Finish Him — Security skill for Claude Code
"Cold ass mother fcker.
How to install Finish Him
Installs to ~/.claude/skills/henchmarketing-rgb-sub-zero-skill-finish-him/SKILL.md
mkdir -p ~/.claude/skills/henchmarketing-rgb-sub-zero-skill-finish-him && curl -fsSL https://raw.githubusercontent.com/henchmarketing-rgb/sub-zero-skill/HEAD/commands/finish-him.md -o ~/.claude/skills/henchmarketing-rgb-sub-zero-skill-finish-him/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Finish Him does
description: '"Cold ass mother f*cker." Sub-Zero. Audit the project, plan the path to win, then execute step by step with real-world verification.'
/finish-him
You are Sub-Zero. Two modes, one slash command.
- Mode A (audit) — default invocation. Read the project deep, find what's done / broken / incomplete / stale / missing, write a multi-step plan from current state to the frozen win condition, hand the operator an HTML report with a button to launch Mode B. NO code changes, N
Alternatives in Security
- Engage.Exploit — Execute Phase 4 - Exploitation and Access Establishment 348 ★
- Security Health Check — Execute the security-health-inline skill for inline orchestration 172 ★
- Rolecraft — The security-first skill manager for AI agents — every install runs a security scan 75 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pause After Planning
Standing instruction: finish planning and verification (including plan-gate and plan-auditor), then stop so yo
Audit With Verification
Run a parallel-review-then-adversarial-verify audit on a URL, feature spec, or code path. Dispatches N reviewe
Ext Exploit
Execute ONE approved step from the external attack plan via the ext-exploit-operator agent, with human confirm
Bug Audit Skill
OpenClaw skill: Dynamic bug audit for Node.js web projects (games, data tools, WeChat, APIs, bots). 200+ real-
Agent Recipes
Copy-paste AI agent workflows for real-world dev tasks - code review, testing, security scanning, DevOps autom
Pentest Projects Discovery
An automated way to discover practical, hands on penetration testing projects using Claude, with structured le
Related Agents
Cold Verifier
Phase 11 cold verification agent that independently re-verifies CRITICAL and HIGH findings with zero prior con
Ops Executor Agent
You are an ops execution sub-agent. Your job is to execute a single approved ops plan (research, strategy, con
Save Memory
Step agent that executes memory writes from the routing manifest. Loads save specs once per run, processes eac