{
  "schema_version": "newruntime-agent-readable-v0.1",
  "type": "disappearing_action",
  "slug": "manual-context-handoff",
  "title": "Manual context handoff between AI clients",
  "description": "The ritual of retelling one AI client what another already understood becomes optional when context moves into a shared layer.",
  "status": "published",
  "human_ritual": "Copy architecture notes, task state, constraints, and decisions between Claude, Codex, Cursor, chat, and docs.",
  "old_cost": "Repeated context switching, stale memory, contradictory assumptions, and lost provenance.",
  "replacement_pattern": "Governed shared context layer that multiple AI clients can read with explicit provenance and access rules.",
  "adoption_status": "challenged",
  "where_old_interface_wins": "Manual handoff is still safer when context contains sensitive data, unclear ownership, or unreviewed agent memories.",
  "related_shift": "shared-context-infrastructure",
  "proof_projects": [
    "verifiable-ai-coding-workflow"
  ],
  "related_posts": [
    "unabyss-shared-context-layer",
    "ghostwriter-agent-memory-poisoning"
  ],
  "topics": [
    "context-engineering",
    "agent-memory"
  ],
  "source_urls": [
    "https://unabyss.com/"
  ],
  "featured": true,
  "routes": {
    "html": "https://newruntime.com/graveyard/manual-context-handoff/",
    "markdown": "https://newruntime.com/graveyard/manual-context-handoff.md",
    "json": "https://newruntime.com/graveyard/manual-context-handoff.json"
  },
  "source_format": "markdown"
}