An interactive wizard for managing how your AI agent communicates and shares information with federated peers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ogp-agent-comms
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ogp-agent-comms using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OGP Agent-Comms Configuration?
The ogp-agent-comms skill provides a robust interactive wizard designed to manage agent-to-agent communication policies within the Open General Protocol (OGP) ecosystem. It serves as the decision-making layer that determines how an agent responds to incoming messages from peers once they have cleared initial security gates. By using this Openclaw Skills extension, developers can define fine-grained rules for topic engagement, ranging from full collaboration to strict human escalation.
Built for modern multi-agent environments, this skill supports multi-framework workflows (OpenClaw and Hermes) and advanced routing. It ensures that federated interactions remain secure and aligned with user expectations by managing human delivery preferences and autonomy modes. Whether you are managing a single personal assistant or a fleet of specialized agents, this skill provides the necessary CLI tools to maintain professional and private communication boundaries.
OGP Agent-Comms Configuration Use Cases
- Establishing communication policies for new or existing federated peers.
- Configuring specific topics (e.g., memory-management, testing) that an agent is allowed to discuss.
- Setting up multi-agent routing where different agents handle specific message contexts.
- Defining human delivery modes to control how and when federated messages are surfaced to the user.
- Auditing peer interactions through detailed activity logging.
How OGP Agent-Comms Configuration Works
- Prerequisite Check: The skill verifies the OGP daemon status and lists approved peers to ensure a foundation for communication exists.
- Delegated-Authority Interview: It initiates a canonical interview to establish global defaults for human delivery, relay handling, and autonomy modes.
- Policy Selection: Users select whether to configure global defaults or specific peer overrides using canonical peer IDs.
- Topic & Level Assignment: For each selected peer, the user defines which topics are active and assigns a response level (Full, Summary, Escalate, Deny, or Off).
- State Persistance: Policies are saved into the framework-specific configuration (e.g., peers.json), leveraging an inheritance model where peer-specific rules override globals.
- Runtime Execution: When a peer message arrives, the agent evaluates the response policy to determine if it should engage autonomously or wait for human approval via hook-driven turns.
OGP Agent-Comms Configuration Setup
Ensure the OGP daemon is installed and initialized before using this skill. Use the following commands to get started:
# Install OGP and required components
npm install -g @dp-pcs/ogp
ogp-install-skills
ogp setup
# Launch the communication policy wizard
ogp agent-comms interview
# For framework-specific configuration (e.g., OpenClaw)
ogp --for openclaw agent-comms interview
OGP Agent-Comms Configuration Data Schema & Taxonomy
The skill organizes data within the active framework's configuration files, primarily peers.json and config.json.
Peer Policy Schema
| Field | Description |
|---|---|
id |
Canonical peer ID (hexadecimal) |
responsePolicy |
Object containing topic-specific levels and notes |
level |
The engagement depth: full, summary, escalate, deny, or off |
Global Configuration
humanDeliveryTarget: Destination for human notifications (e.g., Telegram chat ID).inboundFederationPolicy: Defines the defaultmode(forward, summarize, autonomous, or approval-required).notifyTargets: Map for multi-agent routing targets.
OGP Agent-Comms Configuration Advanced Features
- Multi-Framework Support: Seamlessly switch between OpenClaw and Hermes states using the
--forflag. - Inheritance Logic: Sophisticated policy resolution that falls back from topic-specific to peer-specific, then to global defaults.
- Hook-Driven Delivery: Integration with
/hooks/agentfor native human-facing federated work on OpenClaw. - Activity Auditing: Full logging of inbound and outbound agent-comms messages with the
ogp agent-comms activitycommand. - Multi-Agent Routing: Granular control over which agent handles specific federated intents based on
notifyTargets.
SKILL.md
Loading
Related Openclaw Skills
Business ROI Calculator
A professional-grade real-time investment return calculator designed to help business experts evaluate the viability of partnerships and projects.
Envoy
A comprehensive integration for Envoy that enables AI agents to manage visitor logs, desk reservations, and workplace logistics through the Membrane framework.
Amazon Price History Tracker
A professional-grade Amazon price monitoring and analysis agent designed to identify optimal buying and selling windows.
1Password CLI for Agents
A secure interface allowing AI agents to read, write, and manage 1Password secrets using dedicated Service Account tokens.
AI DevOps Toolkit
An observability and monitoring toolkit for local AI fleet operations using Ollama Herd and SQLite-backed tracing.
Wink Pings News Fetcher
A specialized news retrieval skill that connects to the Wink Pings service to deliver personalized AI industry updates and curated news feeds.
Featured*
