{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ghostfetch",
    "name": "Ghostfetch",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/neothelobster/ghostfetch",
    "canonicalUrl": "https://clawhub.ai/neothelobster/ghostfetch",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ghostfetch",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ghostfetch",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json",
      "setup.sh"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ghostfetch"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/ghostfetch",
    "agentPageUrl": "https://openagent3.xyz/skills/ghostfetch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ghostfetch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ghostfetch/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Ghostfetch",
        "body": "Web search and page fetcher for AI agents. Single binary, no browser needed. Fetches pages with browser-like TLS fingerprints for reliable access.\n\nUse for: web searches, fetching page content as markdown, extracting links, and gathering information from the web."
      },
      {
        "title": "Search the web",
        "body": "ghostfetch \"your search query\"                    # Search DuckDuckGo (default)\nghostfetch \"query\" -e brave                       # Search with Brave\nghostfetch \"query\" -e google                      # Search with Google\nghostfetch \"query\" -e bing                        # Search with Bing\nghostfetch \"query\" -n 5                           # Limit to 5 results\nghostfetch \"query\" --json                         # JSON output with metadata\n\nSearch engines: duckduckgo (default), brave, bing, google"
      },
      {
        "title": "Fetch pages",
        "body": "ghostfetch fetch https://example.com              # Fetch page (raw HTML)\nghostfetch fetch https://example.com -m           # Fetch as markdown (reader mode — preferred)\nghostfetch fetch https://example.com --markdown-full  # Full page as markdown (not just main content)\nghostfetch fetch https://example.com --json       # JSON with body, status, headers, cookies\nghostfetch fetch https://example.com --raw        # Raw HTML without processing\nghostfetch fetch url1 url2 url3 -p 3              # Fetch multiple URLs in parallel\n\nAlways use -m (markdown mode) when reading page content — it extracts the main content and converts to clean markdown, saving tokens vs raw HTML."
      },
      {
        "title": "Extract links",
        "body": "ghostfetch links https://example.com              # Extract all links from page\nghostfetch links https://example.com -f \"github\"  # Filter links by regex pattern\nghostfetch links https://example.com --json       # JSON output"
      },
      {
        "title": "Flags Reference",
        "body": "FlagShortDefaultWhat it does--engine-educkduckgoSearch engine to use--results-n10Number of search results--markdown-mfalseConvert to markdown (reader mode)--markdown-fullfalseFull page markdown (not just main content)--json-jfalseJSON output with metadata--rawfalseRaw HTML output--max-parallel-p5Max parallel fetches--filter-fFilter links by regex--timeout-t30sRequest timeout--browser-bchromeBrowser fingerprint: chrome, firefox--no-cookiesfalseDisable cookie persistence--follow-LtrueFollow redirects--verbose-vfalsePrint request/response details--captcha-serviceCaptcha service: 2captcha, anticaptcha--captcha-keyCaptcha service API key"
      },
      {
        "title": "Decision Guide",
        "body": "I want to...Use thisSearch the webghostfetch \"query\"Search with specific engineghostfetch \"query\" -e braveRead a web pageghostfetch fetch <url> -mRead multiple pages at onceghostfetch fetch url1 url2 url3 -m -p 3Find links on a pageghostfetch links <url>Find specific linksghostfetch links <url> -f \"pattern\"Get structured dataghostfetch fetch <url> --json"
      },
      {
        "title": "Research a topic",
        "body": "ghostfetch \"rust async runtime comparison 2026\" -n 5\nghostfetch fetch https://tokio.rs -m"
      },
      {
        "title": "Scrape structured data",
        "body": "ghostfetch fetch https://api.example.com/data --json"
      },
      {
        "title": "Find all GitHub links on a page",
        "body": "ghostfetch links https://awesome-list.com -f \"github.com\""
      },
      {
        "title": "Installation",
        "body": "The ghostfetch binary must be in your PATH. Build from source:\n\ngit clone https://github.com/neothelobster/ghostfetch.git\ncd ghostfetch\ngo build -o ghostfetch .\ncp ghostfetch ~/.openclaw/workspace/tools/\n\nOr run the included setup.sh which clones at a pinned commit with verification.\n\nRequires Go 1.21+ to build. No runtime dependencies."
      },
      {
        "title": "Security",
        "body": "Read-only tool — output goes to stdout only, no file write capability\nNo custom headers or POST bodies — cannot leak secrets to external endpoints\nNo data is stored except optional cookie jars (disabled with --no-cookies)\nAll network requests go directly from your machine — no proxy or third-party service\nThe setup script clones from GitHub at a pinned commit with verification\nSource code: https://github.com/neothelobster/ghostfetch"
      }
    ],
    "body": "Ghostfetch\n\nWeb search and page fetcher for AI agents. Single binary, no browser needed. Fetches pages with browser-like TLS fingerprints for reliable access.\n\nUse for: web searches, fetching page content as markdown, extracting links, and gathering information from the web.\n\nCommands\nSearch the web\nghostfetch \"your search query\"                    # Search DuckDuckGo (default)\nghostfetch \"query\" -e brave                       # Search with Brave\nghostfetch \"query\" -e google                      # Search with Google\nghostfetch \"query\" -e bing                        # Search with Bing\nghostfetch \"query\" -n 5                           # Limit to 5 results\nghostfetch \"query\" --json                         # JSON output with metadata\n\n\nSearch engines: duckduckgo (default), brave, bing, google\n\nFetch pages\nghostfetch fetch https://example.com              # Fetch page (raw HTML)\nghostfetch fetch https://example.com -m           # Fetch as markdown (reader mode — preferred)\nghostfetch fetch https://example.com --markdown-full  # Full page as markdown (not just main content)\nghostfetch fetch https://example.com --json       # JSON with body, status, headers, cookies\nghostfetch fetch https://example.com --raw        # Raw HTML without processing\nghostfetch fetch url1 url2 url3 -p 3              # Fetch multiple URLs in parallel\n\n\nAlways use -m (markdown mode) when reading page content — it extracts the main content and converts to clean markdown, saving tokens vs raw HTML.\n\nExtract links\nghostfetch links https://example.com              # Extract all links from page\nghostfetch links https://example.com -f \"github\"  # Filter links by regex pattern\nghostfetch links https://example.com --json       # JSON output\n\nFlags Reference\nFlag\tShort\tDefault\tWhat it does\n--engine\t-e\tduckduckgo\tSearch engine to use\n--results\t-n\t10\tNumber of search results\n--markdown\t-m\tfalse\tConvert to markdown (reader mode)\n--markdown-full\t\tfalse\tFull page markdown (not just main content)\n--json\t-j\tfalse\tJSON output with metadata\n--raw\t\tfalse\tRaw HTML output\n--max-parallel\t-p\t5\tMax parallel fetches\n--filter\t-f\t\tFilter links by regex\n--timeout\t-t\t30s\tRequest timeout\n--browser\t-b\tchrome\tBrowser fingerprint: chrome, firefox\n--no-cookies\t\tfalse\tDisable cookie persistence\n--follow\t-L\ttrue\tFollow redirects\n--verbose\t-v\tfalse\tPrint request/response details\n--captcha-service\t\t\tCaptcha service: 2captcha, anticaptcha\n--captcha-key\t\t\tCaptcha service API key\nDecision Guide\nI want to...\tUse this\nSearch the web\tghostfetch \"query\"\nSearch with specific engine\tghostfetch \"query\" -e brave\nRead a web page\tghostfetch fetch <url> -m\nRead multiple pages at once\tghostfetch fetch url1 url2 url3 -m -p 3\nFind links on a page\tghostfetch links <url>\nFind specific links\tghostfetch links <url> -f \"pattern\"\nGet structured data\tghostfetch fetch <url> --json\nExamples\nResearch a topic\nghostfetch \"rust async runtime comparison 2026\" -n 5\nghostfetch fetch https://tokio.rs -m\n\nScrape structured data\nghostfetch fetch https://api.example.com/data --json\n\nFind all GitHub links on a page\nghostfetch links https://awesome-list.com -f \"github.com\"\n\nInstallation\n\nThe ghostfetch binary must be in your PATH. Build from source:\n\ngit clone https://github.com/neothelobster/ghostfetch.git\ncd ghostfetch\ngo build -o ghostfetch .\ncp ghostfetch ~/.openclaw/workspace/tools/\n\n\nOr run the included setup.sh which clones at a pinned commit with verification.\n\nRequires Go 1.21+ to build. No runtime dependencies.\n\nSecurity\nRead-only tool — output goes to stdout only, no file write capability\nNo custom headers or POST bodies — cannot leak secrets to external endpoints\nNo data is stored except optional cookie jars (disabled with --no-cookies)\nAll network requests go directly from your machine — no proxy or third-party service\nThe setup script clones from GitHub at a pinned commit with verification\nSource code: https://github.com/neothelobster/ghostfetch"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/neothelobster/ghostfetch",
    "publisherUrl": "https://clawhub.ai/neothelobster/ghostfetch",
    "owner": "neothelobster",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ghostfetch",
    "downloadUrl": "https://openagent3.xyz/downloads/ghostfetch",
    "agentUrl": "https://openagent3.xyz/skills/ghostfetch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ghostfetch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ghostfetch/agent.md"
  }
}