GitHub connects the work to the evidence. An agent can start when an issue opens or a pull request merges, read either one, and write back an issue or a comment.
Connect
GitHub connects through a GitHub App install, not an OAuth consent screen. Clicking Connect sends you to GitHub’s install app screen.
Start the install
Click Connect on the GitHub card. GitHub’s install app screen opens.
Pick the account and the repositories
That screen asks which account or organisation to install Squad on, and which repositories it may access: all of them, or a list you choose.
What it brings in
Nothing from GitHub becomes a signal. Issues and pull requests are things an agent reads and writes on demand. They don’t enter the evidence pipeline.
Triggers
- Issue opened. An issue is opened in an installed repository.
- Pull request merged. A pull request is merged in an installed repository.
Both fire across every repository in the installation. Closed issues, opened pull requests and review comments are not triggers.
In a triggered run each one defaults to the issue or pull request that started the run, so the agent doesn’t have to guess an ID. Both act on your repositories, so they are opt-in per agent and carry the Outbound badge in the agent builder.
A worked example
Build an agent triggered on Issue opened. It reads the issue, checks the description against recent signals to see whether customers have hit the same thing, and comments with what it found: how many customers, how recently, and which insight it belongs to. Engineering gets the demand context on the issue itself, before anyone picks it up.
Limits
Squad reads issues and pull requests. It does not read code, files, diffs or commits. The two triggers are the only GitHub events available. Repository access is set in the GitHub install, not in Squad. 
