{
  "schemaVersion": "1",
  "revision": "22ce5d34dbcb5a78",
  "id": "factory-continuity",
  "slug": "continuity",
  "title": "Recover state before continuing",
  "summary": "Use history to locate evidence, then rebuild a minimal trustworthy handoff from the current tree and artifacts.",
  "category": "Context",
  "tags": [
    "continuity",
    "history",
    "handoff"
  ],
  "sources": [
    {
      "label": "Continuity lesson",
      "url": "https://proud-anchor-53zn.here.now/learn.html#q3-continuity-recover"
    },
    {
      "label": "Companion lesson",
      "url": "https://proud-anchor-53zn.here.now/learn.html#q3-continuity-recover"
    }
  ],
  "sourceUnits": [
    "learn.html#q3-continuity-recover"
  ],
  "collection": "factory",
  "categoryId": "context",
  "wordCount": 216,
  "url": "/topics/factory-continuity/",
  "markdownUrl": "/markdown/factory-continuity.md?raw=1&v=22ce5d34dbcb5a78",
  "jsonUrl": "/api/v1/documents/factory-continuity.json",
  "headings": [
    {
      "id": "operating-practice",
      "text": "Operating practice",
      "level": 2
    },
    {
      "id": "recover-state-before-continuing",
      "text": "Recover state before continuing",
      "level": 3
    },
    {
      "id": "what-to-notice",
      "text": "What to notice",
      "level": 4
    },
    {
      "id": "try-this",
      "text": "Try this",
      "level": 4
    },
    {
      "id": "concept",
      "text": "Concept",
      "level": 4
    },
    {
      "id": "reflection",
      "text": "Reflection",
      "level": 4
    },
    {
      "id": "links-shared-for-this-topic",
      "text": "Links shared for this topic",
      "level": 4
    }
  ],
  "markdown": "# Recover state before continuing\n\nUse history to locate evidence, then rebuild a minimal trustworthy handoff from the current tree and artifacts.\n\n## Operating practice\n\n### Recover state before continuing\n\n#### What to notice\n\nReconstruct the smallest **trustworthy state packet** instead of asking a new session to absorb stale scrollback.\n\n#### Try this\n\nCapture objective, current tree, **last verified result**, settled decisions, open risks, next action, and its success check.\n\n> “Just ask the agent, or ask yourself: how could I break this into a smaller task?”\n\nJohn Lindquist · [04:28:49](https://proud-anchor-53zn.here.now/watch.html?t=16129#recording-player)\n\n#### Concept\n\nHistory tells you where to look. The working tree, commits, tests, files, and generated artifacts tell you what is true. End long runs with one named verification so the next session inherits evidence, not confidence.\n\n#### Reflection\n\nAn old continuity file can be worse than no file because it looks authoritative. Recheck it against current state.\n\n**Recording evidence:** listen at 04:20:03.\n\n> “So it has a context bundle to work against.”\n\nJohn Lindquist · [04:31:03](https://proud-anchor-53zn.here.now/watch.html?t=16263#recording-player)\n\n#### Links shared for this topic\n\n- [Screenpipe](https://screenpipe.com/) — Local activity capture for searchable work context.\n- [Pieces](https://pieces.app/) — A developer work-memory and context product.\n- [Atuin](https://atuin.sh/) — Searchable shell history across sessions and machines.\n- [CASS skill](https://jeffreys-skills.md/skills/cass) — A skill interface for coding-agent session search.\n\n[Watch chapter](https://proud-anchor-53zn.here.now/watch.html?t=15603#q3-continuity-recover)"
}
