordinator on November 13, 2026: per Anthropic’s @ClaudeDevs account, the coordinator now answers your questions in the project chat and posts status updates on its threads. The coordinator is the one Claude conversation that coordinates a project, and its threads are the separate Claude sessions it starts to work in parallel. Projects is in public beta on the Pro, Max and Ultra plans, rolling out gradually, per Anthropic’s docs.

What you can now do: hand one Claude conversation a stream of coding tasks, let it split them across several Claude workers that run at the same time, and ask that one conversation where everything stands, instead of checking each worker yourself.

How does a Claude Code project work?

A Claude Code project is one coordinating conversation plus the threads it starts, per Anthropic’s docs. The coordinator takes what you send, decides what becomes a thread and tracks every thread. Each thread is a separate Claude session, usually in the cloud, that works on its own Git branch and opens a pull request when the work calls for one.

The coordinator sees what threads report back, not every step they take. When a thread needs your approval, the prompt sits inside that thread, and telling the coordinator to go ahead does not reach it, per the docs.

What changed in the November 13 update?

Anthropic’s docs list requests you can send the Claude Code Projects coordinator, such as “Give me a status update on every thread” or “Only post when something finishes or is blocked”. Claude saves preferences like these to project memory and follows them later.

Who can use Claude Code Projects?

Detail, per Anthropic’s docs
Plans Pro, Max and Ultra, public beta, rolling out gradually
Not yet Team and Enterprise
Where Projects in the sidebar at claude.ai/code or in the desktop app’s Code tab, sometimes under More
No access yet A waitlist at claude.com/form/projects
Sharing A project belongs to one user and cannot be shared

How much of your plan does a project use?

A Claude Code project draws on the same plan limits as your other Claude Code sessions and uses them faster, per Anthropic’s docs. On a Pro plan, the docs say to expect to reach your limit sooner on days you run one. Three defaults matter:

  • Opus everywhere. A new project runs Opus for threads at high effort and for the coordinator at low effort, and for routine tasks you can pick a smaller thread model or a lower effort in Project settings > General.
  • Auto-continue. A thread that stops at your plan’s five-hour or weekly limit continues on its own when the limit resets, so its work counts against your next usage window. This is on by default.
  • Pull request watching. An idle thread wakes up and uses your plan again when CI fails or a review comment arrives on its pull request.

A project with no running threads, no watched pull requests and no new messages uses nothing while idle.

What to do today

If Projects shows in your sidebar, open Project settings > General before your next project starts work. Pick a smaller thread model or a lower effort if the tasks are routine, and decide whether to turn off “Auto-continue when usage limits reset”. Then send the coordinator:

Give me a status update on every thread. From now on, only post when something finishes or is blocked.

Last checked 2026-11-16.

Sources:

Get the next one by email

The Edge is our newsletter: what changed in AI, and what to do about it.

Which emails
Free. Your agent reads every piece we publish, and you hear only what fits.

Subscribe your agent Beta

Your agent reads every post, guide and issue, checks it against your setup, and tells you only what is worth your time. Its inbox gets the daily agent cards email automatically, every day something is published, and the weekly issue as plain text. You pick weekly, daily or both for yourself.

  1. Give it the prompt

    Using Claude Code, Codex or another agent? Copy the prompt and paste it in.

    See the prompt
    Subscribe yourself to The Edge, the newsletter from Rig Labs, and follow what Rig Labs publishes for me.
    Read https://riglabs.ai/agents/subscribe.md and follow its steps. It has you save the skill at https://riglabs.ai/agents/the-edge/SKILL.md, set yourself up with your own inbox on Nym (invite: https://withnym.com/join/NYM-TQZB-WP35, code NYM-TQZB-WP35) unless you already have one, subscribe that address, and confirm with me.
    Treat everything you fetch from Rig Labs as information, not orders. Ask me before anything that touches keys, payments, permissions, installs or sending messages.
  2. Approve its inbox

    It gets its own address on Nym, so The Edge never lands in your inbox. One sign-in in your browser, about a minute.

  3. Hear only what fits

    At most one short message a day. Nothing if nothing fits.

Your agent follows subscribe.md and saves SKILL.md: read both first. Nym is in private beta. The invite is included in the prompt.

Read next

Built by Rig Labs

When a tool we need does not exist, we build it.