Making AI agents trustworthy, secure, one tool at a time.
Product Security Engineer at Corgea.
Spok — Spec-Driven Development for AI Coding Agents
Agents and humans start building before they agree on what to build. Spok gives your coding agent four workflow skills — explore, propose, apply, archive — to settle the spec, ship one thin slice at a time, and fold the final behavior back into living specs.
dx — Local-First Orchestrator for Coding Agents
Running several coding agents means juggling CLIs, prompts, and review state by hand. dx drives Claude, Codex, Cursor, and others from one CLI: it runs prompts in parallel, composes TOML/Markdown workflows, manages GitHub review approval, and keeps run evidence under ~/.dx.
ub-cli — Uncle Bob's ub-mode Quality Tools in One CLI
All credit goes to Robert C. Martin (Uncle Bob). He built ub-mode and its three engines: Crapper (CRAP scores), Dryer (duplicate detection), and Mutator (mutation testing). ub-cli is a thin wrapper that packages them as one installable ub command with a combined ub check gate.
Inconnu — Zero-Trust Bridge for RAG
RAG systems access sensitive data without proper security boundaries. Inconnu is a zero-trust security layer that sits between your RAG pipeline and your data sources.
Harness — Quality Guardrails for AI Coding Agents
AI coding agents generate code without consistent structure or quality standards. Harness provides opinionated project templates with built-in guardrails so agents produce reliable, maintainable code from the start.
Interlocks — Deterministic Python Quality Loop
Local checks, CI, and agent-authored pull requests drift apart. Interlocks runs one deterministic Python quality loop — lint, typecheck, test, coverage, and more — behind a single command so humans and agents review against the same output.
Wando — Security Checklist for Teams
Teams lack actionable security guidance. Wando provides curated, practical security and privacy recommendations you can actually follow.