Update to Atbash Safety

{
  "description": "Check a specific proposed command or tool action against the selected local Atbash agent's safety policy, or inspect that agent's readiness and policy.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 209
    },
    {
      "relative_path": "scripts/atbash-safety.mjs",
      "size_in_bytes": 544
    }
  ],
  "name": "atbash-safety",
  "skill_md_contents": "---\nname: atbash-safety\ndescription: Check a specific proposed command or tool action against the selected local Atbash agent's safety policy, or inspect that agent's readiness and policy.\n---\n\n# Atbash Safety Check\n\nRun explicit checks using the packaged helper in a local desktop thread with Node.js 22.13.0 or newer. Resolve `<skill-directory>` to this file's directory.\n\nFor readiness and policy, run:\n\n```text\nnode <skill-directory>/scripts/atbash-safety.mjs status\n```\n\nFor a specific action, send JSON on standard input to:\n\n```text\nnode <skill-directory>/scripts/atbash-safety.mjs evaluate\n```\n\nThe input is `{\"toolName\":\"<actual tool>\",\"args\":{...},\"context\":\"<brief task purpose>\"}`. Use the exact proposed tool name and arguments. Context is optional and must be a short explanation of this action; do not send conversation history or transcripts. Clarify missing action details before checking. Do not execute a proposed command merely to evaluate it. Submit only the action information needed for the requested check; omit credentials and unrelated private data.\n\nThe helper uses the selected local `codex` profile and signs locally. It sends the tool name, SDK-redacted arguments, and action context to the package's Atbash service. No private key belongs in action input or output.\n\nRead the JSON result even if the process exits nonzero:\n\n- Only `allow: true` with `verdict: \"ALLOW\"` permits proceeding within the user's already-authorized task. A check by itself does not authorize executing the action.\n- `HOLD`: stop the action and explain the returned review reason.\n- `BLOCK`: stop the action and explain the returned policy reason.\n- `ERROR`, missing or malformed output, timeout, or configuration failure: stop the action; report that a safe decision was unavailable. For profile setup, use `$atbash-setup`.\n\nIf the user asked only for an evaluation, report the result and do not execute the action. If the user also authorized execution, check the exact action immediately before executing it through its normal tool. A changed command or arguments need a new evaluation. Never use the helper as a command executor or treat an evaluation reference as reusable authorization.\n\nState the checked action and relevant reason. This package does not automatically intercept other tools; never report agent readiness or a successful check as proof of universal protection.\n"
}