{
  "run_id": "aloth--cred-1-gpt-6-luna-1793200132321949851",
  "date": "2026-10-28T15:12:32.396218+00:00",
  "repo": "aloth/cred-1",
  "kind": "repo",
  "source": "https://github.com/aloth/cred-1",
  "commit": "e0464b554673358fddff97ad506975f06d8f9fbe",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 102.86762267700396,
  "total_s": 220.0737693309784,
  "steps": [
    "pwd && rg --files -g 'README*' -g 'package.json' -g 'pyproject.toml' -g 'requirements*.txt' -g 'setup.py' -g 'Cargo.toml' -g 'go.mod' -g 'AGENTS.md' | head -80 && git status --short && git rev-parse HEAD 2>/dev/null || true",
    "ls -la; find . -maxdepth 3 -type f | head -100",
    "cat README.md; cat package.json; python3 --version; python3 -m pip --version; node --version; npm --version",
    "npm install",
    "npx cred1 check infowars.com && npx cred1 check nytimes.com && npx cred1 stats",
    "sed -n '1,240p' src/mcp.ts; sed -n '1,180p' src/cli.ts; ls -la .coldpass",
    "node -e 'import { Client } from \"@modelcontextprotocol/sdk/client/index.js\"; import { StdioClientTransport } from \"@modelcontextprotocol/sdk/client/stdio.js\"; const t=new StdioClientTransport({command:\"node\",args:[\"dist/cli.js\",\"--mcp\"]}); const c=new Client({name:\"probe\",version:\"1\"}); await c.connect(t); console.log(JSON.stringify(await c.callTool({name:\"check_domain\",arguments:{domain:\"infowars.com\"}}))); await c.close();'",
    "mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npx\",\"cred1\",\"check\",\"nytimes.com\"],\"cwd\":\"<guest-path>\",\"expected_text\":\"Not found in CRED-1 dataset \u2014 treat as unknown/neutral\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"CLI checks a domain and reports absent entries as unknown/neutral\",\"source\":\"cred1 check nytimes.com\",\"input\":\"nytimes.com\",\"expected\":\"unknown/neutral\",\"probe_kind\":\"cli\",\"argv\":[\"npx\",\"cred1\",\"check\",\"nytimes.com\"],\"expected_text\":\"Not found in CRED-1 dataset \u2014 treat as unknown/neutral\",\"cwd\":\"<guest-path>\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Check one domain using the documented CLI\",\"source\":\"README.md / CLI Usage\",\"input\":\"infowars.com\",\"expected\":\"domain lookup result\",\"argv\":[\"npx\",\"cred1\",\"check\",\"infowars.com\"],\"cwd\":\"<guest-path>\",\"expected_text\":\"Category: fake\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"checks\":[],\"reason\":\"Inspected README entrypoints and package scripts: this is a dataset CLI/library and MCP server with no scheduled loop, cron, webhook, or cycle trigger.\"}\nEOF",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Check domain credibility with the CRED-1 CLI and MCP tool\",\"operation_scope\":\"Local bundled dataset; Node.js >=18 and npm dependencies\",\"steps\":[\"Read README and package entrypoints\",\"npm install (runs the documented TypeScript build)\",\"npx cred1 check infowars.com and npx cred1 check nytimes.com\",\"Called MCP check_domain for infowars.com\",\"Validated and replayed probe, README claim, example, and cycle inspection\"],\"deviations\":[\"The README lookup is illustrative: current infowars.com output is score 0.139/category fake, not the example score/category. The documented not-found behavior replayed successfully.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\nls -la .coldpass"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Check domain credibility with the CRED-1 CLI and MCP tool",
  "suggested_fix": null,
  "tokens_in": 164267,
  "tokens_out": 1299,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "npx",
          "cred1",
          "check",
          "nytimes.com"
        ],
        "kind": "cli",
        "returncode": 0,
        "stdout": "\n\u26aa  nytimes.com\n   Not found in CRED-1 dataset \u2014 treat as unknown/neutral\n   Absence from the dataset does not mean reliable.\n",
        "stderr": "",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "Review signals: 41 known vulnerability.",
    "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.",
    "findings": [
      {
        "kind": "known-vulnerability",
        "count": 41,
        "note": "OSV reports a known vulnerability in this dependency version.",
        "location_count": 9
      }
    ],
    "context": [],
    "limitations": [
      "A short run cannot establish that code is safe.",
      "Connections show IP addresses; proxies can hide the final hostname.",
      "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing."
    ],
    "static": {
      "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check."
    },
    "evidence_url": "/safety/?run=aloth--cred-1-gpt-6-luna-1793200132321949851",
    "evidence_file": "/data/safety/aloth--cred-1-gpt-6-luna-1793200132321949851.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "codex",
  "agent_runtime_version": "codex-cli 0.164.0",
  "tool_transport": "mcp-assigned-vm",
  "platform": "linux",
  "reasoning": "low",
  "service_tier": "standard",
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 10,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "e0464b554673358fddff97ad506975f06d8f9fbe",
    "url": "https://github.com/aloth/cred-1"
  },
  "purpose": "initial",
  "profile": {
    "model": "gpt-6-luna",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": null
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 10,
  "guest_setup": null,
  "runtime": null,
  "runtime_version": null,
  "runtime_revision": null,
  "source_revision": null,
  "evidence_version": null,
  "failure_origin": null,
  "evidence_strength": "readme_checked",
  "works": "yes",
  "install_s": null,
  "first_use_s": null,
  "mcp": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [
    "cli"
  ],
  "license": "CC-BY-4.0",
  "repo_url": "https://github.com/aloth/cred-1",
  "cost_to_try": "free",
  "hardware": null,
  "what_failed": null,
  "local_or_hosted": "local",
  "cycle_checks": [
    {
      "kind": "cycle",
      "claim": "Scheduled or looping main behavior",
      "source": "repository entry points",
      "input": "source inspection",
      "expected": "identify the product trigger",
      "verdict": "yes",
      "outcome": "Inspected README entrypoints and package scripts: this is a dataset CLI/library and MCP server with no scheduled loop, cron, webhook, or cycle trigger.",
      "evidence": "Inspected README entrypoints and package scripts: this is a dataset CLI/library and MCP server with no scheduled loop, cron, webhook, or cycle trigger.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "CLI checks a domain and reports absent entries as unknown/neutral",
      "source": "cred1 check nytimes.com",
      "input": "nytimes.com",
      "expected": "unknown/neutral",
      "command": "npx cred1 check nytimes.com",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: Not found in CRED-1 dataset \u2014 treat as unknown/neutral",
      "evidence": "\u2026Not found in CRED-1 dataset \u2014 treat as unknown/neutral\n   Absence from the dataset does not mean reliable.\n\n",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Check one domain using the documented CLI",
      "source": "README.md / CLI Usage",
      "input": "infowars.com",
      "command": "npx cred1 check infowars.com",
      "evidence": "\ud83d\udd34  infowars.com\n   Score:    0.139 / 1.000\n   Category: fake\n   Level:    low\n   Sources:  2\n   Age:      27.6 years\n   Tranco:   #22,784",
      "deferred": false,
      "expected": "domain lookup result",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 40,
    "last_commit_at": "2026-10-27T19:50:39Z",
    "last_release_at": "2026-10-27T19:50:09Z",
    "median_reply_hours": 619.3,
    "merged_prs_90d": 0,
    "note": "actively maintained: last commit 0 days ago; 40 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; 2 of 2 recent threads got a maintainer reply, median first reply 619.3h; latest release 2026-10-27",
    "open_issues": 0,
    "open_prs": 0,
    "reply_share": 1.0,
    "reply_threads": 2,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 0 days ago; 40 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; 2 of 2 recent threads got a maintainer reply, median first reply 619.3h; latest release 2026-10-27",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago; 0 open issues, 2 answered or closed",
  "last_commit_at": "2026-10-27T19:50:40Z",
  "last_release_at": "2026-10-27T19:50:09Z",
  "open_issues": 0,
  "answered_issues": 2,
  "platforms_claimed": [
    "mac"
  ],
  "topic": "mcp-server",
  "agent_interfaces": [
    {
      "interface": "mcp",
      "evidence": "README metadata",
      "observed": false,
      "operation_checked": false
    },
    {
      "interface": "cli",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": true
    }
  ],
  "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.",
  "mcp_context": null,
  "tested_at": "2026-10-28T15:12:32.396218+00:00",
  "tested_commit": "e0464b554673358fddff97ad506975f06d8f9fbe",
  "tested_with": {
    "agent": "codex",
    "agent_version": "codex-cli 0.164.0",
    "model": "gpt-6-luna",
    "model_route": "gpt-6-luna",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "aloth/cred-1",
    "source": "https://github.com/aloth/cred-1",
    "commit": "e0464b554673358fddff97ad506975f06d8f9fbe",
    "source_revision": null,
    "os": "linux",
    "architecture": null,
    "backend": "hyperv",
    "model": "gpt-6-luna",
    "model_version": "gpt-6-luna",
    "agent_execution": "native_agent",
    "agent_runtime": "codex",
    "agent_runtime_version": "codex-cli 0.164.0",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "e0464b554673358fddff97ad506975f06d8f9fbe",
      "url": "https://github.com/aloth/cred-1"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": "standard",
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Check domain credibility with the CRED-1 CLI and MCP tool",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/aloth--cred-1-gpt-6-luna-1793200132321949851.txt",
  "report_url": "/reports/aloth--cred-1-gpt-6-luna-1793200132321949851.json"
}