successor-handoff

Spawn successor agents to maintain context continuity in long-running workflows.

1|Updated Apr 17, 2026

Search Tags:#context management #workflow orchestration #agent handoff #autonomous workflows #file-first

Ready to run

npx skills add https://github.com/wan-huiyan/context-baton --skill successor-handoff

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: successor-handoff
Source: https://github.com/wan-huiyan/context-baton/tree/main/plugins/successor-handoff
Command: npx skills add https://github.com/wan-huiyan/context-baton --skill successor-handoff

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of orchestrating long-running autonomous workflows where a single Claude context window cannot hold the full run, by providing mid-run agent-to-agent handoff capabilities.

Core Features & Use Cases

Mid-Run Handoff: Spawns new successor agents when context pressure rises, maintaining continuity without human intervention.
File-First Subagents: Leans on disk-based memory to manage subagent contexts efficiently.
Orchestrator: Parent orchestrator remains lean by reading only status files, minimizing the risk of context overflow.
Use Case: Ideal for overnight research, multi-hour experiments, and long jobs requiring a continuous agent without a human present.

Quick Start

Set up your workflow using the successor-handoff skill. Ensure all tracks are initialized and ready for autonomous execution.

Frequently Asked Questions about successor-handoff

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

FAQPage Schema

How do I maintain context continuity for long-running autonomous workflows that exceed a single context window?▼

Mid-run agent handoff maintains context continuity by spawning successor agents when context pressure rises. It uses file-based memory and a lean parent orchestrator that reads only status files, ensuring long-running autonomous workflows continue seamlessly without human intervention.

What is file-first subagent management for workflow orchestration?▼

File-first subagent management stores subagent contexts on disk rather than in memory. This approach keeps the parent orchestrator lean by reading only status files, enabling dynamic successor dispatch for workflows exceeding a single context window.

How do I set up autonomous agent handoffs for overnight research jobs?▼

Set up autonomous agent handoffs by initializing workflow tracks for autonomous execution using the successor-handoff mechanism. Configure file-based memory and a lean parent orchestrator to dynamically spawn successor agents as context pressure rises during overnight research.

Can I use a parent orchestrator to manage subagent contexts without context overflow?▼

Yes, a parent orchestrator can manage subagent contexts without overflow by remaining lean and reading only status files from disk-based memory. This minimizes context usage while dynamically dispatching successor agents to handle the workload.

When do I need dynamic successor dispatch in autonomous workflows?▼

Dynamic successor dispatch is needed when an autonomous workflow exceeds a single Claude context window. It is ideal for multi-hour experiments or overnight research requiring a continuous agent presence without human intervention to reset context.

Does workflow orchestration with mid-run handoffs require human intervention?▼

No, mid-run handoffs are designed for autonomous workflows operating without human presence. By automatically spawning successor agents when context pressure rises, the workflow maintains continuity for long-running jobs like overnight research independently.