ry-ops

Mr Robot — Security skill for Claude Code

Security community

An ADR-driven security framework for Kali — a HackTheBox co-pilot orchestrating Hat-persona Claude agents across a shared arcade and a cross-engagement memory layer.

How to install Mr Robot

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ry-ops/mr-robot and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Mr Robot does

An ADR-driven security framework for Kali — a HackTheBox co-pilot orchestrating Hat-persona Claude agents across a shared arcade and a cross-engagement memory layer.

Alternatives in Security

Imcodes — The IM for agents 960 ★
Claude Bootstrap — Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patte 536 ★
Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★

README

Mr. Robot — two-layer architecture: an orchestrator spawns Hat robots that work a shared arcade and memory layer.

Mr. Robot

An orchestrated, ADR-driven security framework for Kali — a HackTheBox co-pilot that runs multiple "Hat" personas concurrently to compress a weekend of boxes into hours. Named for the TV series.

The idea

Mr. Robot does not hard-code its behavior. Every operating mode is an **ADR**, and every ADR prefaces a **Hat** — a persona defined along three axes: intent, ethics, and behavior. The orchestrator points Hat _robots_ at a box; they work a shared task board (the **arcade**); a declarative **playbook** turns findings into new tasks; and the campaign adapts as it runs — spreading robots across the attack surface or ganging up on one tough target.

The differentiator isn't the tooling — Kali already has the tools. The differentiator is **judgment that compounds across boxes**, which is what the memory layer (ADR-0014) is for.

The control loop

The control loop: a heartbeat ticks; the brain reads the arcade and decides per robot (leave, reinforce, repurpose, or assign); robots work; findings post; the playbook unlocks new tasks; repeat.

A tick is a turn. The brain reads the arcade, decides per-robot, robots act, findings come back, the playbook unlocks new tasks. "Assist vs. gang up" is not a policy switch — it's emergent from the same `ready` / `blocker` machinery.

Architecture

Two layers.

The arsenal (layer 1, ADR-0012) — the mr-robot MCP server: the arcade (SQLite findings store + task board), the playbook engine, the Hat registry, and a scope guard.
The orchestrator (layer 2, ADR-0013) — "Mr. Robot": spawns Hat robots as real Claude agents, runs a heartbeat control loop, and adapts.