Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.

Local-first context hygiene for AI coding agents — Claude Code plugin plus shell helpers for large reads, noisy output, redaction, artifacts, and measured token/cost evidence.

A command-line tool that takes a Git repository's URL or local path and generates a video or animated GIF showing the evolution of the codebase. It visualizes file creation, deletion, and code changes, creating a compelling, shareable artifact that tells the story of a project.

Shared workflow skills for agent-driven engineering across repos.

Zero-dependency TypeScript decorators for Node/backend apps — one self-documenting decorator replaces a block of boilerplate: config injection, validation, resilience (retry/timeout/circuit-breaker/cache), secret redaction, observability, Express REST controllers, and LLM-agent tools & guardrails.

obsura-web

TypeScript coding-agent runtime showcase with policy-gated tools, audit logging, secret redaction, fake/OpenAI-compatible providers, and plugin loading.