Skip to main content
skill CX Codex

hunt · h-mmer — Claude Code skill: what it does, how to install

Conducts targeted vulnerability hunting by validating scope, fingerprinting stacks, and dispatching exploit tests.

no license ★ 1,298 updated 2026-06-12

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add H-mmer/pentest-agents --skill hunt -a claude-code
Open on GitHub

What hunt does

The skill manages multi-step offensive security testing against specified domains. Before sending aggressive probes, it verifies targets against scope.yaml and executes tools/scope_check.py to prevent testing out-of-scope assets. It also loads previous intelligence via tools/brain.py and inspects policy.md to pass mandatory operational constraints into every sub-agent dispatch.

During reconnaissance, the routine inspects response headers to identify technologies such as Rails, Django, or Next.js. When --vuln-class is omitted, tools/intel_engine.py scores hypotheses automatically. If a target responds with 403 or 429 status codes, the agent follows a seven-tier escalation process from rules/waf-bypass-protocol.md rather than halting.

Execution requires Python with uv installed, alongside repository helper scripts in $CLAUDE_PROJECT_DIR/tools and defined policy files. Missing scope definitions will stop the workflow at the initial gate.

What it helps with

  • enforce program scope boundaries before active scanning
  • detect backend web technologies via HTTP response headers
  • prioritize vulnerability classes based on detected stack components
  • iterate through structured bypass techniques when encountering a WAF

Example prompts for the agent

  • /hunt target.com
  • /hunt target.com --vuln-class idor
  • /hunt target.com --vuln-class sqli

How to install hunt

1Skills CLI (Vercel)

npx skills add H-mmer/pentest-agents --skill hunt -a claude-code

2Manually: put the files in place

~/.claude/skills/hunt/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/hunt/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about hunt

How to install hunt in Claude Code?

Run npx skills add H-mmer/pentest-agents --skill hunt -a claude-code. The definition will be placed in ~/.claude/skills/hunt/SKILL.md.

What does the hunt skill do?

It orchestrates vulnerability assessments by validating targets against boundaries, fingerprinting server frameworks, and running targeted payloads.

What dependencies are required to run hunt?

You need uv for Python execution, custom CLI helpers located in tools/, and configuration files like scope.yaml and policy.md in the project root.

Similar skills

All skills for Security →

hunt by other authors comes first.

hunt tw93 hunt pinpoints root causes before touching code when an app crashes or regresses. Enforces reproducible evidence and verification before applying any fix. CX Codex +1 15,300installs hunt orwa-mahmoud The hunt Claude Code skill builds a Nightshift work shift from a project request. Give it a task and a number of hours, and it starts without asking for catalog choices. CX Codex +1 ★ 571repo stars fix-security-vulnerabilities-with-strix usestrix The fix-security-vulnerabilities-with-strix skill triages validated Strix findings, fixes their root causes, and runs Strix again to verify the result. Use it after a CLI or cloud scan. CX Codex +1 20,300installs idor-broken-object-authorization yaklang idor-broken-object-authorization is a Claude Code skill with a testing playbook for IDOR, BOLA and BFLA: finding object identifiers, running A-B tests and chaining findings into privilege escalation. CX Codex +1 4,200installs web-pentest briiirussell web-pentest runs black-box and grey-box pentesting of a live web app through the OWASP WSTG phases: authorization, authentication, sessions, input handling. Useful once you have a scope and written permission. CX Codex +1 722installs supabase-audit-authenticated yoanbernabeu supabase-audit-authenticated — a skill for Claude Code, Codex, Cursor, and other platforms that creates a test user and checks what authenticated requests expose versus anonymous ones in Supabase. CX Codex +1 463installs bizlogic-hunter 0xSteph bizlogic-hunter identifies business logic flaws, workflow bypasses, payment tampering, and race conditions during web application tests. CX Codex ★ 2,482repo stars hunt-host-header Sachin Sharma hunt-host-header — a Claude skill that walks a web app through Host header injection checks: password reset poisoning, cache poisoning via forwarded headers, routing SSRF and OAuth redirect abuse. CX Codex +1 ★ 16,193repo stars

From the same set43

The whole set →
pentest-agents-hunting The pentest-agents-hunting rule structures security hunting around scope, practical impact, and attack chains. It helps an agent drop weak leads and investigate confirmed bugs more deeply. CX Codex +1 ★ 1,298repo stars ssti-hunter ssti-hunter — a subagent for finding and exploiting Server-Side Template Injection (SSTI) across Jinja2, Twig, Velocity, FreeMarker, ERB, and Handlebars. Maps sandbox blocklists, identifies engine type, and chains bypasses to RCE. CX Codex +1 ★ 1,298repo stars pentest-agents-techniques The pentest-agents-techniques rule guides agents through checks for authorization flaws and data leaks in web apps. Use it when testing systems you’re authorized to assess. CX Codex +1 ★ 1,298repo stars hunt hunt — a prompt for systematic vulnerability detection on target hosts. Reads scope, detects tech stack, auto-selects vuln classes by likelihood, and runs targeted tests with concrete payloads and WAF bypass rules. CX Codex +1 ★ 1,298repo stars autopilot autopilot coordinates security testing for a target by checking scope and program rules before dispatching specialized subagents. Autonomous mode runs through its completion checks before reporting. CX Codex +1 ★ 1,298repo stars autopilot autopilot — a Claude Code skill that runs a hunt across all vulnerability classes for a target and keeps the agent from calling it done too early. CX Codex +1 ★ 1,298repo stars pentest-agents-mistakes pentest-agents-mistakes is a rule that collects 11 mistakes agents make in security testing, from hallucinated paths to fake PoCs. Read it before a vulnerability hunt. CX Codex +1 ★ 1,298repo stars hunt-idor hunt-idor guides your agent in auditing IDOR and BOLA flaws across APIs, GraphQL schemas, and multi-tenant SaaS platforms. CX Codex +1 ★ 1,298repo stars

Project sponsors

Companies that keep this analytics open