cfn-agent-discovery

Scan .claude/agents directory and generate agents-registry.json with metadata.

14|2|Updated Sep 23, 2025
One-click install
npx skills add https://github.com/masharratt/claude-flow-novice --skill cfn-agent-discovery
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cfn-agent-discovery
Source: https://github.com/masharratt/claude-flow-novice/tree/main/.claude/cfn-extras/skills/deprecated/cfn-agent-discovery
Command: npx skills add https://github.com/masharratt/claude-flow-novice --skill cfn-agent-discovery

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates agent discovery by scanning agent definitions and compiling a registry for use by orchestration components.

Core Features & Use Cases

  • Agent registry generation: Produces a centralized .json of agents with metadata.
  • Frontmatter extraction: Reads agent files to extract name, type, description, and keywords.
  • Use Case: Quickly assemble the agent registry for Loop orchestration, enabling automatic agent selection.

Quick Start

Run discover-agents.sh to generate agents-registry.json and use it for agent selection.

Frequently Asked Questions about cfn-agent-discovery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically discover and inventory Claude agents in my workflow?

Agent discovery scans your .claude/agents directory, extracts metadata from agent definition files, and generates a centralized agents-registry.json with name, description, type, loop level, keywords, and file paths. Run discover-agents.sh to compile the registry automatically.

What metadata does the agent registry include for each agent?

The registry captures per-agent metadata: name, description, type, loop level (Loop 3, Loop 2, or coordinator), keywords, and file location, plus timestamps and total agent count. This enables automatic agent selection in orchestration workflows.

Can the agent discovery handle malformed or missing frontmatter data?

Yes, the Skill includes robust frontmatter parsing that handles missing or malformed data gracefully, ensuring the registry generation completes even when agent definition files have incomplete metadata.

How do I use the agent registry for Loop orchestration?

After generating agents-registry.json with discover-agents.sh, orchestration components read the registry to automatically select agents based on loop level and keywords, enabling dynamic agent routing in Claude Flow Novice workflows.

When should I regenerate the agent registry?

Regenerate agents-registry.json whenever you add, remove, or modify agents in .claude/agents. The registry includes a last_updated timestamp to track freshness and ensure orchestration uses current agent metadata.