Code
Public repositories tagged public-portfolio. Auto-pulled from GitHub, refreshed every six hours.
Methodology and tooling for auditing your own Claude Code session logs. Schema, ingest pipeline, analyses, and LLM-assisted verification-debt audit.
Runnable companion code for articles published on mpiv.ai/blog covering AI agent infrastructure (LiteLLM proxy, agent observability, eval pipelines, model gateways).
Loop-discipline patterns for Claude Code: Stop hooks with evidence files, three skills mapped to common failure modes, and reference samples for structured shell, structured tests, and prompt caching.