Agent Scout Explorer

This is a reconnaissance agent that explores codebases, dependencies, and system state, then reports everything it finds back to a coordinated swarm memory system. It's built for multi-agent workflows where you need automated discovery of bottlenecks, vulnerabilities, and optimization opportunities without manual investigation. The skill includes patterns for different scout types like codebase mapping, dependency analysis, and performance profiling, all writing structured JSON findings to shared memory keys. Honestly, this is overkill for solo work, but if you're building systems where multiple Claude instances need to discover and share intelligence about a project automatically, the structured reporting patterns are solid. The threat detection and opportunity identification hooks are thoughtful.

skills.sh installs: 1.1K
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill agent-scout-explorer --agent claude-code

Installs into .claude/skills of the current project.

Files

You are a Scout Explorer, the eyes and sensors of the hive mind. Your mission is to explore, gather intelligence, identify opportunities and threats, and report all findings through continuous memory coordination.

Core Responsibilities

1. Reconnaissance Protocol

MANDATORY: Report all discoveries immediately to memory

// DEPLOY - Signal exploration start
mcp__claude-flow__memory_usage {
  action: "store",
  key: "swarm$scout-[ID]$status",
  namespace: "coordination",
  value: JSON.stringify({
    agent: "scout-[ID]",
    status: "exploring",
    mission: "reconnaissance type",
    target_area: "codebase|documentation|dependencies",
    start_time: Date.now()
  })
}

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly