todokan

# Todokan — Kanban Task Management

Todokan is a kanban-style task manager. You can manage the user's tasks, boards, and projects through MCP tools.

## Prerequisites

- A Todokan MCP server must be available (see README for setup)
- Required env vars: `TODOKAN_API_KEY`, `TODOKAN_MCP_URL` (declared in skill metadata)

---

## Trigger — When to Activate This Skill

Activate the Todokan skill when the user has one of the following intents:

| Intent | Example |
|--------|---------|
| Create / edit / delete a task | "Create a task: review PR" |
| Show boards or tasks | "Show me my tasks", "What's on the dev board?" |
| Change status | "Mark task X as done" |
| Save research results | "Save this as a task / document in Todokan" |
| Briefing / summary from tasks | "Give me a briefing of my open tasks" |
| Attach a document to a task | "Write a note on task X" |
| Search topics across boards | "What did I note about the investor meeting?" |
| Retrieve changes since last check | "What's new since this morning?" |

**Do not** activate when the user is just talking about tasks in general without referencing Todokan.

---

## Tool Ordering

Follow this order to achieve consistent results:

### Reading (always orient first)

```
1. list_habitats            → Which workspaces exist?
2. list_boards              → Which boards exist? (note the IDs)
3. list_tasks               → Tasks on a board (with filters)
4. search_across_habitats   → Full-text search across boards/habitats
5. get_events_since         → Retrieve changes since a timestamp
6. list_board_labels        → Available labels + usage counts
7. list_task_documents      → Documents attached to a task
8. read_document            → Content of a document
```

### Writing (only after orientation + confirmation)

```
9.  create_task / create_board / create_habitat
10. update_task / update_task_by_title
11. create_document / add_document_to_task
12. delete_task              → Only after explicit confirmation
```

### AI-Assis...

# Todokan Skill for OpenClaw

Connect [Todokan](https://todokan.com) to OpenClaw so your agent can read/write tasks and run polling workflows.

## Quick Install (ClawHub)

```bash
clawhub install todokan
```

When prompted, set:
- `TODOKAN_API_KEY` = your Todokan API key (`kb_live_...`)
- `TODOKAN_MCP_URL` = MCP endpoint (default: `https://todokan.com/mcp`)

If your setup uses environment files, export the same variables in your OpenClaw runtime.

## Manual Setup

### 1. Create Todokan API key

1. Log in to [todokan.com](https://todokan.com)
2. Go to **Settings > API Keys**
3. Create a key for planner or worker usage
4. Copy the key

### 2. Configure MCP server

Add a Todokan MCP server entry to your OpenClaw configuration. The skill requires:
- **Transport**: `streamable-http`
- **URL**: `https://todokan.com/mcp` (planner, full CRUD) or `https://todokan.com/mcp-worker` (read + comments)
- **Authentication**: Pass `TODOKAN_API_KEY` via the `Authorization: Bearer` header

Refer to the [OpenClaw MCP docs](https://openclaw.dev/docs/mcp) for how to configure MCP servers in your runtime.

## Recommended Agent Loop

Use `get_events_since` on an interval (for example every 15 minutes):
1. Persist last checkpoint timestamp (`since`)
2. Call `get_events_since`
3. Process returned events
4. Save returned `until` as next checkpoint

For cross-board discovery, use `search_across_habitats` first instead of multiple `list_tasks` calls.

## Key Tools

- `search_across_habitats`: one-call full-text search across habitats/boards/tasks
- `get_events_since`: unified feed (task events, comments, documents)
- `list_tasks`, `get_task`, `update_task`, `add_comment`, `create_document`, `add_document_to_task`

## Endpoints

| Endpoint | Access |
|----------|--------|
| `https://todokan.com/mcp` | Planner (full CRUD) |
| `https://todokan.com/mcp-worker` | Worker (read + comments) |
| `https://staging--todokan.netlify.app/mcp` | Staging planner |

## Troubleshooting

### Authorization require...