What's on the bench.
React Native
React Native mobile patterns, platform-specific code
Python
Python development with ruff, mypy, pytest - TDD and type safety
Pwa Development
Progressive Web Apps - service workers, caching strategies, offline, Workbox
Project Tooling
gh, vercel, supabase, render CLI and deployment platform setup
Posthog Analytics
PostHog analytics, event tracking, feature flags, dashboards
Polyphony
Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
Playwright Testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD
Nodejs Backend
Node.js backend patterns with Express/Fastify, repositories
Ms Teams Apps
Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API
Mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies
Medusa
Medusa headless commerce - modules, workflows, API routes, admin UI
Maggy 2
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.
LLM Patterns
AI-first application patterns, LLM testing, prompt management
Klaviyo
Klaviyo email/SMS marketing - profiles, events, flows, segmentation
Iterative Development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically
Icpg
Intent-Augmented Code Property Graph — tracks WHY code exists via ReasonNodes with formal contracts, 6-dimension drift detection, and 3 canonical pre-task queries for autonomous development
Gemini Review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration
Flutter
Flutter development with Riverpod state management, Freezed, go_router, and mocktail testing
Firebase
Firebase Firestore, Auth, Storage, real-time listeners, security rules
External Model Delegation
A `UserPromptSubmit` hook classifies every user prompt into one of six cost/performance tiers. The hook injects `additionalContext` instructing Claude to run a specific delegation script and return the output.
Existing Repo
Analyze existing repositories, maintain structure, setup guardrails and best practices
Database Schema
Schema awareness - read before coding, type generation, prevent column errors
Cross Agent Delegation
Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents
Cpg Analysis
Deep code property graph analysis with Joern CPG (AST+CFG+PDG) and CodeQL for control flow, data flow, taint analysis, and security auditing