resume

Resume interrupted OpenCode Swarm sessions from an approved plan.md.

437|45|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/ZaxbyHub/opencode-swarm --skill resume-zaxbyhub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: resume
Source: https://github.com/ZaxbyHub/opencode-swarm/tree/main/.opencode/skills/resume
Command: npx skills add https://github.com/ZaxbyHub/opencode-swarm --skill resume-zaxbyhub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When an AI coding session using OpenCode Swarm is interrupted, resuming work often leads to lost context, stale git branches and worktree directories, or conflicting swarm configuration errors that require manual cleanup and risk losing progress.

Core Features & Use Cases

  • Safe Plan Resumption: Automatically picks up where you left off on an existing approved .swarm/plan.md without redoing prior work.
  • Stale State Cleanup: Prunes orphaned .swarm-worktrees/ lane directories and swarm-lane/* git branches left over from prior sessions to avoid conflicts.
  • Cross-Swarm Reconciliation: Handles context cleanup when switching between local and cloud swarm environments to eliminate identity and stale cache conflicts.
  • Use Case: If you are mid-way through a multi-phase coding project with the Swarm architect and your session is interrupted, use this skill to resume work seamlessly without manual cleanup of orphaned resources.

Quick Start

Use the resume skill to continue your interrupted OpenCode Swarm coding project from its last approved task.

Frequently Asked Questions about resume

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

FAQPage Schema
How do I resume an interrupted OpenCode Swarm coding plan without losing progress?

To resume an interrupted OpenCode Swarm coding plan, you can use session recovery to continue from the last approved task in your .swarm/plan.md file automatically. This avoids rework by safely picking up exactly where you left off.

What is the best way to clean up orphaned worktree directories and git branches after a session crash?

The best way to clean up orphaned worktree directories and git branches is to use automated session recovery tools that prune stale swarm-lane/* branches and .swarm-worktrees/ lane directories left from prior sessions.

Does session recovery work when switching between local and cloud swarm environments mid-project?

Yes, session recovery works when switching between local and cloud swarm environments. It handles cross-swarm context reconciliation to purge stale caches and eliminate identity conflicts during the transition.

How does context reconciliation handle stale state in an OpenCode Swarm environment?

Context reconciliation handles stale state by automatically purging outdated cache and configuration data when you switch swarm environments. This ensures your active .swarm/plan.md file continues execution without conflicting identity errors.

Do I need an existing .swarm/plan.md file to use automated session recovery?

Yes, you need an active .swarm/plan.md file to use automated session recovery. The resumption process relies on an existing approved plan to automatically continue from the last known task without redoing prior work.

Why does my coding session recovery fail due to conflicting swarm configuration errors?

Coding session recovery fails due to conflicting swarm configuration errors caused by stale git branches and orphaned worktree directories from prior sessions. Automated cleanup of these resources is required to eliminate the conflicts.