A cognitive-governance kernel that makes AI agents show their work before they act. Before any high-impact action (git push, deploy, migration), a deterministic hook requires the agent to commit its reasoning to disk — knowns, unknowns, assumptions, and a falsifiable disconfirmation — and refuses to proceed until the artifact is real. Verified lessons become hash-chained, context-scoped protocols that resurface at the next matching decision, so the agent gets sharper on your codebase over time. Ships as a Claude Code plugin and a Python kernel with a vendor-neutral adapter layer.
PythonClaude Code plugin (hooks / skills / agents)TypeScriptNext.jsVercel
Made a website for my partner with Bugcat-Capoo GIFs
HTML, CSS , Javascript
Developed and deployed a web application for my battalion's event management system
Python (flask, smtp, pandas)HTML, CSS , JavascriptAWS EC2NginxGunicorn
Built ML models to predict heart disease. Learned about non-parametric approaches and its tradeoffs
Pythonpandasnumpymatplotlibscikit-learnStatistical Modeling
Learned how facial recognition system works through Principal Component Analysis in Linear Algebra
Dimensionality ReductionLinear AlgebraStatistical Modeling
First project to understand statistical modeling to predict S&P Index based on 15 macroeconomic indicators I extracted from TraidingView
Time Series AnalysisLinear RegressionAugmented Dickey-Fuller TestGranger Causality Test