Agents
Yard works with three coding agents: Claude Code, Codex and Cursor. They do the writing in chats and the building in projects.
Your own account
There is no shared organization key. Each person signs in to the agents they use, and every message runs with the account of the person who sent it. If you send a message without a connected agent, the chat shows Connect an agent to chat with the same sign-in options, and keeps your message until you are connected.
Connect an agent
Go to Account → Agents and choose Add agent. For each agent you can Sign in with your account or Use an API key.
Signing in runs the agent's own sign-in on one of your organization's runners, so a runner must be online:
- Choose Open the sign-in page and approve Yard there.
- Claude Code and Cursor show a code: paste it into Yard and choose Submit.
- Codex uses a device code instead: copy the code Yard shows, enter it on the sign-in page, and Yard notices once you approve it.
If your connection drops for a moment, the sign-in waits for you. If it takes too long, choose Start again.
An API key is stored encrypted and never shown again. A key account is marked "API key" and has Replace key instead of Sign in again.
You can connect more than one account of the same agent; Use this picks the one that runs your work. Its status reads "Not signed in", "Sign-in expired" or, for a key, "Key rejected" when it needs your attention. Remove forgets it.
Models and effort
Pick the agent and model from the model button in the chat's composer or in the Create spec dialog:
| Agent | Models | Effort |
|---|---|---|
| Claude Code | Fable, Opus, Sonnet, Haiku | low, medium, high |
| Codex | GPT-5 Codex, GPT-5 | low, medium, high |
| Cursor | Auto | none |
When a person has not picked one, the workspace's default applies (Workspace settings → General → Agents), then the organization's (Settings → Models, set by admins). When none of those names a model, the agent's default model (in bold) is used. The model button always names the model a message runs with.
Agents run only in containers
An agent never runs on Yard's servers or directly on the runner machine. It runs inside a container on the workspace's runner. Your sign-in is handed to the container for one turn and removed when the turn ends.
There are two kinds of agent:
- The workspace agent answers the workspace chat. It works in the workspace's own container, in the workspace's files: it can write notes that appear on the canvas, look at uploads, and read the repositories, which are read-only reference copies there. It does not change code; code changes happen in a project.
- A project agent belongs to one project and works in that project's
container. It writes the spec, then changes code in the project's
worktrees and commits it. It never pushes or opens pull requests: people
do that from Yard after reviewing the work, or Yard does it when the
agent finishes, if the workspace's
automation is on. It can read from GitHub
(
git fetch,gh pr view) to bring in the base branch, which is how Resolve with the agent fixes a pull request that conflicts. See repositories and git.
Agents can take screenshots of what they build with a headless browser; pictures they save land on the canvas.
Both kinds put things on their canvas in a tidy way: a repository file goes on as a linked, read-only code block rather than a copy, a note opens sized for what it holds (wide when it has pictures or tables), and an agent can gather what belongs together into a titled group, one per topic.
What an agent is told
With every message, the agent gets:
- where it is, which repositories are there and which of them it may change;
- the blocks you selected (with the text of notes) or, with nothing selected, only the pinned blocks (in a project: a list of everything linked to it);
- pinned blocks and the lines you highlighted in a repository (repositories and git);
- files you attached;
- the recent conversation and your message.
A project agent also gets the instructions and spec.md. Highlights set
priority, but the agent can still read the whole repository.
Because each message carries its own context, a conversation can continue with another person's account, another agent, or on another runner.
When an account runs out of usage
When an agent account hits its AI usage limit, its turns wait instead of failing, in every chat that uses it; other people's accounts carry on. They start again by themselves when the provider said the limit resets, or with Resume in the chat. See chat.
When an agent needs you
An agent can end its reply with questions, shown as a form in the chat, or with an offer to connect something that is missing. See chat.