{
  "schemaVersion": "1.0",
  "item": {
    "slug": "cerberus-agent-foundry",
    "name": "Isolated Multi-Agent Control Plane",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/delibrately-cmyk/cerberus-agent-foundry",
    "canonicalUrl": "https://clawhub.ai/delibrately-cmyk/cerberus-agent-foundry",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/cerberus-agent-foundry",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cerberus-agent-foundry",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "assets/blueprint/agents/coder/identity/TOOLS_DEV.md",
      "assets/blueprint/agents/qa-ops/identity/TOOLS_OPS.md",
      "assets/blueprint/agents/researcher/identity/TOOLS_SEARCH.md",
      "assets/blueprint/agents/team-lead/identity/ROLE.md",
      "assets/blueprint/control-plane/shared-memory/README.md"
    ],
    "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/cerberus-agent-foundry"
    },
    "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/cerberus-agent-foundry",
    "agentPageUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry/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": "Cerberus Multi-Agent Control Plane",
        "body": "A professional blueprint for building, operating, and governing local multi-agent teams in OpenClaw. It ships a hardened protocol stack for role isolation, task orchestration, asynchronous handoffs, and auditability."
      },
      {
        "title": "Quick Start",
        "body": "Install blueprint into target path:\n\nbash scripts/install_blueprint.sh /path/to/your/system\n\n\nVerify task board:\n\npython3 /path/to/your/system/scripts/taskctl.py list\n\n\nVerify mailbox:\n\nsend: python3 /path/to/your/system/scripts/mailboxctl.py send --task-id TSK-000 --sender team-lead --receiver coder --correlation-id CORR-001 --body \"ACK protocol\"\nack: python3 /path/to/your/system/scripts/mailboxctl.py status --message-id MSG-0001 --to ACK --actor coder"
      },
      {
        "title": "What This Blueprint Provides",
        "body": "Strict workspace isolation per agent (agents/*/workspace)\nUnified control plane (control-plane/tasks, control-plane/mailbox, control-plane/logs)\nTask state machine tooling (taskctl.py)\nMailbox protocol tooling with checksum and GC (mailboxctl.py)\nShared memory layer under control plane (control-plane/shared-memory)"
      },
      {
        "title": "Core Rules (must enforce)",
        "body": "Never use shared agent workspaces.\nUse only control-plane/mailbox for agent-to-agent messaging.\nTeam Lead is sole mailbox garbage-collection authority.\nDeploy actions require explicit human approval artifacts."
      },
      {
        "title": "References",
        "body": "Read references/operations-checklist.md for rollout and audit checks.\nRead assets/blueprint/docs/protocol-v1.md for protocol details."
      }
    ],
    "body": "Cerberus Multi-Agent Control Plane\n\nA professional blueprint for building, operating, and governing local multi-agent teams in OpenClaw. It ships a hardened protocol stack for role isolation, task orchestration, asynchronous handoffs, and auditability.\n\nQuick Start\nInstall blueprint into target path:\nbash scripts/install_blueprint.sh /path/to/your/system\nVerify task board:\npython3 /path/to/your/system/scripts/taskctl.py list\nVerify mailbox:\nsend: python3 /path/to/your/system/scripts/mailboxctl.py send --task-id TSK-000 --sender team-lead --receiver coder --correlation-id CORR-001 --body \"ACK protocol\"\nack: python3 /path/to/your/system/scripts/mailboxctl.py status --message-id MSG-0001 --to ACK --actor coder\nWhat This Blueprint Provides\nStrict workspace isolation per agent (agents/*/workspace)\nUnified control plane (control-plane/tasks, control-plane/mailbox, control-plane/logs)\nTask state machine tooling (taskctl.py)\nMailbox protocol tooling with checksum and GC (mailboxctl.py)\nShared memory layer under control plane (control-plane/shared-memory)\nCore Rules (must enforce)\nNever use shared agent workspaces.\nUse only control-plane/mailbox for agent-to-agent messaging.\nTeam Lead is sole mailbox garbage-collection authority.\nDeploy actions require explicit human approval artifacts.\nReferences\nRead references/operations-checklist.md for rollout and audit checks.\nRead assets/blueprint/docs/protocol-v1.md for protocol details."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/delibrately-cmyk/cerberus-agent-foundry",
    "publisherUrl": "https://clawhub.ai/delibrately-cmyk/cerberus-agent-foundry",
    "owner": "delibrately-cmyk",
    "version": "0.1.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry",
    "downloadUrl": "https://openagent3.xyz/downloads/cerberus-agent-foundry",
    "agentUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cerberus-agent-foundry/agent.md"
  }
}