I have been working with AI since 2020, but never got the time to create a git for myself, so here I am. The below thread here are some tooling for Claude Code and some fun apps, I built around one habit, since the inception of LLMs: verify what a chat model would otherwise just assert.

	research-hound A five-stage research workflow for Claude Code, with 21 scripts that check citations and claims instead of trusting the model.
	skill-vision Validates Claude Agent Skills for spec conformance, quality and security, and counts the context tokens each one costs.
	agent-oracle Decides how an agent system should be built before it runs, from the number of agents to what gets locked down.
	mr-usage A Rust and Tauri desktop app that shows what is left on nine paid APIs, with keys kept in the OS keystore.
	llm-dogfight Two small local language models command rival saucer fleets in your terminal while a genetic algorithm evolves their tactics.

NVIDIA SkillSpector scans the three skills on every push, and each ships with a .skillspector-baseline.yaml that names every suppressed finding and why.

Three of my own, still in active development.

	TigerOCR  beta Hosted GPU OCR that turns PDFs and images into clean Markdown, as a remote MCP server and REST API.
	OpenCarMind  beta A car logger for the ESP32-S3 with a 93 KB on-chip neural network and a desktop app for Windows, macOS and Linux.
	Murasaki  invite only A purple-team platform for authorized security research, with AI-driven reverse engineering and ICS threat modeling.

My Claude Code sessions run in the cloud with a short rulebook that Claude reads before anything else.

• Anything that touches the live web goes through agent-reach: SerpApi answers which pages rank, Firecrawl reads the page, and its developer, research and government indexes handle code, papers and law. The built-in search stays off unless I ask for it, because I want results I can audit.
• Every draft that leaves a session passes through humanizer, and anything that looks too confident gets hall-hunter, which has to name the file, line and contradicting fact for every finding or report it as unverified.
• Skills get validated by skill-vision before they ship. Agent designs start with agent-oracle's four questions. Papers go through research-hound, which checks that each DOI resolves and that its metadata matches the citation.
• The quantum-computing skill covers Qiskit, PennyLane, QuTiP and D-Wave Ocean, which is where the power systems work and the Claude work meet.

The icons on the five repositories above came out of one such sessions (Clearly I am no Photo Editor). Firecrawl read each project page, Higgsfield rendered the marks on the same near-black tile as the mr-usage app icon, Claude Design laid out the family, and Claude Code pushed the commits.

LinkedIn · Google Scholar