vern-bot

Runs a multi-LLM discovery pipeline (Default 5-step or Expanded 7-step) that chains analysis, refinement, chaos-checking, and consolidation across LLMs, then breaks results into actionable VTS tasks. Use when the user wants to explore, validate, or plan an idea through multiple AI perspectives.

Delivers high-quality, production-grade code using Opus-level reasoning — clean architecture, thorough error handling, tests, and documentation. Use when the user asks for elegant solutions, quality-first code, architectural excellence, or best-practice implementations.

Performs deep, multi-pass exploration of a problem using Claude sub-agents — runs 3+ planning passes from different angles, then synthesizes insights into a holistic solution. Use when the user wants deep thinking, creative exploration, unconventional approaches, or multi-perspective analysis of a complex problem.

Generates comprehensive code and thorough analysis using OpenAI Codex sub-agents — handles large-scale code generation, exhaustive edge case coverage, and detailed boilerplate scaffolding. Use when the user wants comprehensive output, large code generation, thorough analysis, or 'give me everything' solutions.

Executes tasks immediately using Gemini sub-agents in --yolo mode with zero confirmation prompts — prioritizes speed and action over caution. Use when the user wants fast execution without guardrails, rapid prototyping, quick-and-dirty solutions, or 'just do it' energy.

Generate a new Vern persona using AI

Rerun a discovery pipeline on an existing project. Cleans previous output and re-runs with fresh config.

Run VernHole on existing discovery output. Point the council at a consolidation or master plan and get fresh perspectives.

Create a new discovery idea folder with standardized input/output structure. Use when the user wants to prepare an idea for discovery.

Historian Vern - Index a directory of input files into a structured concept map with source references.

VernHole / K-Hole Vern - Be careful what you wish for. Random Vern personas do discovery on your idea. The more the merrier.

Post-hoc Oracle operations - consult the Oracle on existing VernHole output or apply an Oracle vision to rewrite VTS tasks.

Oracle Vern - The ancient seer who reads the council's chaos and finds the signal. Pattern recognition across perspectives.

Academic Vern - Needs more research. Cites sources, considers prior art, wants peer review.

Architect Vern - Systems design, scalable architecture, production-grade thinking. The blueprints before the build.

Enterprise Vern - Needs 6 meetings and a committee first. Process, governance, compliance.

Inverse Vern - Contrarian takes only. Whatever the consensus is, he's against it.

Vern the Mediocre - missed his alarm, throwing down code fast. Uses Sonnet, watches token consumption.

Nyquil Vern - brilliant as Vernile but the NyQuil is kicking in. Haiku-level brevity.

Optimist Vern - Everything will be fine! Sunny-side-up. Encouragement and can-do energy.

Paranoid Vern - What could possibly go wrong? Everything. Risk assessment and failure mode specialist.

Retro Vern - We solved this with cron jobs and a CSV in 2004. Grizzled veteran, historical perspective.

Startup Vern - MVP or die trying. Lean, fast, validate assumptions, iterate or pivot.

UX Vern - Cool architecture, but can the user find the button? Empathy-driven design thinking.