I build and test agent tooling in Python, TypeScript, and Shell. At Independent Developer, I direct AI coding agents with written briefs, then rerun tests and review diffs before committing.
I built Leap Frog, a CLI and set of drop-in skills that estimates tasks against a token budget, gates commands behind scoped backups, and creates checkpoints and handoffs for another agent. It has 459 passing tests and CI.
I also built current-registry, a fact-verification registry that requires agreement across three separate reads before marking a sentence supported, and logs splits or failed reads with their reasons. Its 301 passing tests use fictional data only.
Before software, I served as a U.S. Marine and worked as a Deputy, including as a School Resource Deputy and Detention Deputy. I was certified in Law Enforcement and Corrections, and wrote legally defensible documentation under time pressure and accountability.
