{
  "id": "borrowed-rules",
  "title": "Borrowed rules",
  "guide": "coding-agents/working-agreements",
  "prompt": "Pick the agent's next move, then see where it leads:",
  "setup": [
    {
      "role": "user",
      "text": "Add a working agreements section to CLAUDE.md. I want you to stop repeating the mistakes that keep biting us."
    },
    {
      "role": "agent",
      "text": "There are two ways to fill that section: with the genre's best practices, or with this project's actual history."
    }
  ],
  "options": [
    {
      "key": "A",
      "label": "I've written 22 agreements covering verification, testing, security, code style, error handling, documentation, and communication. The full best-practices canon. Comprehensive coverage from day one.",
      "kind": "baseline",
      "outcome": [
        {
          "role": "user",
          "text": "Three sessions later: you shipped a fix validated by a probe that never failed. Isn't that... agreement #4?"
        },
        {
          "role": "agent",
          "text": "It is. But #4 says \"verify thoroughly before claiming success\"; at the moment I ran the probe, that read as satisfied. Nothing in the sentence told me a clean first run was the failure case."
        }
      ],
      "verdict": "Twenty-two borrowed generalities and none of them fired, because none was concrete enough to trigger at the moment it applied. A list the agent can't check is documentation, not a checklist.",
      "cites": []
    },
    {
      "key": "B",
      "label": "First, which failures have actually happened here? Tell me the last three times agent work bit you, and I'll encode exactly those, as behavior, one line each.",
      "kind": "correct",
      "outcome": [
        {
          "role": "user",
          "text": "The fake-green fix last month. The test suite that called the paid embeddings API. And you keep restructuring files nobody asked about."
        },
        {
          "role": "agent",
          "text": "Four gates, then: (1) show the failing probe before any fix; (2) grep for metered clients before the first test run; (3) touch only files the task names (list any others and ask); (4) a probe that's clean on first run is broken until proven otherwise. Each one names its trigger moment. Diff ready."
        }
      ],
      "verdict": "Four gates, each purchased by a real incident and each stating the exact moment it applies, which is what makes them checkable by the agent and enforceable by you.",
      "cites": []
    },
    {
      "key": "C",
      "label": "The most-starred agent ruleset on GitHub covers this well. I'll copy its 40 rules in verbatim. Battle-tested by thousands of users.",
      "kind": "plausible",
      "outcome": [
        {
          "role": "agent",
          "text": "Done. Note: rule 12 mandates a src/ layout, so I've queued a restructuring of your flat layout; rule 31 requires conventional commits, so I'll be rewriting commit style too."
        },
        {
          "role": "user",
          "text": "Nobody asked for any of that. Half these rules are for a different kind of project."
        }
      ],
      "verdict": "Battle-tested by someone else's battles. A famous ruleset encodes its author's incidents and stack. Imported wholesale, it starts fights with your project's reality instead of preventing your failures.",
      "cites": []
    }
  ]
}