Ext Scope — Testing skill for Claude Code
Define and record the scope of an authorized external penetration test (target IPs/hostnames, out-of-scope, window, rate limits, forbidden actions) into a per-engagement scope file the other commands.
How to install Ext Scope
Installs to ~/.claude/skills/xcoy0te-claude-externalpentest-ext-scope/SKILL.md
mkdir -p ~/.claude/skills/xcoy0te-claude-externalpentest-ext-scope && curl -fsSL https://raw.githubusercontent.com/xcoy0te/Claude-ExternalPentest/HEAD/commands/ext-scope.md -o ~/.claude/skills/xcoy0te-claude-externalpentest-ext-scope/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ext Scope does
description: Define and record the scope of an authorized external penetration test (target IPs/hostnames, out-of-scope, window, rate limits, forbidden actions) into a per-engagement scope file the other commands read.
Define the scope for an authorized EXTERNAL penetration test.
Targets (IPs and/or hostnames): **$ARGUMENTS**
**Authorized engagements only.** This file is the boundary every later step trusts. Fill it from what the client authorized IN WRITING; never widen it.
Do the fo
Alternatives in Testing
- Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
- Factory — Dark Factory Mode - Spec-in, software-out autonomous pipeline 2.8k ★
- Ext Apps — Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP serve 1.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Continuous Retest Loop
Re-test a target on every change instead of once per engagement — detect drift, then re-run ONLY the affected
Nuguard Redteam
Run authorized non-destructive NuGuard adversarial testing and report evidence.
SkillAtlas
The open marketplace for AI Agent Skills — publish, discover, install, and rate SKILL.md-compatible skills for
Agent Docs Spec
A specification for making documentation sites accessible to AI coding agents: discovery, truncation limits, c
Model Provider
Switch the default model provider for sf's spawned build/test sub-agents: anthropic (default), codex, or curso
Bug Hunting
Bug bounty hunting & penetration testing skills for Claude, Codex, and any agentic coding tool.
Related Agents
Ext Enumerator
Runs the RECON + ENUMERATION phase of an authorized external penetration test against the in-scope targets (IP
Engagement Planner
Delegates to this agent when the user needs to plan a penetration test, define attack methodology, scope an en
Penetration Tester
Use this agent for AUTHORIZED penetration testing of your own applications on local or staging environments on