Skip to main content
When a task moves to In Progress, Claude Board spawns a Claude Code CLI process on your local machine. This is the “agent” — it reads your codebase, writes files, runs commands, and commits code.

​
How Agents Spawn

Task enters In Progress

The server builds a prompt from the task description, project context snippets, prompt template, role, and any file attachments.

Branch created

If git automation is enabled, a feature branch is created from the base branch (e.g., feature/CB-101-add-auth).

CLI process starts

Claude Board runs claude with --no-input and the configured permission mode. The working directory is set to the project’s configured path.

Streaming begins

All output is captured and streamed to connected clients via WebSocket. Logs are persisted to the database for session replay.

Agent completes

When the CLI exits, the task moves to Testing automatically. If auto-test is enabled, tests run before the transition.

​
Token Tracking

Claude Board tracks token usage per task in real-time: Usage updates are emitted via the task:usage WebSocket event and visible on the task card.

​
Smart Timer

The task timer measures active agent time accurately:
The smart timer gives you an accurate picture of how long Claude actually spent coding, excluding review wait time.

​
Concurrency

Run up to 5 agents simultaneously. The auto-queue feature lets you set a concurrency limit per project.
Running multiple agents on the same project can cause file conflicts. Use task dependencies to coordinate which files each agent touches. The Live view detects conflicts in real-time.

​
Agent Lifecycle Events

Each agent emits events that you can monitor: See Events API for WebSocket subscription details.