Value Engineer @ Ivanti · I build open-source tooling for AI coding agents, plus native iOS and data products — from App Store releases to live market systems.
App Store release · Portfolio · Public source · GitHub achievements
Small, standalone tools. All MIT, all zero-dependency, all with real test suites and tagged releases.
| Repo | What it does |
|---|---|
| agentsmith | Mines your repo's actual conventions into an AGENTS.md, with evidence for every rule — and detects drift in CI when the file and the repo disagree. No LLM, no network. |
| burnrate | What your coding agent actually cost, read from local session logs, plus a hook that caps spend mid-session. Fixes a ~3× overcount that naive token counters hit. |
| tripwire | Offline audit of the skills, MCP servers, hooks, and permissions installed for your agent. Shows your real capability surface, then flags how it can be turned against you. |
| contexttest | A/B testing for AGENTS.md. Runs the same task from the same commit under two instruction sets and reports which one measurably worked. |
| gtm-skills | Nine production-grade go-to-market skills for agents — business cases, ICP scoring, pricing, market sizing — on a tested arithmetic engine with an assumption ledger. |
| contexttest-findings | Measured results for common AGENTS.md rules. Twelve live agent trials so far; the popular "add nothing beyond what was asked" rule showed no measurable effect. Null results published on purpose. |
A theme runs through all five: be honest about what you don't know. The business cases grade their own evidence, the convention miner refuses to assert a rule from four files, the cost tool names models it can't price instead of costing them at zero, and the security scanner treats a false positive as the failure mode that matters.
| Product | State | Built with | Proof |
|---|---|---|---|
| Nalee — honest product-toxin scoring backed by a 2.4M+ product library | Live on the App Store | Expo · Supabase | App Store · Site |
| Goals — a cinematic goal-discovery and execution command center for turning intention into daily progress | iOS / TestFlight lane + live web | SwiftUI · TypeScript · Supabase | Live · Private source |
| Tapt — beer discovery, Passport collecting, and a live beer market | Native iOS release lane | Swift · Supabase | Source · Site |
| Mend — a free, private journey and shared-space app for relationship repair | TestFlight | Expo · TypeScript · Supabase | Source |
| Lore — geospatial place stories hiding in the streets around you | Native iOS / TestFlight lane | Swift · Supabase | Source |
| Precision Algorithms — a published prediction-market models desk | Live web product | Data · Web | Live |
| SqueezeRadar — short-squeeze signals with live price overlays | Live web product | Next.js · Market data | Live |
| Penny Catcher — volume and flow radar for quiet, low-priced tickers | Live web product | Web · Market data | Live |
agentsmith CI (Python 3.9–3.13 + self-audit) · tripwire CI (plants a live attack each run) · Tapt release automation · Lore CI and TestFlight · Merged pull requests · Achievements
Ivanti · Value engineering and AI adoption strategy for enterprise clients. I built the Capability & Maturity Assessment framework.
- Native: Swift, SwiftUI, Expo, React Native
- Web: TypeScript, Next.js, React, Tailwind CSS, Node.js
- Data and delivery: Supabase, Python, GitHub Actions, Vercel
- Agent tooling: Claude Code skills and plugins, MCP, static analysis, dependency-free Python CLIs
- MBA, Data Analytics concentration — Rowan University
- First-generation Polish-American, based in New Jersey
- 18K+ LinkedIn followers and 3× Top Voice
- Philly sports across all four, golf whenever possible
- 130 memorized digits of Pi, listed on the Pi World Ranking List
