agent-registryMANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or ....
Install via ClawdBot CLI:
clawdbot install matrixy/agent-registryGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdCalls external URL not in known-safe list
https://img.shields.io/badge/version-2.0.1-blueAI Analysis
The skill appears to be a legitimate agent registry system with no evidence of data exfiltration or credential harvesting. The external URL reference is to a version badge image (img.shields.io) which is benign metadata display, not data transmission. The /etc/passwd reference in signals appears to be a false positive from pattern matching rather than actual credential access.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 1, 2026
A development team needs to review pull requests for security vulnerabilities and best practices. The agent registry allows lazy-loading specialized agents like security-auditor or code-reviewer based on the code's domain, reducing token overhead by 95% compared to loading all agents upfront. This ensures efficient, on-demand expertise for tasks such as authentication code audits.
A customer service platform uses AI agents to handle diverse inquiries, from billing issues to technical troubleshooting. The registry enables searching for agents matching specific intents, such as 'billing dispute' or 'network error', and loading only the relevant agent to provide accurate, token-efficient responses without pre-loading all agents.
A healthcare organization employs AI agents to analyze patient data for insights like disease prediction or treatment recommendations. Using the registry, analysts can search for agents specialized in areas like 'clinical trial matching' or 'symptom checker', loading them on-demand to maintain compliance and reduce computational overhead in sensitive environments.
A financial institution monitors transactions for fraud and regulatory compliance. The registry allows lazy-loading agents such as 'fraud-detector' or 'aml-auditor' based on transaction patterns, enabling efficient, real-time analysis without the token cost of pre-loading all compliance agents, crucial for high-volume data processing.
An e-learning platform personalizes lessons for students based on their learning styles and subjects. Instructors use the registry to search for agents like 'math-tutor' or 'language-helper', loading them only when needed to provide tailored assistance, optimizing resource usage in dynamic educational workflows.
Offer the agent registry as a cloud-based service with tiered subscriptions based on usage, such as number of agents or search queries. This model generates recurring revenue by providing enterprises with scalable, token-efficient AI agent management, including premium features like enhanced UI and analytics.
Provide professional services to help organizations migrate their existing agents to the registry and customize workflows. Revenue comes from one-time project fees or ongoing support contracts, targeting businesses needing tailored solutions for complex AI agent deployments in industries like finance or healthcare.
Release the core registry as open-source software to build a community, then monetize through premium add-ons like advanced search algorithms, enterprise support, or proprietary agents. This model drives adoption while generating revenue from upsells to larger organizations requiring enhanced functionality.
💬 Integration Tip
Always use the search tool first to find relevant agents based on user intent keywords, then load only the best match to minimize token usage and follow the agent's instructions for execution.
Scored Apr 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...