{
  "schemaVersion": "1.0",
  "item": {
    "slug": "jameseball-clawdio",
    "name": "Clawdio",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/JamesEBall/jameseball-clawdio",
    "canonicalUrl": "https://clawhub.ai/JamesEBall/jameseball-clawdio",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/jameseball-clawdio",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=jameseball-clawdio",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "package.json",
      "src/__tests__/basic.test.ts",
      "src/cli.ts",
      "src/crypto.ts",
      "src/index.ts"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/jameseball-clawdio"
    },
    "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/jameseball-clawdio",
    "agentPageUrl": "https://openagent3.xyz/skills/jameseball-clawdio/agent",
    "manifestUrl": "https://openagent3.xyz/skills/jameseball-clawdio/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/jameseball-clawdio/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": "Clawdio",
        "body": "Minimal secure peer-to-peer communication for AI agents. Two agents exchange a connection string, perform a Noise XX handshake, then communicate over encrypted channels. No central server required."
      },
      {
        "title": "When to Use",
        "body": "Agent-to-agent communication across machines or networks\nSecure task delegation between sub-agents on different hosts\nAny scenario requiring encrypted, authenticated P2P messaging"
      },
      {
        "title": "Setup",
        "body": "The Clawdio project lives at projects/clawdio/. Install dependencies and build:\n\ncd projects/clawdio && npm install && npx tsc"
      },
      {
        "title": "Quick Start",
        "body": "const { Clawdio } = require('./projects/clawdio/dist/index.js');\n\n// Create two nodes\nconst alice = await Clawdio.create({ port: 9090, autoAccept: true });\nconst bob = await Clawdio.create({ port: 9091, autoAccept: true });\n\n// Connect (Noise XX handshake)\nconst aliceId = await bob.exchangeKeys(alice.getConnectionString());\n\n// Send messages\nawait bob.send(aliceId, { task: \"What's the weather?\" });\nalice.onMessage((msg, from) => console.log(msg.task));"
      },
      {
        "title": "Connection Consent (Recommended)",
        "body": "By default, unknown inbound peers require explicit consent:\n\nconst node = await Clawdio.create({ port: 9090 }); // autoAccept defaults to false\n\nnode.on('connectionRequest', (req) => {\n  console.log(`Connection from ${req.id}`);\n  console.log(`Fingerprint: ${req.fingerprint}`);\n  // Accept or reject\n  node.acceptPeer(req.id);  // or node.rejectPeer(req.id)\n});\n\nOutbound connections (you calling exchangeKeys) are auto-accepted. Already-trusted peers auto-reconnect."
      },
      {
        "title": "Human Verification",
        "body": "For high-trust scenarios, verify peers in person:\n\nnode.setOwner('Alice');\nconst code = node.getVerificationCode(peerId); // \"torch lemon onyx prism jade index\"\n// Both humans compare codes in person, then:\nnode.verifyPeer(peerId); // trust: 'accepted' → 'human-verified'\nnode.getPeerTrust(peerId); // 'human-verified'"
      },
      {
        "title": "Trust Levels",
        "body": "pending — connection request received, not yet accepted\naccepted — peer accepted, encrypted communication active\nhuman-verified — verified via in-person code exchange"
      },
      {
        "title": "Persistent Identity",
        "body": "Pass identityPath to persist keys and trusted peers across restarts:\n\nconst node = await Clawdio.create({\n  port: 9090,\n  identityPath: '.clawdio-identity.json'\n});"
      },
      {
        "title": "Sub-Agent Pattern",
        "body": "Spawn a sub-agent to handle Clawdio communication:\n\n1. Main agent spawns sub-agent with task\n2. Sub-agent creates Clawdio node, connects to remote peer\n3. Sub-agent exchanges messages, collects results\n4. Sub-agent reports back to main agent"
      },
      {
        "title": "Security Properties",
        "body": "Forward secrecy (ephemeral X25519 keys)\nMutual authentication (Noise XX)\nReplay protection (monotonic counters)\nXChaCha20-Poly1305 AEAD encryption\nConnection consent for inbound peers"
      },
      {
        "title": "API Reference",
        "body": "MethodDescriptionClawdio.create(opts)Create and start a nodenode.exchangeKeys(connStr)Connect to peernode.send(peerId, msg)Send encrypted messagenode.onMessage(handler)Listen for messagesnode.acceptPeer(id)Accept pending connectionnode.rejectPeer(id)Reject pending connectionnode.setOwner(name)Set human owner namenode.getVerificationCode(id)Get 6-word verification codenode.verifyPeer(id)Mark peer as human-verifiednode.getPeerTrust(id)Get trust levelnode.getFingerprint(id)Emoji fingerprintnode.getPeerStatus(id)alive/stale/downnode.stop()Shutdown"
      }
    ],
    "body": "Clawdio\n\nMinimal secure peer-to-peer communication for AI agents. Two agents exchange a connection string, perform a Noise XX handshake, then communicate over encrypted channels. No central server required.\n\nWhen to Use\nAgent-to-agent communication across machines or networks\nSecure task delegation between sub-agents on different hosts\nAny scenario requiring encrypted, authenticated P2P messaging\nSetup\n\nThe Clawdio project lives at projects/clawdio/. Install dependencies and build:\n\ncd projects/clawdio && npm install && npx tsc\n\nQuick Start\nconst { Clawdio } = require('./projects/clawdio/dist/index.js');\n\n// Create two nodes\nconst alice = await Clawdio.create({ port: 9090, autoAccept: true });\nconst bob = await Clawdio.create({ port: 9091, autoAccept: true });\n\n// Connect (Noise XX handshake)\nconst aliceId = await bob.exchangeKeys(alice.getConnectionString());\n\n// Send messages\nawait bob.send(aliceId, { task: \"What's the weather?\" });\nalice.onMessage((msg, from) => console.log(msg.task));\n\nConnection Consent (Recommended)\n\nBy default, unknown inbound peers require explicit consent:\n\nconst node = await Clawdio.create({ port: 9090 }); // autoAccept defaults to false\n\nnode.on('connectionRequest', (req) => {\n  console.log(`Connection from ${req.id}`);\n  console.log(`Fingerprint: ${req.fingerprint}`);\n  // Accept or reject\n  node.acceptPeer(req.id);  // or node.rejectPeer(req.id)\n});\n\n\nOutbound connections (you calling exchangeKeys) are auto-accepted. Already-trusted peers auto-reconnect.\n\nHuman Verification\n\nFor high-trust scenarios, verify peers in person:\n\nnode.setOwner('Alice');\nconst code = node.getVerificationCode(peerId); // \"torch lemon onyx prism jade index\"\n// Both humans compare codes in person, then:\nnode.verifyPeer(peerId); // trust: 'accepted' → 'human-verified'\nnode.getPeerTrust(peerId); // 'human-verified'\n\nTrust Levels\npending — connection request received, not yet accepted\naccepted — peer accepted, encrypted communication active\nhuman-verified — verified via in-person code exchange\nPersistent Identity\n\nPass identityPath to persist keys and trusted peers across restarts:\n\nconst node = await Clawdio.create({\n  port: 9090,\n  identityPath: '.clawdio-identity.json'\n});\n\nSub-Agent Pattern\n\nSpawn a sub-agent to handle Clawdio communication:\n\n1. Main agent spawns sub-agent with task\n2. Sub-agent creates Clawdio node, connects to remote peer\n3. Sub-agent exchanges messages, collects results\n4. Sub-agent reports back to main agent\n\nSecurity Properties\nForward secrecy (ephemeral X25519 keys)\nMutual authentication (Noise XX)\nReplay protection (monotonic counters)\nXChaCha20-Poly1305 AEAD encryption\nConnection consent for inbound peers\nAPI Reference\nMethod\tDescription\nClawdio.create(opts)\tCreate and start a node\nnode.exchangeKeys(connStr)\tConnect to peer\nnode.send(peerId, msg)\tSend encrypted message\nnode.onMessage(handler)\tListen for messages\nnode.acceptPeer(id)\tAccept pending connection\nnode.rejectPeer(id)\tReject pending connection\nnode.setOwner(name)\tSet human owner name\nnode.getVerificationCode(id)\tGet 6-word verification code\nnode.verifyPeer(id)\tMark peer as human-verified\nnode.getPeerTrust(id)\tGet trust level\nnode.getFingerprint(id)\tEmoji fingerprint\nnode.getPeerStatus(id)\talive/stale/down\nnode.stop()\tShutdown"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/JamesEBall/jameseball-clawdio",
    "publisherUrl": "https://clawhub.ai/JamesEBall/jameseball-clawdio",
    "owner": "JamesEBall",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/jameseball-clawdio",
    "downloadUrl": "https://openagent3.xyz/downloads/jameseball-clawdio",
    "agentUrl": "https://openagent3.xyz/skills/jameseball-clawdio/agent",
    "manifestUrl": "https://openagent3.xyz/skills/jameseball-clawdio/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/jameseball-clawdio/agent.md"
  }
}