backlog
Persistent, cross-session task management for Claude Code. Tasks survive sessions so work started by one agent can be picked up by another.
Built on @backloghq/agentdb — typed schemas, auto-increment IDs, virtual filters, blob storage. Pure TypeScript, zero native dependencies.
Install
/plugin marketplace add backloghq/backlog
/plugin install backlog@backloghq-backlog
From source
git clone https://github.com/backloghq/backlog.git
cd backlog && npm install && npm run build
claude --plugin-dir /path/to/backlog
Standalone MCP server
Add to your project's .claude/settings.json:
{
"mcpServers": {
"backlog": {
"command": "node",
"args": ["/path/to/agent-teams-task-mcp/dist/index.js"],
"env": {
"TASKDATA": "/path/to/task-data"
}
}
}
}
Skills
| Skill | Description |
|---|
/backlog:tasks | Show the current backlog — pending, active, blocked, overdue tasks |
/backlog:plan | Break down a goal into tasks with dependencies, priorities, and specs |
/backlog:standup | Daily standup — done, in progress, blocked, up next |
/backlog:refine | Groom the backlog — fix vague tasks, missing priorities, broken deps, stale items |
/backlog:spec | Write a spec document for a task before implementation |
/backlog:implement | Pick up a task, read its spec, implement it, mark done |
/backlog:handoff | Prepare for next session — annotate progress, stop active tasks, summarize state |
Agent
The task-planner agent can be auto-invoked by Claude when someone needs to plan work. It reads the codebase, decomposes goals into tasks with dependencies, and writes specs for complex items.
Hooks
| Event | What it does |
|---|
SessionStart | Shows pending task count when a session begins |
TaskCreated | Syncs Claude's built-in tasks to the persistent backlog |
TaskCompleted | Marks the matching backlog task as done when Claude completes a built-in task |
SubagentStart | Auto-assigns unassigned pending tasks to the spawned agent |
Tools (MCP)
Tools for full task lifecycle management:
| Tool | Description |
|---|
task_list | Query tasks with filter syntax. Returns JSON array with all fields. |
task_count | Count tasks matching a filter. Same syntax as task_list. |
task_add | Create a new pending task. Only description required; all other fields optional. |
task_log | Record already-completed work directly in completed status. |
task_modify | Partial-update one or more tasks matching a filter. Only provided fields change. |
task_duplicate | Copy an existing task with optional field overrides. |
task_done | Mark a task as completed with end timestamp. |
task_delete | Soft-delete a task. Restorable with task_undo. Use task_purge to permanently remove. |
task_annotate | Add a timestamped note. Use task_doc_write for longer content. |
task_denotate | Remove an annotation by exact text match. |
task_start | Mark a task as actively being worked on. Visible in +ACTIVE queries. |
task_stop | Stop working on a task. Returns it to pending status. |
task_undo | Undo the most recent operation. Can be called repeatedly. |
task_info | Get full JSON details for a single task by ID or UUID. |
task_import | Bulk-create tasks from a JSON array. Atomic batch operation. |
task_purge | Permanently remove a deleted task. Irreversible. |
task_doc_write | Attach/replace a markdown document on a task (specs, notes, context). |
task_doc_read | Read the markdown document attached to a task. |
task_doc_delete | Remove a task's document. Permanent. |
task_archive | Move old completed/deleted tasks to quarterly archive segments. |
task_archive_list | List available archive segments. |
task_archive_load | Load archived tasks for read-only inspection. |
task_projects | List project names with pending/recurring tasks. |
task_tags | List tags with pending/recurring tasks. |
Filter Syntax
