backlog

backlog

Persistent, cross-session task management for Claude Code. 24 MCP tools for tasks, projects, dependencies, and docs. 7 skills for planning, standups, and handoffs. Event-sourced storage with per-project isolation.

Category
访问服务器

README

backlog

GitHub stars License: MIT CI Docs

Persistent, cross-session task management for Claude Code. Tasks survive sessions so work started by one agent can be picked up by another.

Zero external dependencies — pure TypeScript with event-sourced storage. Install and it works.

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)

24 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

status:pending                    # all pending tasks
project:backend +bug              # bugs in backend project
priority:H due.before:friday      # high priority due before friday
+OVERDUE                          # overdue tasks
+ACTIVE                           # tasks currently being worked on
+BLOCKED                          # tasks blocked by dependencies
+READY                            # actionable tasks (past scheduled date)
agent:explorer                    # tasks assigned to the explorer agent
( project:web or project:api )    # boolean with parentheses
description.contains:auth         # substring match

Supports attribute modifiers (.before, .after, .by, .has, .not, .none, .any, .startswith, .endswith), tags (+tag, -tag), virtual tags (+OVERDUE, +ACTIVE, +BLOCKED, +READY, +TAGGED, +ANNOTATED, etc.), and boolean operators (and, or).

Task Docs

Attach markdown documents (specs, context, handoff notes) to any task:

task_doc_write  id:"1"  content:"# Spec\n\nBuild the auth flow.\n"
task_doc_read   id:"1"
task_doc_delete id:"1"

Writing a doc adds a +doc tag and has_doc:yes, so agents can discover tasks with docs:

task_list filter:"+doc"
task_list filter:"has_doc:yes"

Agent Identity

Tasks support an agent field for tracking which agent owns a task:

task_add  description:"Investigate bug"  agent:"explorer"
task_list filter:"agent:explorer status:pending"

Project Isolation

Each project gets its own task data automatically. When used as a plugin, task data lives in ~/.claude/plugins/data/backlog/projects/<project-slug>/. When used standalone, set TASKDATA explicitly.

Variable Description
TASKDATA Explicit path to task data directory (overrides auto-derivation)
TASKDATA_ROOT Root directory for auto-derived per-project task data

Development

npm install
npm run build          # compile TypeScript
npm run lint           # run ESLint
npm test               # run tests
npm run test:coverage  # run tests with coverage
npm run dev            # watch mode

Community

If backlog is useful to you, consider giving it a star — it helps others find the project.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选