Agent Claude Code
A planning agent for authorized security assessments that organizes reconnaissance results into a map of services, technologies, dependencies, and possible entry points. It does not perform attacks or destructive checks.
Agent Claude Code
A cleanup and rollback planning agent for authorized security testing. It lists possible test remnants, the order for reversing changes, and evidence that shows cleanup was completed.
Agent Claude Code
A planning agent for authorized security assessments. It defines the test scope, rules of engagement, success criteria, evidence requirements, and an iterative test plan without carrying out attacks.
Agent Claude Code
A security-assessment agent that designs minimal, auditable evidence for proving business impact and data reach without exposing real sensitive data.
Agent Claude Code
A role definition for an information-gathering security subagent. It collects publicly available information about an explicitly identified, authorized target, such as domains, exposed services, technologies, interfaces, and possible leaks.
Agent Claude Code
A specialist agent for analysing movement between systems inside a private network after an initial access point has been obtained. A private network is an organisation's internal set of connected computers and services.
Agent Claude Code
A security-testing planning agent focused on reducing noise and disruption while collecting evidence. It requires the target, scope, and testing rules before suggesting actions.
Agent Claude Code
A planning agent for authorized, non-destructive security testing. It creates and revises detailed steps for an executor agent, with each step stating the target, allowed scope, one action, and expected evidence.
Agent Claude Code
A supervisor agent that coordinates specialist agents by sending each one a defined part of a task. It handles simple tasks itself and combines specialist work when broader coordination is needed.
Agent Claude Code
Instructions for a coordinating agent that plans multi-agent security work, delegates separate tasks, combines evidence, and delivers the result. A multi-agent workflow uses several specialized agents on parts of one job.
Agent Claude Code
An authorized penetration-testing agent for checking whether identified security weaknesses can be verified and used within a defined scope. Penetration testing is a controlled security assessment of a system.
Agent Claude Code
A security-assessment role for evaluating ways authorized access might persist or remain reusable, while keeping the work low-impact and reversible.
Agent Claude Code
An authorized security-assessment agent for examining whether a user with limited access might reach higher privileges. Privilege escalation means gaining permissions beyond the current account or session.
Agent Claude Code
A reconnaissance agent for authorized security assessments. Reconnaissance means collecting information about a specified system, such as domains, services, paths, and other parts of its exposed attack surface.
Agent Claude Code
A report-writing agent that turns collected security-testing evidence into a structured report. It also gives high-level repair suggestions and checks for verifying those repairs.
Agent Claude Code
Nástroj na triedenie možných bezpečnostných chýb podľa dostupných dôkazov a návrh bezpečných spôsobov ich overenia.
Skill Claude Code
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude CodeCodex
A collection of methods for testing and attacking Windows Active Directory networks, which manage users, computers, and permissions inside many organizations.
Skill Claude CodeCodex
A security-testing skill for applications that use artificial-intelligence models, agents, retrieval systems, tool plugins, or model files. It focuses on risks such as prompt injection, unsafe tool use, data poisoning, and dangerous model-file loading.
Skill Claude CodeCodex
A security-recon workflow for finding a domain’s internet-facing assets, such as subdomains, services, ports, and technology fingerprints. It uses passive sources first, then active checks.
Skill Claude CodeCodex
A skill for examining Android packages, Windows executables, native libraries, and some cross-platform app binaries to understand how they work.
Skill Claude CodeCodex
Postupy na kontrolu blockchainov a inteligentných zmlúv, čo sú programy, ktoré automaticky vykonávajú pravidlá transakcií.
Skill Claude CodeCodex
A method for finding attack chains by combining smaller capabilities such as reading files, writing files, making server requests, or using credentials. It treats a serious outcome as a sequence of separately gained abilities.
Skill Claude CodeCodex
A reference of methods for attacking cloud services, including metadata endpoints, object storage, Kubernetes clusters, and cloud identity systems.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: