xohzzwn6kcj9/claude-code-harness-kit
A kit of Claude Code hooks (read-only auto-approve, secret guards, opinionated bash guards) + repo-radar, a read-only repo-analysis skill. Less prompt friction, no less safety.
A kit of Claude Code hooks (read-only auto-approve, secret guards, opinionated bash guards) + repo-radar, a read-only repo-analysis skill. Less prompt friction, no less safety.
npx add-skill xohzzwn6kcj9/claude-code-harness-kitA kit of Claude Code hooks (read-only auto-approve, secret guards, opinionated bash guards) + repo-radar, a read-only repo-analysis skill. Less prompt friction, no less safety.
Host-agnostic, industry-agnostic catalog of harnesses, knowledge objects, logic & rule packs, tools, pipelines, processors, personas, model adapters, rubrics, datasets, and benchmarks for AI-assisted systems. Emits to Croissant, MCP, Agent Skills, HF cards, CycloneDX-ML, OpenLineage, and more.
A Unified Virtual Filesystem For AI Agents
Industrial Deep Diagnostic Platform — full-stack application for root cause analysis with Claude Code skill integration
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
Rag Implementation
Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.