By jdonohoo
Run a multi-LLM discovery pipeline that chains analysis, refinement, and stress-testing across 16 AI personas to explore ideas, validate plans, and break results into actionable tasks. Includes council review, risk analysis, MVP scoping, and code generation via OpenAI, Gemini, and Claude sub-agents.
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.
The ultimate multi-LLM discovery process. Your idea goes through the gauntlet and emerges battle-tested.
Enterprise Vern - Needs 6 meetings and a committee first. Process, governance, compliance.
Generate a new Vern persona using AI
Academic Vern - Needs more research. Cites sources, considers prior art, wants peer review. Use for thorough analysis and evidence-based decisions.
Architect Vern - The one who draws the blueprints before anyone touches a keyboard. System design, scalable architecture, production-grade thinking. Use when you need systems architecture, refactoring plans, or code that'll still make sense in two years.
Enterprise Vern - Needs 6 meetings and a committee first. Process, governance, compliance. Use when you need enterprise-grade rigor and bureaucratic thoroughness.
Vernile the Great - Opus excellence. The agent other agents aspire to be. Use for high-quality architectural work, elegant solutions, and when excellence matters.
Historian Vern - The one who actually reads the whole thing. Gemini's 2M context window digests massive inputs into indexed concept maps. Use when you need to catalog, cross-reference, or make sense of large input folders.
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.
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.
Enterprise Vern - Needs 6 meetings and a committee first. Process, governance, compliance.
Generate a new Vern persona using AI
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
https://jdonohoo.github.io/vern-bot/
AI discovery pipelines with personality disorders. Multi-LLM orchestration, competing AI personas, VernHole council tiers, Oracle vision, Historian indexing, and chaos-to-clarity workflows.
Now available as a standalone terminal app — no Claude Code required.
| Command | Model | Best For |
|---|---|---|
/vern:mediocre | Sonnet | Quick fixes, scripts, "just make it work" |
/vern:great | Opus | Architecture, elegant solutions, quality code |
/vern:nyquil | Haiku | Quick answers, minimal output, brevity |
/vern:ketamine | Opus | Deep exploration, multi-pass planning, patterns |
/vern:yolo | Gemini | Fast execution, no guardrails, chaos |
/vern:mighty | Codex | Comprehensive code gen, thorough analysis |
| Command | Model | Best For |
|---|---|---|
/vern:architect | Opus | Systems design, scalable architecture, production-grade thinking |
/vern:inverse | Sonnet | Devil's advocate, stress-testing assumptions |
/vern:paranoid | Sonnet | Risk assessment, finding failure modes |
/vern:optimist | Haiku | Encouragement, positive framing, can-do energy |
/vern:academic | Opus | Evidence-based analysis, citing prior art |
/vern:startup | Sonnet | MVP thinking, lean approach, cut scope |
/vern:enterprise | Opus | Governance, compliance, process rigor |
/vern:ux | Opus | User experience, empathy-driven design, journey mapping |
/vern:retro | Sonnet | Historical perspective, proven tech, cutting through hype |
/vern:oracle | Opus | Reads the council's wisdom, recommends VTS task changes |
/vern:historian | Gemini | Indexes massive input folders into structured concept maps |
| Situation | Command |
|---|---|
| "I need this NOW" | /vern:mediocre |
| "I need this RIGHT" | /vern:great |
| "Just answer the question" | /vern:nyquil |
| "Help me think through this" | /vern:ketamine |
| "YOLO" | /vern:yolo |
| "Give me EVERYTHING" | /vern:mighty |
| "Design the system" | /vern:architect |
| "Play devil's advocate" | /vern:inverse |
| "What could go wrong?" | /vern:paranoid |
| "Hype me up" | /vern:optimist |
| "What does the research say?" | /vern:academic |
| "What's the MVP?" | /vern:startup |
| "Enterprise-grade analysis" | /vern:enterprise |
| "Can a real person use this?" | /vern:ux |
| "Haven't we solved this before?" | /vern:retro |
| "What did the council actually say?" | /vern:oracle |
| "Index these 50 input files" | /vern:historian |
| "Create a custom persona" | /vern:generate |
| "I want chaos/creativity" | /vern:hole |
| "Full project discovery" | /vern:discovery |
| "What commands are there?" | /vern:help |
| "Configure LLMs/pipeline" | /vern:setup |
/plugin marketplace add https://github.com/jdonohoo/vern-bot
/plugin install vern
brew tap jdonohoo/vern
brew install vern
To update later: brew upgrade vern
scoop bucket add vern https://github.com/jdonohoo/homebrew-vern
scoop install vern
To update later: scoop update vern
winget install jdonohoo.vern
To update later: winget upgrade jdonohoo.vern
Download the latest binary from GitHub Releases:
# macOS Apple Silicon
curl -Lo vern https://github.com/jdonohoo/vern-bot/releases/latest/download/vern-darwin-arm64
chmod +x vern
sudo mv vern /usr/local/bin/
git clone https://github.com/jdonohoo/vern-bot.git
cd vern-bot/go
go build -o bin/vern ./cmd/vern
sudo cp bin/vern /usr/local/bin/
Run the setup wizard to detect your LLMs and configure defaults:
vern setup
Then launch the TUI:
vern tui
Available binaries: macOS (Intel + Apple Silicon), Linux (x64 + ARM64), Windows (x64 + ARM64).
Required: At least one LLM CLI installed — claude, codex, gemini, or copilot.
Launch the interactive terminal UI — no Claude Code needed:
vern tui
npx claudepluginhub jdonohoo/vern-bot --plugin vernCollect and synthesize opinions from multiple AI Agents for Claude Code
Theory-grounded product-thinking discipline for AI agents. 49 skills, 15 theory gates, six diamond scales (Purpose to Market). Discovery to delivery with evidence gates that block on insufficient evidence.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Tools for crafting, reviewing, analyzing, refining, and optimizing LLM prompts for clarity, precision, goal effectiveness, and token efficiency
Compile humans into AI agents through deep interviews. Conducts comprehensive behavioral interviews, analyzes work artifacts via MCP tools, and generates installable Claude Code plugins that embody a person's decision-making, communication style, and expertise.
The Answer Computer — reasoning tools for brainstorming, planning, architecture design, and deep thinking