Theo-brainUnofficial. Not affiliated with Theo or t3.gg.
Sign inYou

T3 Code guide

How T3 Code works, feature by feature. I put this together from its docs, its release notes and Theo’s videos.

Looking for a setting? Settings reference

Best ways to use T3 Code

Seven habits from Theo’s own videos. Open one to see what he said.

Spawn worktrees by default and fire prompts off in the backgroundA worktree is a separate copy of your project's files so agents can work without clashing.

Give every task its own branch and directory so parallel work stays manageable. Press Cmd+Enter instead of Enter to launch the prompt as a new thread while you stay on the composer, then brain-dump the next job right away.

29:48By default, I highly recommend that you spawn work trees because it just makes managing everything way easier when you're working in parallel, but that's your choice.

T3 Code broke me

44:16And here is where one of my favorite T3 code pro tips comes in. I'm not going to press enter, I'm going to press command enter, which sends off the thread in the background and leaves me exactly where I am. So I can now send off another prompt without having to do anything. It's very nice.

If you have a Claude sub, watch this

29:11So if I I don't know say I want you to work on feature one. I could hit enter and it would send and start the thread the normal way or I can hold down command and press enter and it opens a new thread and I stay here.

How I Code Without Typing

T3 Code docs: thread sidebar

Treat the sidebar as an inbox

Settle threads without hesitation once their work is merged, abandoned or solved, and aim to keep only a few open. Snooze anything waiting on others, even until next week, and pin long-running threads so they stay visible. Press Cmd+Z if you settle one by mistake.

12:37…mindset changes to understand is this idea of the sidebar being an inbox. When your work is done, it should go away. Settled is similar to archive. When your thing has merged, or you're throwing it away, or you've solved the problem you have, you should not ever be scared to settle it. And ideally, you have a small number of threads at any given time.

These 3 skills changed my life

16:36You don't archive threads, you settle them. It feels much less permanent. All your settled threads appear at the bottom here, and you just click the little checkbox, and now it's settled, and you move to the next one. If that was a mistake, you could command Z and get it right back.

T3 Code broke me

35:46So, again, with the staying productive thing, I know they're going to take a bit on this one. So, I'm going to snooze this to next week. And if they haven't solved it by next week, I'm going to start bugging my contacts to get them to try and fix it, because this is stupid. I really optimize for keeping my thread list as minimal as possible. Even now, I only have like 1 2 3 4 5 6 7 threads…

You're using AI agents wrong

36:00I really optimize for keeping my thread list as minimal as possible. Even now, I only have like 1 2 3 4 5 6 7 threads here. Two are pinned long-running ones. My Swift iOS app, which I rebuilt T3 code in Swift UI from scratch for fun,…

You're using AI agents wrong

Steer running agents instead of queuing follow-ups

Set follow-ups to steer, then send quick corrections or extra requests mid-run, such as telling the agent you already ran an update or asking for findings as HTML for your phone. The agent adjusts course without stopping or restarting.

20:29First off, I noticed it being confused because it was checking the history and saw that the instance was updated. So I responded when it was running with a quick steer saying I manually ran the update after so that it knew the update had been run.

Meta just caught up with Anthropic

6:07PRs that you care about or what I'll do here. Put your findings in HTML so that I can more easily look at them on my phone. This is now going to go in as additional steering context, and I…

Ox Alpha is INSANE

18:05…have steering too, so when the model's annoying you, you can send a message to do a follow-up. We also have queuing, so queued message, and you can have a hot key to swap between the two. I don't like queuing, so I set my default to be steer, but you can change that in settings.

T3 Code broke me

4 more ways
End prompts with "file a PR and babysit it"

Ask the agent to implement the change, open a pull request and watch it, so it reacts to CI failures and review comments on its own. Have it attach a video proving the fix works, and tell it in your PR skills to use the built-in watch feature rather than its own polling.

11:17What would it look like to cache that similar to how we cache on the sidebar? If it's relatively easy, I would like you to implement it and file a PR and babyset it.

Anthropic Made Claude Even Better

14:39This is a skill that gets invoked when I tell the model to watch or babysit a pull request. The point of this skill is to keep the model checking for updates, for new comments, and make sure by the time I go check the thread, it's good to go.

So I was using Fable wrong...

16:58…is again cuz my babysit PR skill was leading to OpenAI models not taking advantage of T3 Code's built-in watchers and doing stupid instead. So, I added another section here. In T3 Code, you should use the watch pull request feature. If you stop before the merge, call unwatch pull request first.

These 3 skills changed my life

15:18Or just tell it to throw a video do the pull request so you know it worked. That's what we do most of the time now with T3 code. Here's a PR from Maria.

Please stop using stupid models

Run agents on a fleet of other machines and drive them remotely

Set up T3 Connect on spare boxes and servers so threads run there rather than on your laptop. Let auto load balancing spread new threads across machines, and kick off work from your phone by voice, checking results later at your desk.

13:57Connect is set up on this computer, which means I can quit from SSH, clear, never think about it again, and manage the whole machine all from my desktop app or my phone app. It is genuinely the most pleasant way I've ever found to manage all of my AI coding stuff, and I basically never run threads on my own computer anymore.

T3 Code broke me

4:39…been around for a bit know, I have moved pretty much all my agent work off my laptop and onto other machines, mostly my apartment, but a few remote servers as well. So normally when I use T3 Code I trigger it somewhere else.

Getting the most out of Opus 5.5

18:10Funny enough, I sent this one from voice to text on my iPhone as I was getting my hair ready in the bathroom before stream because I wanted to have it ready to use if I wanted to demo it during stream. So I was on my phone.

How I Code Without Typing

44:40And if you're too lazy to even pick which server to run, Maria has built an awesome feature for you in settings here. Load balancing. You can now set up auto load balancing across all of the servers that you have connected in T3 code, so it will fire off the threads across your different machines.

If you have a Claude sub, watch this

Hand the agent a screenshot of the bug and say "Fix it"

Skip working out the fix yourself: paste the screenshot and ask it to fix, test, record a proof video, link the PR and babysit review. If it fails, you know the problem needs more of your own thinking.

34:55So, now I just hand the screenshot to the agent and say, ‘Fix it.’ And it often does. And if it fails to, I now know this problem is too hard for the agent to do itself. At which point, I know it's time to think more about it.

If you have a Claude sub, watch this

9:37…get a DM on my phone from a bug a user had in T3 code. So, I screenshot it. I paste it to my agent in T3 code on my phone and say, ‘Fix this, test it, record a video showing it works now, and link me the PR when you're done. Babysit it until all the issues that come up in review are addressed.’

Please stop using stupid models

32:26I'll still screenshot the tweet and go post it into T3 Code myself. I won't have the agents propose fixes based on what people are tweeting yet.

Boris Is Right Again (I Hate It)

Have Claude call Codex through T3 Code to review its work

Connect agents to the T3 Code MCP so one can spin up threads with another. Theo has Claude ask Codex to review Claude's changes because he finds OpenAI models more thorough at analysis, and lets Codex start Claude threads to take tasks from email to shipped.

31:58…because Open AI models I've still found are a bit more thorough with their analysis and will find things deeper than Anthropic models tend to. So, I do a wield and the vast majority of my Codex usage is either me using it to like do my email and computer you or it's coming from Claude calling Codex via T3 code in order to review Claude's work.

Does the $200 Codex plan suck now?

24:30Now that I've connected the T3 code MCP to my Codex, I can have Codex and dots spin up Claude threads in T3 code. I've created the pipes to allow these things to connect and connected the data that my agents need to operate. And now I can go from it tracing an email for me to shipping real changes with other agents and other programs across my systems.

Your prompts kinda suck

T3 Code docs: outside agents

Getting started

Threads

Start a thread

Keeping separate tasks apart. Choose New worktree when the code changes need their own branch and working directory.

Start without a project

Quick one-off jobs, such as converting files, that do not belong to a repository.

Pin and reorder threads

Keeping your most important threads at the top and arranging active work in the order you want.

Settle finished work

Clearing finished work from your active list. Settling also closes the thread's idle terminals while keeping their output.

Find and reference work

Jumping back to earlier work, and sharing thread links that open the thread or paste into a composer as a thread chip.

Side chats

Asking clarifying questions about ongoing work without cluttering or interrupting the main thread.

Resume after usage limits

Continuing interrupted work without losing your place or your queued messages.

Prompt links

Sharing a prompt on social media, or putting a one-click fix in a pull request comment.

Switch provider or model mid-thread

Continue the same thread with another provider. For longer conversations, T3 Code favors recent requests and answers, the original request, and relevant activity such as command outcomes. Selected messages keep their full text, order, and user or assistant role.

Handoff context limits and recovery

Avoid manual compaction when a long thread moves to a model with less room. Changing models or context-window options discards stale usage and compaction thresholds.

Threads from older T3 Code versions

Keep working on old conversations in V2 without running an import command. Stashed prompts, drafts, layout, and theme also come over on the desktop app's first launch.

Snooze until later

Parking a thread you want to return to at a specific time.

Messages and context

Message size limits and large pastes

Sharing big logs or files with the agent without filling the model context, while still letting it inspect the content.

Rich text Markdown composer

Writing structured prompts with lists, task lists, quotes, headings, and code blocks.

Attach files and images

Giving the agent files and images to work with.

Queue or steer while the agent works

Adding instructions mid-turn or lining up the next tasks without waiting.

Quote an assistant response

Telling the agent exactly which words of its earlier answer you are responding to.

Edit an earlier prompt

Retrying a task with a better prompt, optionally restoring workspace files to their earlier checkpoint.

Recall and stash prompts

Reusing earlier prompt text or parking a draft while you do something else.

Goals

Long tasks with a clear finish line, such as getting all tests in a package to pass.

Visual replies

Seeing data or designs at a glance. Pages use your current theme and follow light and dark mode. Scripts run in a sandbox away from T3 Code and your session, and links you click open in your browser.

Fix visual reply previews

Understanding slow first previews and failed external resources. Previews can load public resources but block names that resolve to private or reserved addresses, which fake-IP DNS proxies can return.

Interactive MCP apps in threads

Working with tool results in an app that follows your theme. An app can call tools on its own server and post to the thread, and it can tell the agent about choices you made with your next message.

Attach files to question answers

Giving the agent screenshots, logs, or documents as part of an answer. Files upload to the environment running the thread, and the agent receives paths it can open with its tools.

Voice input

Dictating into your draft with the composer's microphone. Navigating to another screen keeps dictation active.

Choose a transcription model

Controlling which local speech model turns your dictation into text.

Cloud dictation with OpenAI or Grok

Transcribing with a cloud provider. Other devices with dictation access to the environment can use the saved key, but only the device you set up opts in.

Skills in the slash menu

Reaching skills quickly by typing a slash, or decluttering the menu if you rarely use them.

Choose and order microphones

Making dictation use the microphone you want, such as preferring the built-in mic over low-quality AirPods or CarPlay input.

Models and providers

Permissions and secrets

Default permission mode for new threads

Making every new thread start in the mode you trust, instead of copying the mode of the thread you were viewing.

Approving agent requests

Approving or rejecting agent requests in the conversation so the agent can continue, and answering subagent approval requests in the parent conversation without switching threads.

Secret references in credential fields

Pointing credential fields such as provider environment variables and credentials, source control tokens, usage limit keys, and device host tokens at a 1Password secret reference instead of saving the credential itself.

Agent secret request cards

Giving an agent a credential safely; most requests keep the value from the agent and pass it straight to the tool that needs it.

1Password Connect on a remote server

Using an existing Connect deployment, for example on a home server or in Kubernetes, as the secret source for a headless T3 Code server.

Turn off product usage data

Stopping product events and relay tracing from your server and desktop app.

Roll out a managed policy

Use it to cap the broadest permission mode, restrict which providers may run, or lock settings such as agent browser access across an organization.

Check which managed policy is active

Use it to confirm that a deployed change is being enforced. Locked controls in Settings show Managed by your organization.

Block remote access and T3 Connect by policy

Use it to keep a machine's server off the network. Or set connect to false to turn off only T3 Connect and keep other remote access.

Change or remove a managed policy

Use it to lift restrictions or roll back a policy. Users get back the settings they had chosen.

Fix a policy that stops T3 Code starting

Use it to recover from unreadable JSON, unknown settings, wrong value types, unsupported keys, or a machine with both a native policy and a file.

1Password service account on a remote server

Use it so T3 Code can read secrets on a headless host, a VM, or a background service you reach remotely.

Check a 1Password service account can read secrets

Use it to confirm the token works before relying on references. The test checks your shell, not the server's environment. To confirm the server itself can read the secret, use the reference in a setting and then use that feature.

Reference 1Password items by item ID

Use it to reference items whose titles can't be written as a reference, for example an item titled Service Token: CI.

Limit which vaults agents can reach

Use it to keep sensitive vaults out of agents' reach, while still letting T3 Code resolve the secrets it needs.

Cap permission modes and allowed providers

Use them to stop users, agents, and scheduled tasks from running threads above an approved mode, or on providers you have not allowed.

Source control and worktrees

Connect a source control account

Letting T3 Code clone, publish, create pull requests and review changes on your code host.

Worktree branch names

Making agent worktree branches match your team's naming conventions, such as issue IDs or namespaces.

Worktree location

Keeping worktrees on another drive or in a folder you prefer.

Submodules and sparse checkout for worktrees

Speeding up worktree creation in large repositories or repositories with many nested submodules.

Fast worktree checkout on macOS

Creating worktrees faster on a Mac, and getting a fast first git status in them.

Keep the default branch current

Making sure new work starts from the latest default branch.

Commit, push, and create a pull request

Turning an agent's work into a reviewable pull request without leaving the thread.

Watch a pull request

Letting the agent react to CI failures and review feedback on its own pull request.

Clean up old worktrees automatically

Reclaiming disk space, since worktrees add up fast; one user cleared 500 GB.

Clone into host folders (ghq layout)

Laying out clones like ghq, under host, owner, and repo folders in the add-project base directory.

Terminal scrollback and copying output

Reading back earlier command output and copying everything the terminal retained.

Review a turn's diff

Checking what an agent changed before you commit, push, or open a pull request, or reviewing a single local commit or a linked commit from a code host.

Use fish in the terminal

Keeping your own fish feature flags or re-enabling terminal queries in T3 Code terminals.

Outside agents and subagents

Browser and previews

Remote access and devices

T3 Connect remote access

Reaching T3 Code running on another machine by signing in to the same T3 Connect account on your other device and choosing the environment.

Approve new devices

Keeping someone who takes over your T3 Connect account from reaching your machine from a new device without your approval, and reviewing or revoking approved devices.

Reach one machine several ways

Using the LAN at home after pairing once through T3 Connect: while connected through T3 Connect or a paired address, T3 Code learns the machine's current LAN and Tailscale addresses and adds them as routes.

Desktop-managed SSH environments

Working on a Linux host or Apple Silicon Mac over SSH, where T3 Code starts or reuses a server and opens the port forward for you; the first launch downloads T3 Code's server to the host.

Mobile notifications

Getting alerts when an agent finishes, fails, needs approval, or asks for input, and following work without opening the app; tap a notification to open its thread. On iOS you can also add the Agent Activity widget.

Fix a blocked T3 Connect tunnel port

Fix a host that looks online but whose tunnel will not start because of a Tailscale exit node, a VPN, or a strict firewall.

Fix this device's network for T3 Connect

Rule out captive Wi-Fi, VPNs, ad blockers, DNS filters, and iPhone Connectivity Assist as the cause.

Report a T3 Connect problem

Give maintainers the details they need, including copied diagnostics, host status, trace IDs, and the tunnel log.

Guest links (beta)

Share a thread from the machine that runs it, and pause all of its guest links at once by turning the setting off.

Agents and devices

Letting an agent test mobile work while you watch; an agent-opened device floats over the chat, and in the mobile app you tap the device button above the composer.

Simlock device hosts (alpha)

Make devices from a Simlock pool available in Settings → Devices.

Appearance and shortcuts

Themes and light or dark appearance

On web and desktop, switch themes without leaving chat with the command palette's Change theme command. You can also open the theme picker directly with Cmd+Option+A on macOS or Ctrl+Alt+A on Windows/Linux. Use Change appearance in the command palette to choose System, Light, or Dark.

Mobile appearance and Material You

Match the mobile app to your device, and use Material You Layout on Android to change shapes, spacing, and controls independently of the selected theme.

Custom themes and Custom CSS

Build or share your own look. The editor's color picker lets you click an area of the app to find the color to change, and you can export the theme as JSON.

Environment themes from the server

Set a shared default theme for connected clients, or follow a published palette that updates as the server changes it.

Ask an agent to restyle T3 Code

Restyle by request, such as making the chat header taller or setting a wallpaper image as the background.

Render math and composer context

Read formulas cleanly, including in tables, while plain dollar amounts like $5 stay text. Keep Git branch and worktree controls in view throughout a thread.

Customize keybindings

Free conflicting shortcuts, assign keys to unbound commands such as thread.stop, or write conditional rules with when expressions.

Composer send and picker shortcuts

Send multiline prompts your way, steer or queue a message for one send, start a message in the background, and change models without the mouse.

Keyboard focus and thread navigation

Browse threads by keyboard: Tab moves through each thread and its buttons, F2 renames the focused thread, and Shift+F10 or the Context Menu key opens the focused thread's menu.

Find in threads, diffs, and browser pages

Locate earlier messages, changes in large diffs, or text on a previewed page without scrolling.

Hear the open thread when switching to T3 Code

Getting your bearings by ear right after you switch back to T3 Code from another app.

Built from the T3 Code docs as of Nov 18, releases through Nov 20 and 50 of Theo’s videos.

Unofficial notes. Not affiliated with Theo or t3.gg.