claude-agentboard 0.2.0

Bidirectional kanban board for AI agents and humans

Agentboard

A bidirectional kanban board for AI agents and humans. Both sides read and write the same .agentboard/board.json file, with a live web UI that syncs in real-time.

Install

pip install agentboard

Quick start

# Initialize a board in your project
cd your-project
agentboard init

# Open the web UI
agentboard

How it works

• The agent reads and writes .agentboard/board.json directly via the filesystem
• The web server polls the file every second and pushes changes to the browser via SSE
• User changes in the UI are posted back to the server, which writes to the same file
• No database, no external services, just a JSON file

CLI Commands

Command	Description
agentboard	Start the web UI (default)
agentboard init	Create .agentboard/board.json in the current directory
agentboard status	Print task counts per column
agentboard add "title"	Add a task (options: --column, --tag, --priority)

Claude Code Integration

Copy skill/SKILL.md to your Claude Code skills directory:

mkdir -p ~/.claude/skills/agentboard
cp skill/SKILL.md ~/.claude/skills/agentboard/SKILL.md

The skill teaches the agent to read the board before writing, move tasks through columns as it works, and respect user-added tasks.

Board Schema

Tasks have these fields:

• id - Unique identifier (e.g., t_a1b2c3d4)
• title - Short imperative description
• description - Optional longer description
• tag - One of: feature, bug, chore, docs, test, design
• priority - One of: high, medium, low, or null
• column - One of: backlog, todo, in_progress, done
• created_by - Either agent or user

Web UI Features

• Drag and drop cards between columns
• Double-click cards to edit title, description, tag, and priority
• Add tasks via the input at the bottom of the Backlog column
• Live updates when the agent modifies the board file
• Connection status indicator

License

MIT