DEV Community: QuanticStudios

Group Claude Code and Codex workers in pitwall beta 13

QuanticStudios — Tue, 20 Oct 2026 15:09:10 +0000

We build pitwall at Quantic Studios. In beta 13, tabs opened from a pitwall pane are grouped under their parent tab. The parent shows a bar of worker states and counts for workers that need you, failed, are working or are done. You can fold the workers away and still see those counts.

Sample workspace. Billing epic groups ten worker tabs. The state bar summarizes the group; click it to fold the worker rows.

The example below starts with two tasks that request no file changes.

Start with two read-only tasks

Install pitwall and update to v0.1.0-beta.13. Install and authenticate Claude Code and Codex separately. Their subscription or API costs still apply.

On Linux or macOS with Homebrew:

brew install quanticstudios/tap/pitwall
# If it is already installed:
# brew upgrade quanticstudios/tap/pitwall
pitwall --version
pitwall

Use the first-run hook setup, or inspect and install the hooks from a terminal:

pitwall hooks install --dry-run
pitwall hooks install

In Codex, run /hooks once to trust the hooks. Restart agent sessions that were running before hook installation.

Open a terminal pane inside pitwall, in a small repository. Run both commands from that same pane:

pitwall new -n explain -- claude "Explain this repository's entry points. Do not edit files."
pitwall new -n tests -- codex "Find the documented test commands and explain what they cover. Do not run commands or edit files."

Each command prints its new tab address. Leave off -d so the tabs stay visible in the sidebar. Run these from a pitwall pane so the commands have a calling pane for grouping.

These prompts request read-only work. They do not create a security sandbox or change the agents' permissions.

List the workers and wait for them

From the same parent pane:

pitwall ls --children
pitwall wait --children --until done --timeout 10m

The wait covers the tabs opened by that parent, including workers added while it waits. A worker that needs permission, an answer or plan approval stops the wait early. Answer that worker in its tab, then run the wait again.

The exit status tells the caller what happened:

Status	Meaning
0	The workers reached the requested state.
2	A worker needs human input or approval.
3	A worker process exited with an error while waiting.
124	The timeout expired.
1	The command failed, for example because a tab closed.

Inspect the printed state as well as the exit status. Done means an agent finished its turn. It does not prove the explanation is correct or that a code change passed its tests.

Click the state bar to fold the worker rows. Ctrl+Shift+U can still jump to a folded worker that needs you.

Give editing tasks separate worktrees

Once the read-only example works, use a separate worktree for each task that changes files:

pitwall worktree new docs-example -- claude "Improve the README setup example. Do not edit application code. Review the diff and commit your changes on this branch."

Run that from the parent pane too. The worker gets its own branch and ports. pitwall warns when workers edit the same file, but those warnings do not resolve conflicts. Inspect the diff and run the relevant checks before merging.

Sample worktree card. The conflict warning names the other task and the affected file.

Keep the permission prompts

wait --children reports that a worker needs you. It does not answer the request. Grouping the tabs also does not give one agent authority to approve another agent's actions.

If you use pitwall send for follow-up messages, remember that its queue is held in memory. A daemon restart loses pending messages. Check the receiving transcript before resending.

Staged conversation in the real pitwall interface. Message headers identify the sender and where to reply.

The beta 13 release notes also cover Vim and Neovim pane navigation. The agent command guide has the full worker and wait semantics.

pitwall is free and MIT-licensed. Linux is where we use it daily; macOS and Windows builds need more testing. If this example stops at the wrong state, an issue with your OS, pitwall version, agent version and the order of events helps us reproduce it. Leave private prompt content out.

An AI agent drafted this guide from the release notes and command documentation. The commands were checked against those documents; this article does not report a newly executed agent run.

Run Claude Code and Codex side by side with pitwall

QuanticStudios — Thu, 15 Oct 2026 21:13:33 +0000

We're Quantic Studios, the team building pitwall, a free, MIT-licensed desktop terminal for coding agents. This guide gets two agents into visible tabs, sets up their status reporting, and shows how to send a follow-up without interrupting a turn.

The goal is specific: spot the agent waiting for you while another agent is still working. Start with a small repository you can inspect.

The image shows a sample workspace, not a live customer project.

Install and open a session

With Homebrew on Linux or macOS:

brew install quanticstudios/tap/pitwall
pitwall --version
pitwall

Linux is where we use pitwall daily. macOS and Windows builds are newer beta builds with less hands-on testing. Windows installation and platform limitations are in the install guide.

Claude Code and Codex must already be installed and authenticated separately. pitwall doesn't include either agent or pay for its usage.

Set up status reporting

The first window lists the agents on your PATH and offers to install their reporting hooks. The command-line equivalent is:

pitwall hooks install

The installer backs up agent configuration and preserves existing hooks. In Codex, run /hooks once to trust the new hooks. Restart agent sessions that were already running. The hook documentation explains the files this changes.

Start with two read-only questions

Inside a pitwall terminal, change to your repository. Open two visible tabs:

pitwall new -n explain -- claude "Explain this repository's entry points. Do not edit files."
pitwall new -n tests -- codex "Explain how this repository runs its tests. Do not edit files."

Both tabs appear in the sidebar. Watch their states as they work and finish. If an agent asks for permission or input, inspect the request in its tab. Ctrl+Shift+U jumps to an agent that needs you; on macOS, use Cmd+U.

These first tasks request no edits, so you can check the workflow before running agents that modify the same repository. Use separate worktrees for independent editing tasks.

Send a follow-up without interrupting a turn

The current beta includes pitwall send. From another pane in the same session:

pitwall send tests -- "Which test should a new contributor read first? Do not edit files."

The message queues until the agent is ready at its prompt. It doesn't answer a permission request. Queued messages live in memory and disappear if the daemon restarts.

For an agent-to-agent discussion, the message header includes the sender and a reply address. The released command guide covers replies, waiting for results and the message limit.

If a state looks wrong

Check that the hooks are installed with the binary you're running. Include your OS, pitwall version, agent CLI version, expected state and reproduction steps in a bug report. Remove private project details before sharing screenshots or logs.

See the sample workspaces and supported-agent table. The latest release checked for this guide is v0.1.0-beta.8.

i made pitwall, a terminal multiplexer for coding agents

QuanticStudios — Sat, 03 Oct 2026 20:12:51 +0000

hey, i'm the author of pitwall. it's a native terminal multiplexer for running coding agents side by side.

split panes, group tabs by project, and see who's working, waiting for you, asking for approval, or done. closing the window leaves your sessions running in a background daemon.

Claude Code and Codex work now. more harnesses are coming soon. it's free, MIT-licensed and alpha. Linux is the main platform; macOS and Windows are experimental.

it's written in Go with Gio. terminals use real fonts and pixels. agent hooks report state to the sidebar, and Ctrl+Shift+U jumps to a pane that needs you.

source, downloads and setup: https://github.com/quanticstudios/pitwall

sorry about the AI-generated promo video. the two images are rendered frames from the promo.

watch the promo video

give it a try if you're running several agents at once. i'd like feedback on installation, pane/tab handling and whether agent status updates correctly in your workflow. bugs, ideas and PRs are welcome. include your OS/version and architecture if something breaks.

After installing from the repo instructions:

pitwall hooks install --dry-run
pitwall hooks install
pitwall