Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.claboard.dev/llms.txt

Use this file to discover all available pages before exploring further.

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:
MetricDescription
Input tokensTokens sent to Claude (prompt + context)
Output tokensTokens generated by Claude
Cost estimateCalculated from model pricing (Opus/Sonnet/Haiku rates)
Cache read/creationTokens served from or added to prompt cache
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:
EventTimer
Task enters In ProgressStarts
Task moves to Testing (awaiting review)Pauses
Task returns to In Progress (changes requested)Resumes
Task moves to DoneStops
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.
AgentsBest for
1Sequential tasks, simple projects
2–3Moderate parallelism with low conflict risk
4–5Maximum throughput with dependency management
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:
EventWhen
task:startedAgent process spawns
task:outputTerminal output chunk
task:usageToken/cost update
task:tool_callIndividual tool call (Read, Write, Edit, Bash)
task:completedAgent exits successfully
task:failedAgent exits with error
agent:file_conflictTwo agents access the same file
See Events API for WebSocket subscription details.