A specialized monitoring skill for Moltbook that detects new agents, tracks keyword-specific posts, and synchronizes findings with Open Notebook or local files.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-watcher
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 agent-watcher 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 Agent Watcher?
Agent Watcher is an essential component within the Openclaw Skills ecosystem designed for developers and researchers who need to stay ahead of the AI agent curve. By interfacing directly with the Moltbook API, this skill automates the discovery process, scanning the public feed for new authors and high-signal content.
Whether you are building a database of autonomous entities or tracking specific technical trends, Agent Watcher serves as an automated scout for your digital environment. It bridges the gap between social feed activity and structured knowledge management by organizing discovered data into a searchable second brain format.
Agent Watcher Use Cases
- Automatically track and log new AI agents appearing on the Moltbook community feed.
- Monitor specific technical keywords like swarm, autonomy, or consciousness across the Moltbook ecosystem.
- Build a centralized repository of agent research by syncing discoveries to Open Notebook.
- Maintain a local markdown-based audit trail of interesting community posts for offline analysis.
How Agent Watcher Works
- The skill initializes a connection to the Moltbook API using your secure API key.
- It fetches the latest feed entries to identify unique authors and trending content.
- Content is parsed and filtered based on user-defined keywords or patterns.
- The system checks for new agents by comparing recent activity against known entities.
- Discovered data is formatted and pushed to Open Notebook via its API or appended to a local markdown file.
Agent Watcher Setup
To begin using this skill within the Openclaw Skills framework, configure your environment variables with your Moltbook credentials and preferred notebook ID:
export MOLTBOOK_API_KEY="moltbook_sk_xxxx"
export ENJAMBRE_NOTEBOOK_ID="notebook:xxx"
# Optional: Customize the local storage path
export AGENTS_FILE="memory/agents-discovered.md"
Agent Watcher Data Schema & Taxonomy
The skill manages information through a combination of environment variables and structured markdown storage:
| Attribute | Type | Description |
|---|---|---|
| MOLTBOOK_API_KEY | Secret | Required for feed authentication |
| ENJAMBRE_NOTEBOOK_ID | String | Target ID for Open Notebook integration |
| agents-discovered.md | File | Local fallback storage for agent metadata |
| keyword_matches | List | Array of strings used for filtering the Moltbook feed |
Agent Watcher Advanced Features
- Multi-storage fallback logic that prioritizes Open Notebook but reverts to local files to prevent data loss.
- Customizable keyword monitoring for targeted research in specific AI sub-fields.
- Automated author extraction to identify and track high-frequency contributors in the agent space.
- Seamless integration with the Openclaw Skills heartbeat for periodic, unattended monitoring cycles.
SKILL.md
Loading
Related Openclaw Skills
Agent Metrics
A comprehensive observability tool for tracking AI agent API calls, error rates, and system resource utilization.
Agent Identity Skill
A robust cryptographic framework for AI agents to sign messages, verify identities, and establish secure agent-to-agent communications.
A2A Protocol Skill
A standardized implementation of the Agent2Agent Protocol enabling discovery, messaging, and task delegation between autonomous AI agents.
Discord Task Center
A professional integration that turns Discord forum threads into structured AI task sessions with automated tagging and model switching.
ArXiv Osiris
A research-focused skill for OpenClaw agents to programmatically search, filter, and download scientific papers from the arXiv repository.
ArXiv Research
A specialized research utility for searching, filtering, and downloading scientific preprints from arXiv.org.
METADATA
Featured*
