elementalsouls

Hunt Agent — Security skill for Claude Code

Security community

Start an agent pentest.

How to install Hunt Agent

Installs to ~/.claude/skills/elementalsouls-claude-agenthunter-hunt-agent/SKILL.md

Terminal
mkdir -p ~/.claude/skills/elementalsouls-claude-agenthunter-hunt-agent && curl -fsSL https://raw.githubusercontent.com/elementalsouls/Claude-AgentHunter/HEAD/commands/hunt-agent.md -o ~/.claude/skills/elementalsouls-claude-agenthunter-hunt-agent/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Hunt Agent does


name: hunt-agent description: Start an agent pentest. Fingerprint the target agent, select applicable hunt-agent skills, run their probes, score with the 4 detection arms, apply both gates, report only actioned findings.

Run the agent-pentest workflow against the target the user names:

  1. Characterize first — visibility, tool allowlist, egress, oracle semantics, auth model (never send a payload before this).
  2. Select skills by surface: MCP server → hunt-agent-mcp-*; chat/RAG → hunt-agen

Alternatives in Security

  • Raptor Loop Hunt — RAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill 212 ★
  • Commit Hook Checklist — Audit commit-hook automation as gates against AI slop and broken commits (Node.js, Go, polyglot) 168 ★
  • Release Audit — Use right before cutting a release — it spawns ONE fresh sibling session via CCC that audits only the JUDGMENT 130 ★

Full documentation available on GitHub

View Source Repository