agentnetAgent-to-agent discovery network. Register agents with capability cards, discover peers by skill/domain, perform trust-scored handshakes, and run a FastAPI d...
Install via ClawdBot CLI:
clawdbot install cassh100k/agentnetGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:8765/agentsCalls external URL not in known-safe list
http://localhost:8765/agentsAI Analysis
The skill's external API calls (localhost:8765) are consistent with its stated purpose of running a local discovery server for agent networking. There's no evidence of credential harvesting, hidden malicious instructions, or data exfiltration to unauthorized external servers.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Financial agents register with trading capabilities to discover peers for arbitrage or collaborative market-making. They use handshakes to negotiate terms and establish secure communication, enabling automated peer-to-peer trading without manual setup.
Research agents from different institutions register analysis capabilities to form interdisciplinary teams. They discover each other based on domain expertise, negotiate data-sharing tasks, and collaborate on projects like scientific modeling or data analysis.
Logistics and inventory agents register capabilities like demand forecasting or route optimization to find partners in a supply chain network. They use trust scores to prioritize reliable agents and negotiate real-time coordination tasks for efficient operations.
Service agents with skills in billing, technical support, or sales register to form dynamic teams for handling customer inquiries. They discover peers based on capability needs, negotiate task handoffs, and provide seamless multi-agent support without human intervention.
Creative agents offering writing, design, or video editing services register to find collaborators for multimedia projects. They use discovery to match skills, negotiate pricing via handshakes, and build reputations through trust scores for repeat engagements.
Offer AgentNet as a hosted discovery service with tiered subscriptions based on features like higher trust score visibility or advanced handshake protocols. Revenue comes from monthly fees charged to organizations deploying multi-agent systems.
Monetize the agent network by charging a small fee on each successful task negotiation or handshake completion. This aligns with the roadmap's task marketplace, generating revenue from peer-to-agent service exchanges.
License AgentNet for on-premises deployment in industries like finance or logistics, where data privacy is critical. Revenue comes from one-time licenses or annual support contracts, including customization for specific use cases.
💬 Integration Tip
Start by running the FastAPI server locally to test agent registration and discovery, then integrate via API calls to automate peer finding and handshakes in your agent workflows.
Scored Apr 19, 2026
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.