skills.rest
marcus
marcusCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

claude-code-tasks

Automate Claude Code Todo system workflows via hooks, MCP tools, and CLI streaming.

3|1|Updated Dec 23, 2025
Search Tags:#subagents#mcp#todo#agent-sdk#claude-code#task-management#automate
One-click install
npx skills add https://github.com/marcus/marcus-skills --skill claude-code-tasks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code-tasks
Source: https://github.com/marcus/marcus-skills/tree/main/skills/claude-code-tasks
Command: npx skills add https://github.com/marcus/marcus-skills --skill claude-code-tasks

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Programmatic control of Claude Code's task/todo system to automate and orchestrate cross-agent workflows.

Core Features & Use Cases

  • Monitor and react to TodoWrite updates via the Agent SDK.
  • Implement hooks (PostToolUse, TaskCompleted) and MCP-based tools to enforce governance and integrate external systems.
  • Orchestrate complex workflows using subagents, references to patterns, and CLI headless streaming.

Quick Start

Design a simple Todo workflow in Claude Code and use TodoWrite updates to drive automation.

Frequently Asked Questions about claude-code-tasks

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Claude Code TodoWrite updates programmatically?▼

You can automate Claude Code TodoWrite updates by using scripts to apply real-time monitoring and event-driven hooks. This enables programmatic control over the task system to orchestrate cross-agent workflows.

Can I use hooks to trigger external systems when a Claude Code task completes?▼

Yes, you can implement PostToolUse and TaskCompleted hooks to trigger external systems. These event-driven hooks enforce governance and integrate outside systems directly into the task workflow.

What is the best way to orchestrate subagents in multi-step Claude Code workflows?▼

The best way to orchestrate subagents in multi-step workflows is by using the Agent SDK to monitor TodoWrite updates. You can combine this with CLI headless streaming and custom MCP tools for complex automation.

Does the Claude Code Agent SDK support building custom MCP tools for task management?▼

Yes, the Agent SDK supports building custom MCP tools for task management. You can use these MCP-based tools alongside hook events to satisfy streaming input support and automate governance.

How does CLI headless streaming work with Claude Code task automation?▼

CLI headless streaming works by allowing scripts to programmatically stream input and monitor TodoWrite updates without a user interface. It satisfies real-time monitoring requirements across multi-step subagent workflows.

Related Skills

Explore More Software Engineering Skills→
KjdraganKjdragan
1

coding-agent

Control coding agents programmatically via PTY sessions across Codex, Claude Code, OpenCode, and Pi.

Community
Advanced
compozycompozy
182

combined

Configure MCP server connectivity and session lifecycle hooks via YAML frontmatter.

Official
Basic
nanorepublicananorepublica
61

Global Tech Stack

Validate code against centralized global tech stack standards.

Community
Basic
ZaibunisZaibunis

spec-kit-agent-orchestrator

Generate workflow prompts and scripts for multi-agent orchestration using Speckit methodology.

Community
Advanced