Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.

DeepSeek Harness: Everything is a Plugin.

A long-horizon benchmark harness: give a coding agent a real game engine, professional conditions and time, and ask it to build an open-world game. Harness only, no results.

documenting undocumented interfaces

Single-file, zero-dependency task board: owner-vs-agent plates, a dependency map, tap-to-complete.

Deployment of an Active Directory Tier Model structure to support Tier 0, Tier 1, and Tier 2 objects.

Packaged ready-to-go Tier Zero PZ rules/searches and Tier One PZ rules for critical business applications

A Vulnerable-by-Design Cybersecurity Training Platform

Entra ID user enumeration and auth method discovery via the public GetCredentialType API

Agent Package Manager

The universal skill manager for AI coding agents.

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

OID-See is an identity attack surface mapping tool that models OAuth trust, persistence, and impersonation paths in Entra using a graph-based approach.

Some awesome prompts for Jules Agent

Troubleshooting MDE Workstations

Mask the trail, keep the scent. AnonymousHound anonymizes sensitive data within BloodHound exports (users, groups, PKI, etc.) ensuring PII is scrubbed, but the full map of security vulnerabilities …

Simple script to extract useful informations from the combo BloodHound + Neo4j

Azure administrative tiering based on known attack paths

Penelope Shell Handler

The "Monash Enterprise Access Model" (MEAM) is a model for tiering Active Directory that builds heavily on the Microsoft Enterprise Access Model.

Extracted lua script from Defender mpavbase.vdm and mpasbase.vdm

Maester is a test automation framework to help you stay in control of your Microsoft security configuration.

Tool for creating reports on Entra ID Role Assignments

OSINT cheat sheet, list OSINT tools, wiki, dataset, article, book , red team OSINT for hackers and OSINT tips and OSINT branch. This repository will grow every time will research, there is a resear…

Misconfiguration Manager is a central knowledge base for all known Microsoft Configuration Manager tradecraft and associated defensive and hardening guidance.