Build with your Claude plan

A new chat runs on the free Flockbay demo model, under an amber Low-quality model warning. Press "Use your own AI" on that warning, then "Sign in with Claude". Or open the model menu, the pill beside Send, and pick the Claude tab. Connectors, in the Flockbay menu, has the same Claude row.

The choice belongs to the chat, like any model. Flockbay starts Claude Code for each message and resumes the same session, so the conversation carries on across messages and across restarts of the app.

Claude Pro, Max, Team or Enterprise. The free Claude plan does not include Claude Code, so it cannot build here: the card says so, names the plans that can, and you upgrade on Anthropic’s site.

Two more refusals are Anthropic’s, not Flockbay’s: a country where Claude Code is not offered, and a Claude organization whose admin turned Claude Code off. The card says which.

Flockbay asks Claude Code one thing about your account, its own auth status: whether you are signed in, as whom, and on which plan. The card shows that account so you can see which one is in use.

It never reads or writes Claude Code’s own files: not your sign-in, not your settings, not your history. It does not modify or wrap the Claude Code program, and it sets no API key and no proxy for it, so your usage goes to Anthropic on your own plan.

Flockbay’s tools and instructions are handed to Claude Code for each session, on its command line. Your own Claude settings and MCP servers load beside them and are not edited.

What Flockbay counts is that Claude was picked, signed in and used. Those are events: no prompt, no reply, no file name, no account and no plan is in them.

One sentence does go to Flockbay’s server: the first sentence of a new game, which is read once to tell whether it is a 2D or a 3D game.

Flockbay’s own tools run without an approval card, and so do file edits inside the project you have open. Any other shell command asks first, on a card in the chat with Allow and Deny.

A question from Claude arrives as a question card, the same one Flockbay’s own questions use.

The model menu lists the models Claude Code offers your account, under their real names, with Default first. Under the list, Effort offers the levels Claude Code gives for the model you picked; a model with no levels shows no control. Both are remembered per chat.

Claude Code updates with Flockbay. Each release carries the Claude Code it was built with, and Flockbay never updates its copy any other way, so there is no Update button for it.

A copy you installed yourself is not Flockbay’s, and it keeps updating the way it always did. Both copies read the same sign-in and settings.

Stop, where Send is while a turn runs, ends the turn and the Claude Code process behind it.

To stop using Claude in a chat, pick another model in the model menu. Flockbay has no sign-out for Claude, because the sign-in is Claude Code’s own: sign out from Claude Code itself.

A turn on your own AI may run for up to twelve hours, and a question card waits as long as you do.

It is Windows only today. The Mac build does not run Claude Code in the app yet; there, connect Claude Code as your own agent over MCP.

On a PC whose organization blocks programs it does not know, Windows can refuse to start Claude Code. The card says "Windows won’t start Claude Code on this PC", and nothing in Flockbay can change that.