Hunt Agent — Security skill for Claude Code
Start an agent pentest.
How to install Hunt Agent
Installs to ~/.claude/skills/elementalsouls-claude-agenthunter-hunt-agent/SKILL.md
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:
- Characterize first — visibility, tool allowlist, egress, oracle semantics, auth model (never send a payload before this).
- 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 RepositoryRelated Skills
Hunt
Start hunting on a target — loads scope, reads disclosed reports, picks best attack surface based on tech stac
UI Refine
Iterative UI refinement: audit existing UI, select issues to fix, apply fixes, re-audit. Provide file paths or
Characterize Agent
Step 1 of an agent pentest — fingerprint the target before sending any payload. Maps visibility, tool allowlis
Zp Cve
Known-CVE check - version fingerprint to confirmed finding, backed by KEV and the local exploit corpora. Usage
Grey Haven Plugin Audit Report
Generated: 2026-01-08 Claude Code Version Target: v2.1.0 Plugins Audited: 16 Overall Health Score: 72/100 ---
Code Review Intense Flow
Heavy code review - fans out to all applicable specialized reviewers (security, frontend, seo, geo, playwright
Related Agents
Event Plan Builder
Merges every validated artifact into one coherent, human-readable event plan. Runs only after the validator re
Effect Prober
Adversarial effect-verifier for irreversible actions. Given an action that reports success (a deploy, migratio
Apply Hunt
Job hunter for the /apply pipeline. Searches LinkedIn's public, logged-out job pages (via the stdlib li.py hel