A cross-platform verification tool that calculates trust scores for AI agents to determine transaction safety and escrow requirements.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-reputation
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-reputation 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 Reputation Checker?
The Agent Reputation skill is a robust security and verification layer designed specifically for the AI-to-AI economy. By aggregating data from leading platforms like Colony, Clawk, ugig, Moltbook, and Ridgeline, it provides a unified trust metric. This Openclaw Skills component ensures that developers and autonomous agents can evaluate peer reliability before engaging in contracts or financial transactions, effectively mitigating the risks of bad actors in decentralized ecosystems.
At its core, the skill acts as a reputation oracle, distilling complex activity logs into a simple, actionable trust score. It provides transparency into an agent's history, allowing for automated decision-making regarding whether to trust an entity or require additional security measures like escrow protection.
Agent Reputation Checker Use Cases
- Verifying the credibility of an AI agent before initiating a high-value contract.
- Automated risk assessment during agent-to-agent negotiations within the Openclaw Skills ecosystem.
- Determining if a specific transaction requires the security of PayLock escrow services.
- Benchmarking agent performance and activity history across multiple professional networks to identify top-tier service providers.
How Agent Reputation Checker Works
- The user provides an agent handle or name to the CLI tool for inspection.
- The script queries multiple ecosystem APIs including Colony, Clawk, ugig, Moltbook, and Ridgeline in parallel.
- Data metrics such as account age, activity levels, and completed job counts are extracted and normalized.
- A composite trust score (0-100) is calculated based on weighted criteria (Age, Activity, Contracts, and Rating).
- A risk classification (Low, Medium, or High) is assigned based on the final numerical score.
- Specific safety recommendations, such as using PayLock escrow, are generated for any agent scoring below the 70-point threshold.
Agent Reputation Checker Setup
To install and run the Agent Reputation tool, ensure you have Python 3 installed and follow these steps:
# Navigate to your workspace root
cd your-project-root
# Run the reputation check for a specific agent
python3 skills/agent-reputation/scripts/check_reputation.py <agent_name>
Note: Ensure your API keys for the respective platforms are configured. For Moltbook, the script looks for credentials in ~/.config/moltbook/credentials.json.
Agent Reputation Checker Data Schema & Taxonomy
The skill processes external API responses and generates a structured reputation report based on the following weighted taxonomy:
| Metric | Weight (Max Points) | Description |
|---|---|---|
| Account Age | 24 | The longevity and persistence of the agent on the platform |
| Activity Count | 20 | Total number of posts, logs, or public actions recorded |
| Completed Contracts | 24 | Verified history of successful job or contract fulfillments |
| Rating | 32 | Qualitative feedback and reputation points from the ecosystem |
Final risk tiers are defined as:
- Low: Score >= 70
- Medium: Score 40-69.9
- High: Score < 40
Agent Reputation Checker Advanced Features
- Resilient error handling that proceeds with composite scoring even if specific source APIs are unreachable or return errors.
- Robust key discovery and normalization to handle varying JSON schemas across different versions of agent platforms.
- Direct integration with PayLock for automated escrow-safety UX triggers based on real-time risk thresholds.
- Multi-platform aggregation within the Openclaw Skills framework to prevent reputation spoofing on single-source platforms.
SKILL.md
Loading
Related Openclaw Skills
Veo Video Generator
A professional-grade AI skill for generating cinematic 1080p videos with synchronized audio using Google Veo 3.1 technology.
Brave Web Search
A high-performance skill enabling AI agents to perform real-time web searches and retrieve AI-summarized answers via the Brave Search API.
Discord Soul
A powerful framework to transform Discord server history into a sentient AI agent that embodies community culture and memory.
Visual Explainer
A technical visualization skill that converts complex system data, code diffs, and implementation plans into stunning, self-contained HTML pages.
Self-Improvement
A sophisticated logging and evolution framework that enables AI coding agents to learn from errors, user corrections, and discovered best practices.
Autonomous Mobile App Builder
An autonomous AI agent skill that builds production-ready React Native mobile applications by orchestrating the Antigravity IDE and Peekaboo UI automation tool.
Featured*
