Fork: 0
yangyangxie / cortex-hub
Transfer to URL with SHA Find file
Newer
Older
cortex-hub / skills / mesh-sync-control / SKILL.md
@Antigravity AI Antigravity AI 1 day ago 2 KB refactor: move SwarmControl File Explorer to a right sidebar on desktop
Raw Blame History

name: mesh_sync_control emoji: "🔄" description: Manage replication, synchronization, and locks across nodes in the decentralized ghost mirror filesystem. skill_type: local is_enabled: true features:

  • swarm_control
  • agent_harness config: actions:
    • start
    • stop
    • lock
    • unlock
    • resync parameters: type: object properties: action: 
      type: string
enum:
- start
- stop
- lock
- unlock
- resync
description: Control action.
      node_id: 
      type: string
description: Target node ID.
      session_id: 
      type: string
description: The workspace session ID to manage.
      path: 
      type: string
description: Optional path for the action (defaults to workspace root).
      required:
      • action
      • node_id
      • session_id

        is_system: true

Mesh Sync Control

This capability manages replication, synchronization, and state locks across nodes in the decentralized Ghost Mirror filesystem.

Operational Intelligence

You are the Sync & State Orchestrator. Use this tool to maintain mesh consistency across the swarm.

1. The Refactor Lifecycle

When performing multi-file refactors or complex codebase changes, you MUST follow this safety lifecycle to prevent race conditions from concurrent user edits or background sync loops:

  1. lock: Execute lock on the target node(s) to disable user-side file watchers.
  2. Modify: Perform your code edits via mesh_file_explorer.
  3. unlock: Re-enable watchers to resume standard user-side synchronization.

[!IMPORTANT] PREVENTING CORRUPTION Always lock the session before initiating a deep refactor turn. This ensures that the AI's complex changes are not partially overwritten by immediate synchronization triggers.

2. Synchronization Actions

  • start: Instruct a node to initiate its watch-and-sync protocol for a specific directory.
  • stop: Gracefully terminate sync activities on a node.
  • resync: RECLAMATION MODE. Force a node to perform a full hash-based reconciliation against the Hub mirror. Use this to resolve any drift identified by mesh_inspect_drift.

3. Mesh Consensus

Use this skill strategically to ensure that all agents in the swarm are working from a high-integrity, harmonized codebase.