How I work with agentic AI: personal patterns, homelab infra (vLLM, Ollama, Grafana Alloy, LibreChat), project scaffolding. Not best practices - what I run.
This repository also configures its own agents. See what agentic-ai-homelab tells them →
Skill Claude CodeCodex
Check a message to another Claude session (ingestion, mobile, homelab, orrery, a subagent) before sending it — refuses leftover placeholders ( , {x}, $VAR, TODO, a bare ALLCAPSTOKEN) and any state claim (held, deployed, applied, pushed, approved, verified, green, done …) that has no proof command passing right now.…
Skill Claude CodeCodex
Prove a telemetry path end to end with one labelled test signal, then delete it — a GlitchTip error, an Umami event or a Langfuse trace is sent, read back from the target, checked ABSENT from sibling targets (prod vs dev, staging vs prod), deleted, and the deletion confirmed. Ends with PROBE PASS/FAIL. Use when asked…
Skill Claude CodeCodex
Establish a UX baseline for an app (a clickable mockup of every screen, painted by the app's own styles, with real data and guards), review it with independent reviewers, decide with the operator one decision record at a time, and prototype the decisions as before/after variants in a guided review the operator…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: