Skip to content

aiskillstore/marketplace / skills/92bilal26/nextjs-devtools

nextjs-devtools

Verified

Next.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps. Use when working on Next.js applications, debugging routing, or inspecting app structure. NOT for general React or non-Next.js projects.

FileKindSize
SKILL.mdskill md2.2 KB
scripts/mcp-client.pyscript16.4 KB
scripts/start-server.shscript266 B
skill-report.jsonconfig57.4 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T15:35:22.102Z",
    "slug": "92bilal26-nextjs-devtools",
    "source_url": "https://github.com/92Bilal26/TaskPilotAI/tree/main/.claude/skills/nextjs-devtools",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "278acbb34f61feebf623a000d5d5dafd7bf920e51cce2a7b0921779c4c671f09",
    "tree_hash": "cb9d001b53744e4f17a6b7b7c449a936cbb3207c36dcd6988de0cb933830e16a",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "nextjs-devtools",
    "description": "Next.js development tooling that connects to a Model Context Protocol server to inspect routes, components, build information, and configuration.",
    "summary": "Inspect Next.js routes, components, build data, and configuration through an MCP client.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "92Bilal26",
    "license": "MIT",
    "tags": [
      "nextjs",
      "mcp",
      "debugging",
      "routes",
      "devtools"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ],
    "category": "coding"
  },
  "security_audit": {
    "risk_level": "high",
    "is_blocked": false,
    "safe_to_publish": false,
    "analysis_status": "ok",
    "summary": "The main risks are intentional command execution and unpinned npm package execution. The Python client can run a user-supplied stdio command through a shell, and the shell script and docs run npx next-devtools-mcp@latest. Network use is mostly expected MCP communication, and many static hits were Markdown formatting or session bookkeeping false positives.",
    "remediation": [
      {
        "issue": "Shell-based stdio execution",
        "suggestion": "Replace shell=True with an argument list, or allow only a reviewed command template for the Next.js MCP server.",
        "severity": "high"
      },
      {
        "issue": "Unpinned npm package execution",
        "suggestion": "Pin next-devtools-mcp to a reviewed version and document how maintainers verify updates before changing the pin.",
        "severity": "high"
      },
      {
        "issue": "Agent-facing command examples",
        "suggestion": "Require user confirmation before running bash, Python stdio, or npx commands from the skill documentation.",
        "severity": "medium"
      },
      {
        "issue": "User-selected HTTP MCP endpoints",
        "suggestion": "Warn users before connecting to non-localhost MCP URLs or sending custom HTTP headers.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 191,
            "line_end": 191
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 204,
            "line_end": 204
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 348,
            "line_end": 348
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 371,
            "line_end": 371
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 377,
            "line_end": 379
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "SKILL.md",
            "line_start": 15,
            "line_end": 23
          },
          {
            "file": "SKILL.md",
            "line_start": 23,
            "line_end": 29
          },
          {
            "file": "SKILL.md",
            "line_start": 29,
            "line_end": 30
          },
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 32
          },
          {
            "file": "SKILL.md",
            "line_start": 32,
            "line_end": 33
          },
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 64
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 72
          },
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 80
          },
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 84
          },
          {
            "file": "SKILL.md",
            "line_start": 84,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 94
          },
          {
            "file": "SKILL.md",
            "line_start": 94,
            "line_end": 100
          },
          {
            "file": "SKILL.md",
            "line_start": 100,
            "line_end": 102
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 146,
            "line_end": 146
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 271,
            "line_end": 271
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 314,
            "line_end": 314
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 323,
            "line_end": 323
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 328,
            "line_end": 328
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 333,
            "line_end": 333
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 33,
            "line_end": 33
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 16,
            "line_end": 16
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 23,
            "line_end": 23
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 10,
            "line_end": 10
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:scripts/mcp-client.py:191:python-subprocess-popen",
        "category": "external_commands",
        "severity": "high",
        "pattern": "Python subprocess.Popen",
        "file": "scripts/mcp-client.py",
        "line_start": 191,
        "line_end": 191,
        "snippet": "self._process: Optional[subprocess.Popen] = None"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:204:python-subprocess-popen",
        "category": "external_commands",
        "severity": "high",
        "pattern": "Python subprocess.Popen",
        "file": "scripts/mcp-client.py",
        "line_start": 204,
        "line_end": 204,
        "snippet": "self._process = subprocess.Popen("
      },
      {
        "id": "external_commands:scripts/mcp-client.py:348:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/mcp-client.py",
        "line_start": 348,
        "line_end": 348,
        "snippet": "lines.append(f\"## `{name}`\\n\")"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:371:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/mcp-client.py",
        "line_start": 371,
        "line_end": 371,
        "snippet": "lines.append(f\"- **`{prop_name}`** (`{prop_type}`){req_marker}: {prop_desc}\")"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:377:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/mcp-client.py",
        "line_start": 377,
        "line_end": 379,
        "snippet": "lines.append(\"```json\")"
      },
      {
        "id": "network:scripts/mcp-client.py:146:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 146,
        "line_end": 146,
        "snippet": "def request(self, method: str, params: Optional[dict] = None) -> dict:"
      },
      {
        "id": "network:scripts/mcp-client.py:271:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 271,
        "line_end": 271,
        "snippet": "def request(self, method: str, params: Optional[dict] = None) -> dict:"
      },
      {
        "id": "network:scripts/mcp-client.py:314:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 314,
        "line_end": 314,
        "snippet": "result = self.transport.request(\"tools/list\")"
      },
      {
        "id": "network:scripts/mcp-client.py:323:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 323,
        "line_end": 323,
        "snippet": "result = self.transport.request(\"tools/call\", params)"
      },
      {
        "id": "network:scripts/mcp-client.py:328:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 328,
        "line_end": 328,
        "snippet": "result = self.transport.request(\"resources/list\")"
      },
      {
        "id": "network:scripts/mcp-client.py:333:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 333,
        "line_end": 333,
        "snippet": "result = self.transport.request(\"prompts/list\")"
      },
      {
        "id": "network:scripts/mcp-client.py:33:python-http-libraries",
        "category": "network",
        "severity": "low",
        "pattern": "Python HTTP libraries",
        "file": "scripts/mcp-client.py",
        "line_start": 33,
        "line_end": 33,
        "snippet": "from urllib.request import Request, urlopen"
      },
      {
        "id": "network:scripts/mcp-client.py:10:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 10,
        "line_end": 10,
        "snippet": "python mcp-client.py list --url http://localhost:8080"
      },
      {
        "id": "network:scripts/mcp-client.py:16:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 16,
        "line_end": 16,
        "snippet": "python mcp-client.py call --url http://localhost:8080 --tool create_issue \\"
      },
      {
        "id": "network:scripts/mcp-client.py:20:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 20,
        "line_end": 20,
        "snippet": "python mcp-client.py emit --url http://localhost:8080"
      },
      {
        "id": "network:scripts/mcp-client.py:23:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 23,
        "line_end": 23,
        "snippet": "python mcp-client.py emit --url http://localhost:8080 --format json"
      },
      {
        "id": "blocker:scripts/mcp-client.py:52:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 52,
        "line_end": 52,
        "snippet": "self._request_id = 0"
      },
      {
        "id": "blocker:scripts/mcp-client.py:57:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 57,
        "line_end": 57,
        "snippet": "self._request_id += 1"
      },
      {
        "id": "blocker:scripts/mcp-client.py:58:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 58,
        "line_end": 60,
        "snippet": "return self._request_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:88:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 88,
        "line_end": 88,
        "snippet": "self._session_id = resp.headers.get('Mcp-Session-Id')"
      },
      {
        "id": "blocker:scripts/mcp-client.py:137:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 137,
        "line_end": 139,
        "snippet": "headers[\"Mcp-Session-Id\"] = self._session_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:165:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 165,
        "line_end": 167,
        "snippet": "headers[\"Mcp-Session-Id\"] = self._session_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:190:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 190,
        "line_end": 190,
        "snippet": "self._request_id = 0"
      },
      {
        "id": "blocker:scripts/mcp-client.py:196:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 196,
        "line_end": 196,
        "snippet": "self._request_id += 1"
      },
      {
        "id": "blocker:scripts/mcp-client.py:197:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 197,
        "line_end": 199,
        "snippet": "return self._request_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:275:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 275,
        "line_end": 275,
        "snippet": "req_id = self._next_id()"
      },
      {
        "id": "blocker:scripts/mcp-client.py:286:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 286,
        "line_end": 287,
        "snippet": "# Wait for response with matching id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:480:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 480,
        "line_end": 480,
        "snippet": "print(f\"Invalid JSON: {e}\", file=sys.stderr)"
      },
      {
        "id": "external_commands:scripts/start-server.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/start-server.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "network:scripts/start-server.sh:10:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/start-server.sh",
        "line_start": 10,
        "line_end": 10,
        "snippet": "echo \"Server started. Use mcp-client.py with -u http://localhost:$PORT\""
      },
      {
        "id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 15,
        "line_end": 23,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 23,
        "line_end": 29,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 29,
        "line_end": 30,
        "snippet": "| `list-routes` | Get all app routes |"
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 30,
        "line_end": 31,
        "snippet": "| `get-route-info` | Details for specific route |"
      },
      {
        "id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 31,
        "line_end": 32,
        "snippet": "| `list-components` | React components in app |"
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 32,
        "line_end": 33,
        "snippet": "| `get-build-info` | Build configuration |"
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 33,
        "line_end": 39,
        "snippet": "| `get-config` | next.config.js settings |"
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 50,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 54,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 54,
        "line_end": 64,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 68,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 72,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 72,
        "line_end": 80,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 84,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 84,
        "line_end": 88,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 88,
        "line_end": 90,
        "snippet": "For single calls, use `-s` flag which spawns server per-call:"
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 94,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 94,
        "line_end": 100,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:100:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 100,
        "line_end": 102,
        "snippet": "| Server not starting | Check `npx next-devtools-mcp@latest` works manually |"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:scripts/mcp-client.py:191:python-subprocess-popen",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This is only a type annotation for a subprocess handle. It does not start a process or pass data to a shell."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:204:python-subprocess-popen",
        "verdict": "confirmed",
        "confidence": 0.9,
        "severity": "high",
        "reason": "The code executes self.command through subprocess.Popen with shell=True. That command is supplied by the --stdio option, so untrusted input could execute arbitrary shell syntax."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:348:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines only format generated documentation with Markdown backticks or code fences. They do not evaluate the content or execute a shell command."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:371:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines only format generated documentation with Markdown backticks or code fences. They do not evaluate the content or execute a shell command."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:377:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "These lines only format generated documentation with Markdown backticks or code fences. They do not evaluate the content or execute a shell command."
      },
      {
        "id": "network:scripts/mcp-client.py:146:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.78,
        "severity": "low",
        "reason": "This method sends JSON-RPC requests to the URL configured by the user through HTTPTransport. It is legitimate MCP behavior but can disclose supplied headers or parameters to a remote endpoint."
      },
      {
        "id": "network:scripts/mcp-client.py:271:http-client-library",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "This request method belongs to StdioTransport and writes JSON-RPC messages to a local child process over stdin. It does not perform HTTP or external network I/O."
      },
      {
        "id": "network:scripts/mcp-client.py:314:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.68,
        "severity": "low",
        "reason": "The call uses transport.request to list MCP tools. When the selected transport is HTTP, this sends MCP traffic to the configured endpoint."
      },
      {
        "id": "network:scripts/mcp-client.py:323:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "low",
        "reason": "The tool call is sent through transport.request and can include user-supplied arguments. With HTTPTransport, those arguments go to the configured MCP endpoint."
      },
      {
        "id": "network:scripts/mcp-client.py:328:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.66,
        "severity": "low",
        "reason": "The resource listing uses transport.request and may be sent over HTTP when that transport is selected. This is expected MCP behavior but remains a network data flow."
      },
      {
        "id": "network:scripts/mcp-client.py:333:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.66,
        "severity": "low",
        "reason": "The prompt listing uses transport.request and may be sent over HTTP when that transport is selected. This is expected MCP behavior but remains a network data flow."
      },
      {
        "id": "network:scripts/mcp-client.py:33:python-http-libraries",
        "verdict": "confirmed",
        "confidence": 0.82,
        "severity": "low",
        "reason": "The urllib imports are used by HTTPTransport to send MCP requests. This is an expected feature, but it provides real network capability to user-selected URLs."
      },
      {
        "id": "network:scripts/mcp-client.py:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL appears only in usage text and points to localhost. It does not create an outbound network request or encode a remote destination."
      },
      {
        "id": "network:scripts/mcp-client.py:16:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL appears only in usage text and points to localhost. It does not create an outbound network request or encode a remote destination."
      },
      {
        "id": "network:scripts/mcp-client.py:20:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL appears only in usage text and points to localhost. It does not create an outbound network request or encode a remote destination."
      },
      {
        "id": "network:scripts/mcp-client.py:23:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL appears only in usage text and points to localhost. It does not create an outbound network request or encode a remote destination."
      },
      {
        "id": "blocker:scripts/mcp-client.py:52:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:57:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:58:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:88:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Reading Mcp-Session-Id from an MCP response is protocol session management. It is not host reconnaissance."
      },
      {
        "id": "blocker:scripts/mcp-client.py:137:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Adding Mcp-Session-Id to a request header is MCP session continuity. It does not inspect local system state."
      },
      {
        "id": "blocker:scripts/mcp-client.py:165:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Adding Mcp-Session-Id to a request header is MCP session continuity. It does not inspect local system state."
      },
      {
        "id": "blocker:scripts/mcp-client.py:190:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:196:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:197:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:275:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines manage JSON-RPC request counters, MCP session headers, or error output. They do not enumerate host files, processes, users, or system configuration."
      },
      {
        "id": "blocker:scripts/mcp-client.py:286:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This comment describes waiting for a matching JSON-RPC response id. It is not host or environment reconnaissance."
      },
      {
        "id": "blocker:scripts/mcp-client.py:480:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "This line prints a JSON parse error to stderr. It does not collect or reveal host system inventory."
      },
      {
        "id": "external_commands:scripts/start-server.sh:1:unix-shell-invocation",
        "verdict": "confirmed",
        "confidence": 0.82,
        "severity": "medium",
        "reason": "The flagged line identifies a shell script, and the same script starts an MCP server with npx on line 8. Running it executes local commands and can fetch npm packages."
      },
      {
        "id": "network:scripts/start-server.sh:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "This line only prints a localhost URL for the user. It does not perform a network connection or target an external host."
      },
      {
        "id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.82,
        "severity": "medium",
        "reason": "The quick-start block instructs users or agents to run bash and Python commands that spawn npx next-devtools-mcp@latest. This is intentional external command execution from a community skill."
      },
      {
        "id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.8,
        "severity": "medium",
        "reason": "The route inspection workflow tells the user or agent to run the Python client with a stdio npx command. Following it executes a local shell command."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.8,
        "severity": "medium",
        "reason": "The build debugging workflow instructs use of the Python client with npx next-devtools-mcp@latest. This is local external command execution."
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.78,
        "severity": "medium",
        "reason": "The component discovery example runs the Python client with a stdio command. This launches an external MCP server process."
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.76,
        "severity": "medium",
        "reason": "The persistent server example instructs users to run bash scripts/start-server.sh. That script starts an npx-based MCP server process."
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.62,
        "severity": "medium",
        "reason": "The prose explicitly recommends the -s mode that spawns a server process per call. It is not execution by itself, but it directs command-spawning behavior."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.8,
        "severity": "medium",
        "reason": "The on-demand example runs the Python client with npx next-devtools-mcp@latest as the stdio command. Following it executes an external command."
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "These lines are Markdown table entries or fence closings. They name tools or formatting only and do not instruct shell execution."
      },
      {
        "id": "external_commands:SKILL.md:100:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "The troubleshooting table instructs manual execution of npx next-devtools-mcp@latest. That is external package execution from a community skill."
      }
    ],
    "semantic_findings": [
      {
        "title": "Unpinned MCP Package Execution",
        "description": "The skill runs npx next-devtools-mcp@latest in the shell script and usage examples. This downloads and executes the newest npm package version without pinning or integrity controls.",
        "severity": "high",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 8,
            "line_end": 8
          },
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 22
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 43
          }
        ],
        "confidence": 0.95,
        "confidence_reasoning": "The script and documented workflows directly use npx with the @latest tag. That is clear evidence of unpinned package download and execution."
      }
    ],
    "critical_findings": [],
    "high_findings": [
      {
        "title": "Python subprocess.Popen",
        "description": "self._process = subprocess.Popen(",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 204,
            "line_end": 204
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "high",
        "confidence": 0.9,
        "confidence_reasoning": "The code executes self.command through subprocess.Popen with shell=True. That command is supplied by the --stdio option, so untrusted input could execute arbitrary shell syntax."
      },
      {
        "title": "Unpinned MCP Package Execution",
        "description": "The skill runs npx next-devtools-mcp@latest in the shell script and usage examples. This downloads and executes the newest npm package version without pinning or integrity controls.",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 8,
            "line_end": 8
          },
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 22
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 43
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "high",
        "confidence": 0.95,
        "confidence_reasoning": "The script and documented workflows directly use npx with the @latest tag. That is clear evidence of unpinned package download and execution."
      }
    ],
    "medium_findings": [
      {
        "title": "Unix shell invocation",
        "description": "#!/bin/bash",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 1,
            "line_end": 1
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The flagged line identifies a shell script, and the same script starts an MCP server with npx on line 8. Running it executes local commands and can fetch npm packages."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 15,
            "line_end": 23
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The quick-start block instructs users or agents to run bash and Python commands that spawn npx next-devtools-mcp@latest. This is intentional external command execution from a community skill."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 50
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.8,
        "confidence_reasoning": "The route inspection workflow tells the user or agent to run the Python client with a stdio npx command. Following it executes a local shell command."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 64
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.8,
        "confidence_reasoning": "The build debugging workflow instructs use of the Python client with npx next-devtools-mcp@latest. This is local external command execution."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 72
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "The component discovery example runs the Python client with a stdio command. This launches an external MCP server process."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 84
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.76,
        "confidence_reasoning": "The persistent server example instructs users to run bash scripts/start-server.sh. That script starts an npx-based MCP server process."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "For single calls, use `-s` flag which spawns server per-call:",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 90
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.62,
        "confidence_reasoning": "The prose explicitly recommends the -s mode that spawns a server process per call. It is not execution by itself, but it directs command-spawning behavior."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 94
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.8,
        "confidence_reasoning": "The on-demand example runs the Python client with npx next-devtools-mcp@latest as the stdio command. Following it executes an external command."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| Server not starting | Check `npx next-devtools-mcp@latest` works manually |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 100,
            "line_end": 102
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "The troubleshooting table instructs manual execution of npx next-devtools-mcp@latest. That is external package execution from a community skill."
      }
    ],
    "low_findings": [
      {
        "title": "HTTP client library",
        "description": "def request(self, method: str, params: Optional[dict] = None) -> dict:",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 146,
            "line_end": 146
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.78,
        "confidence_reasoning": "This method sends JSON-RPC requests to the URL configured by the user through HTTPTransport. It is legitimate MCP behavior but can disclose supplied headers or parameters to a remote endpoint."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"tools/list\")",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 314,
            "line_end": 314
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.68,
        "confidence_reasoning": "The call uses transport.request to list MCP tools. When the selected transport is HTTP, this sends MCP traffic to the configured endpoint."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"tools/call\", params)",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 323,
            "line_end": 323
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.72,
        "confidence_reasoning": "The tool call is sent through transport.request and can include user-supplied arguments. With HTTPTransport, those arguments go to the configured MCP endpoint."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"resources/list\")",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 328,
            "line_end": 328
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.66,
        "confidence_reasoning": "The resource listing uses transport.request and may be sent over HTTP when that transport is selected. This is expected MCP behavior but remains a network data flow."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"prompts/list\")",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 333,
            "line_end": 333
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.66,
        "confidence_reasoning": "The prompt listing uses transport.request and may be sent over HTTP when that transport is selected. This is expected MCP behavior but remains a network data flow."
      },
      {
        "title": "Python HTTP libraries",
        "description": "from urllib.request import Request, urlopen",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 33,
            "line_end": 33
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.82,
        "confidence_reasoning": "The urllib imports are used by HTTPTransport to send MCP requests. This is an expected feature, but it provides real network capability to user-selected URLs."
      }
    ],
    "dangerous_patterns": [],
    "files_scanned": 3,
    "total_lines": 605,
    "audit_model": "codex",
    "audited_at": "2026-07-05T15:35:22.102Z",
    "agent_auto_install_policy": "confirmation_required",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Inspect Next.js Apps with MCP DevTools",
    "value_statement": "Debugging Next.js routes, components, and build settings can require many manual checks. This skill connects Claude, Codex, and Claude Code to a Next.js MCP server for focused inspection.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "Next.js DevTools",
      "Next.js MCP",
      "MCP client",
      "Next.js routes",
      "React components",
      "build debugging",
      "next.config.js"
    ],
    "actual_capabilities": [
      "Starts or connects to a Next.js DevTools MCP server.",
      "Lists available MCP tools from HTTP or stdio transports.",
      "Calls MCP tools for routes, route details, components, build information, and configuration.",
      "Emits MCP tool schemas as Markdown or JSON documentation.",
      "Supports custom HTTP headers for MCP requests."
    ],
    "limitations": [
      "Designed for Next.js projects, not general React applications.",
      "Requires Python 3, Node.js, npx, and access to the MCP server package.",
      "Can execute local commands when stdio or shell scripts are used.",
      "Does not replace manual validation of build output or security settings."
    ],
    "use_cases": [
      {
        "title": "Route Inventory During Refactors",
        "description": "Inspect all application routes before changing navigation, layouts, or API paths.",
        "target_user": "Frontend developer"
      },
      {
        "title": "Build Configuration Review",
        "description": "Check build information and Next.js configuration while diagnosing compile or deployment issues.",
        "target_user": "Full-stack engineer"
      },
      {
        "title": "AI-Assisted Project Inspection",
        "description": "Let an AI coding assistant query MCP tools and summarize project structure during development.",
        "target_user": "Claude, Codex, or Claude Code user"
      }
    ],
    "prompt_templates": [
      {
        "title": "List Project Routes",
        "scenario": "Beginner route discovery",
        "prompt": "Inspect this Next.js project with the nextjs-devtools skill. List the available routes and summarize any dynamic routes."
      },
      {
        "title": "Inspect One Route",
        "scenario": "Focused route debugging",
        "prompt": "Use nextjs-devtools to review the route I am working on. Explain its route details and any configuration signals that matter."
      },
      {
        "title": "Review Build Setup",
        "scenario": "Deployment troubleshooting",
        "prompt": "Use nextjs-devtools to inspect build information and Next.js configuration. Identify settings that could affect deployment behavior."
      },
      {
        "title": "Map Route, Component, and Build Context",
        "scenario": "Advanced project investigation",
        "prompt": "Use nextjs-devtools to combine route data, component inventory, build information, and configuration. Produce a concise diagnosis for the feature area I am changing."
      }
    ],
    "output_examples": [
      {
        "input": "Inspect routes before a navigation refactor.",
        "output": [
          "A grouped route inventory for pages, app routes, and API endpoints.",
          "A short note about dynamic routes that need extra review."
        ]
      },
      {
        "input": "Review why the build behaves differently in production.",
        "output": "A plain-language summary of relevant build and configuration settings, with likely causes to check first."
      },
      {
        "input": "Find components related to a dashboard feature.",
        "output": "A component inventory summary that highlights likely dashboard files and follow-up inspection targets."
      }
    ],
    "best_practices": [
      "Run the skill from the root of a trusted Next.js repository.",
      "Pin and review the MCP server package before regular use.",
      "Prefer localhost MCP endpoints unless a remote server is explicitly trusted."
    ],
    "anti_patterns": [
      "Running shell commands from untrusted prompts without user review.",
      "Sending secrets through MCP HTTP headers or tool parameters.",
      "Using this skill for non-Next.js projects and trusting incomplete results."
    ],
    "faq": [
      {
        "question": "What projects does this skill support?",
        "answer": "It is intended for Next.js applications that can be inspected through a Next.js DevTools MCP server."
      },
      {
        "question": "Does it modify my application?",
        "answer": "The documented tools are inspection focused, but the helper scripts can start local processes."
      },
      {
        "question": "Can it work with Claude, Codex, and Claude Code?",
        "answer": "Yes. The report marks support for Claude, Codex, and Claude Code."
      },
      {
        "question": "Does it require network access?",
        "answer": "It can connect to HTTP MCP endpoints and can use npx to fetch the MCP server package."
      },
      {
        "question": "What should I check before installing it?",
        "answer": "Review the command execution behavior, pin the npm package version, and use trusted local projects."
      },
      {
        "question": "Is it useful outside Next.js?",
        "answer": "No. The skill is built around Next.js routes, configuration, components, and build information."
      }
    ]
  },
  "file_structure": [
    {
      "name": "scripts",
      "type": "dir",
      "path": "scripts",
      "children": [
        {
          "name": "mcp-client.py",
          "type": "file",
          "path": "scripts/mcp-client.py",
          "lines": 491
        },
        {
          "name": "start-server.sh",
          "type": "file",
          "path": "scripts/start-server.sh",
          "lines": 11
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 103
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall