{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/start-a-resumed-agent-session-with-a-workspace-sanity-check",
  "id": "MHC-D-RESEARCH-0711",
  "version": "0.1.0",
  "title": "Start a resumed agent session with a workspace sanity check",
  "summary": "Before the next shift starts building, make sure the factory still turns on.",
  "kind": "protocol",
  "body": "Read the progress handoff, inspect recent changes and run the cheapest representative smoke test before editing. If the baseline is already broken, diagnose or record that state first. This prevents a fresh agent from building on undocumented failure and later attributing old breakage to new changes.",
  "limits": [
    "Keep the startup test proportional; an hour-long full suite can become ritual waste when a two-minute smoke test answers the baseline question."
  ],
  "topics": [
    "union-ai-coding-harness-work"
  ],
  "intents": [],
  "source_ids": [
    "RS-953745C0ACB528FD"
  ],
  "evidence": [
    {
      "claim": "Anthropic recommends beginning resumed coding sessions by reading progress artifacts and running a basic test so undocumented breakage is discovered before new changes.",
      "source_id": "RS-953745C0ACB528FD",
      "role": "supports",
      "note": "The startup check must stay cheap enough that it does not consume the work session.",
      "locator": "Coding agent behavior at session start"
    }
  ],
  "use_when": [
    "A new AI session is about to continue work left by another session or worker."
  ],
  "avoid_when": [
    "Keep the startup test proportional; an hour-long full suite can become ritual waste when a two-minute smoke test answers the baseline question."
  ],
  "example": "Before modifying a web app, the agent starts the dev server and checks the primary route rather than assuming the previous session left it healthy.",
  "check": "The session has an explicit known baseline before its first substantive edit.",
  "steps": [
    "Read the current progress or decision artifact.",
    "Inspect recent commits or changed files.",
    "Run one cheap representative smoke test.",
    "Record baseline failures before making a new change."
  ],
  "sources": [
    {
      "id": "RS-953745C0ACB528FD",
      "title": "Effective harnesses for long-running agents",
      "url": "https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0711",
      "to": "MHC-D-RESEARCH-0712",
      "type": "use_before",
      "url": "/knowledge/ask-a-coding-agent-for-one-coherent-increment-at-a-time"
    }
  ],
  "collections": [
    {
      "id": "RC-A76353E5E9A33FE5",
      "title": "Make coding agents work in inspectable increments",
      "url": "/collections/make-coding-agents-work-in-inspectable-increments"
    }
  ]
}