Monitor MCP tool calls for prompt injection, PII leakage, shadow servers, and exfiltration patterns.

Removes 20+ patterns of AI slop from any piece of writing.

Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we confi…

This project demonstrates how to implement runtime configuration patterns in ReAct Agents and supervisor-style architectures using LangGraph. It shows the progression from hardcoded agents to flexi…

An autonomous Kubernetes SRE agent. It monitors cluster health, diagnoses issues, and applies fixes — with human approval required before any write operation.

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

The CUSTODY(TM) Framework for AI Agent Containment

access to david ondrej's personal agent skills

Public repo for HF blog posts

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

AI Deep SAST - LLM-powered deep static analysis for CI/CD. Combines Semgrep, tree-sitter code indexing and frontier LLMs (e.g. GPT-4o, Claude) for fast and deep vulnerability scanning.

A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows

Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.

AI coding jargon, explained in plain English.

access to david ondrej's personal agent skills

How to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.

Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

Reference code for the Meta-Harness paper.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

An agentic skills framework & software development methodology that works.

SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams. Works for any team with repeatable proces…

Skills for Real Engineers. Straight from my .agents directory.

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.