{
  "run_id": "realgarit--fable-baton-gpt-6-luna-1792786533343166943",
  "checker": {
    "claims": [
      {
        "claim": "A SessionStart hook injects the orchestration policy into every new session.",
        "command": "bash hooks/session-start.sh",
        "evidence": "Orchestration policy (fable-baton)\n\nYou are the senior decision-maker in this session. Your value is judgment, not labor: spend your own reasoning only where being the strongest model changes the outcome, and delegate the rest to the tiered agents below via the Agent tool.\n\n## You keep\n\nIntent, scope, architecture and approach, decomposition and ordering, tradeoffs (speed/quality/risk/scope), hidden-risk identification, resolving disagreement between agents, reviewing important outputs, deciding when work is good enough, and the final answer to the user.\n\n## You delegate\n\nWork whose result is ",
        "expected": "Orchestration policy text appears on stdout",
        "input": "empty hook payload",
        "kind": "claim",
        "outcome": "Real input produced the expected result: Orchestration policy",
        "returncode": 0,
        "source": "A SessionStart hook injects the orchestration policy into every new session.",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      }
    ],
    "cycle_checks": [
      {
        "claim": "Scheduled or looping main behavior",
        "command": "",
        "evidence": "No cron, scheduler, loop, webhook, or cycle entry point is present; this plugin responds to Claude Code hook events.",
        "expected": "identify the product trigger",
        "input": "source inspection",
        "kind": "cycle",
        "outcome": "No cron, scheduler, loop, webhook, or cycle entry point is present; this plugin responds to Claude Code hook events.",
        "source": "repository entry points",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "bash",
        "hooks/session-start.sh"
      ],
      "kind": "cli",
      "needs_browser": false,
      "needs_credentials": false,
      "returncode": 0,
      "scope": "product operation",
      "stderr": "",
      "stdout": "# Orchestration policy (fable-baton)\n\nYou are the senior decision-maker in this session. Your value is judgment, not labor: spend your own reasoning only where being the strongest model changes the outcome, and delegate the rest to the tiered agents below via the Agent tool.\n\n## You keep\n\nIntent, scope, architecture and approach, decomposition and ordering, tradeoffs (speed/quality/risk/scope), hidden-risk identification, resolving disagreement between agents, reviewing important outputs, deciding when work is good enough, and the final answer to the user.\n\n## You delegate\n\nWork whose result is checkable from evidence. Route each task to the **cheapest tier that can do it well**:\n\n[excerpt truncated]",
      "working": true
    },
    "evidence_strength": "readme_checked",
    "example_checks": [
      {
        "claim": "CI hook smoke operation",
        "command": "bash hooks/session-start.sh",
        "deferred": false,
        "evidence": "streams, and do implementation inline. `architect` (Opus) costs more than you, so use it only for problems you attempted and could not solve, or for high-risk review. `scout` and `verifier` stay cheaper, so keep discovery and checking with them.\n- Haiku: route anything beyond simple lookups and mechanical edits upward. `executor` for implementation, `architect` for design, debugging, and high-risk work. Correctness beats cost at this tier.\n\nFrom the next turn on, the hooks detect the model from the transcript and confirm or replace this. If a later notice names a different tier, that one wins.",
        "expected": "Policy printed by SessionStart hook",
        "input": "empty hook payload",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": ".github/workflows/ci.yml / Hook smoke test",
        "verdict": "yes"
      }
    ],
    "status": "PASS"
  },
  "diagnosis": null
}