agent-migration

Safely rename or migrate an OpenClaw agent by updating config and naming, migrating session content, fixing session metadata, restarting, verifying, and asking separately before deleting the old agent.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "agent-migration" with this command: npx skills add kid0114/agent-migration

Agent Migration

Use this skill when the user wants to rename or migrate an OpenClaw agent safely.

Scope

This skill handles:

  • agent id rename
  • workspace rename
  • config/path updates
  • prior session content migration
  • session display metadata updates
  • restart and verification
  • separate deletion confirmation for the old agent

Defaults and boundaries

  • Confirm old id, new id, new workspace, and whether model also changes.
  • Migrate prior session content by default unless the user explicitly says not to.
  • Do not skip migration just because a session does not look active.
  • Do not hard-edit active lock files or force-rewrite a live session shell.
  • Restart is required after migration.
  • Never delete the old agent without a separate user confirmation.

Files involved

  • config: ~/.openclaw/openclaw.json
  • agent dirs: ~/.openclaw/agents/<id>/...
  • workspace: /home/yln/claw-workspace/<name>
  • session metadata such as sessions.json

Use the included files

  • references/checklist.md
  • references/cleanup.md
  • scripts/inspect_agent_migration.sh
  • scripts/copy_session_content.sh
  • scripts/verify_agent_migration.sh

Recommended commands

bash skills/agent-migration/scripts/inspect_agent_migration.sh <old-id> <new-id>
bash skills/agent-migration/scripts/copy_session_content.sh <old-id> <new-id>
bash skills/agent-migration/scripts/verify_agent_migration.sh <old-id> <new-id>

Guardrails

  • Keep config, workspace, and naming changes consistent.
  • Update session display-layer metadata as part of the migration.
  • Verify the new agent before offering deletion of the old one.
  • Use references/cleanup.md only after the user separately confirms deletion.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Agent Builder Plus

Build high-performing OpenClaw agents end-to-end with comprehensive safety features. Use when you want to design a new agent (persona + operating rules) and...

Registry SourceRecently Updated
4600Profile unavailable
Automation

Agent Memory Persistent Workspace Memory System

Stop your AI agent from forgetting everything between sessions. Three-tier memory architecture (long-term owner namespace / daily logs / session handoff), cr...

Registry SourceRecently Updated
3050Profile unavailable
Security

SPIRIT State Sync

State Preservation & Identity Resurrection Infrastructure Tool (SPIRIT). Preserves AI agent identity, memory, and projects to a private Git repository. NEW:...

Registry SourceRecently Updated
7520Profile unavailable
Automation

Mobayilo Voice (Beta)

Place outbound phone calls via Mobayilo with safe defaults (preview mode by default) and explicit live execution.

Registry SourceRecently Updated
3890Profile unavailable