long-running-tasks

Coordinate multi-step tasks with JSON-based progress files across sessions.

2|Updated Jan 16, 2026

Search Tags:#long-running #resume #ai-agent #multi-session #progress-tracking #state-persistence

Ready to run

npx skills add https://github.com/MysMon/Spec-Workflow-Toolkit --skill long-running-tasks

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: long-running-tasks
Source: https://github.com/MysMon/Spec-Workflow-Toolkit/tree/main/skills/workflows/long-running-tasks
Command: npx skills add https://github.com/MysMon/Spec-Workflow-Toolkit --skill long-running-tasks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Patterns and practices for autonomous, multi-step tasks that may span sessions or exceed a single context window, enabling state persistence and reliable resumption.

Core Features & Use Cases

Initializer + Coding Agent Pattern to split initialization from iterative work and document resumption context.
JSON-based state persistence and workspace isolation to track progress across sessions.
TodoWrite-style progress management to enforce a single active feature and transparent progress tracking.
Support for background/foreground subagents and resumable tasks to recover from interruptions.

Quick Start

Invoke the long-running-tasks skill to coordinate a multi-step job and persist progress across sessions.

Frequently Asked Questions about long-running-tasks

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

FAQPage Schema

How do I resume a long-running task after a context window limit is exceeded?▼

Long-running task resumption uses JSON-based state persistence files and a session-resume mechanism to recover multi-step workflows that exceed a single context window. It reloads prior progress to continue autonomous execution seamlessly across sessions.

What is the best way to track progress for multi-step workflows across sessions?▼

Multi-step workflow progress tracking uses TodoWrite-style task management and JSON state files to enforce a single active feature. This ensures transparent, persistent state monitoring across multiple sessions for complex, autonomous jobs.

How does the Initializer and Coding Agent pattern work for complex refactoring tasks?▼

The Initializer and Coding Agent pattern splits complex refactoring tasks by separating initialization from iterative work. It documents resumption context, enabling autonomous agents to execute and persist multi-step migrations reliably.

Can I recover an interrupted multi-session migration without losing state?▼

Interrupted multi-session migrations recover without losing state through JSON-based workspace isolation and persistent progress files. The resumable task mechanism restores the exact workflow state, preventing data loss during unexpected interruptions.

Does this approach support background and foreground subagents for multi-step jobs?▼

Yes, multi-step job coordination supports both background and foreground subagents. It uses persistent state files to manage these subagents, enabling reliable recovery and resumption of resumable tasks after interruptions.

When should I use state persistence for autonomous AI agent workflows?▼

State persistence is needed for autonomous AI agent workflows that exceed a single context window or span sessions. It enables reliable resumption and progress tracking for complex refactoring and migrations that require multi-session execution.