Geoffrussy User Manual

The official guide to operating the Ussyverse's premier autonomous agent.

01. Installation

Geoffrussy is distributed as a single Go binary. It requires no external dependencies other than an active internet connection for API access.

# Install via Go Toolchain
$ go install github.com/mojomast/geoffrussy@latest

# Verify Installation
$ geoffrussy version

02. Initialization

Before your first run, you must initialize the configuration. This sets up your strategy for the Planner (Brain) and the Executor (Hands).

Strategy Guide: We recommend Claude Opus 4.5 or Gemini 3 Pro for the Planner. For the Executor, configure GLM 4.7 or Llama 5 to keep costs negligible while maintaining high velocity.

$ geoffrussy init

This will create a ~/.geoffrussy/config.yaml file where you can define your model routing table.

03. The Interview (DevUssy Protocol)

This is where the magic happens. Instead of writing a prompt, you enter a dialogue. Geoffrussy uses the integrated DevUssy v2 engine to interview you about your project.

mojo@linux:~$ geoffrussy interview
[GEOFF] Initializing Interview Protocols...
[GEOFF] Hello! I'm ready to architect your next system. What are we building today?
> I want to build a CLI tool that tracks my coffee consumption.
[GEOFF] Interesting. A few questions to clarify scope:
1. Should this data be stored locally (SQLite/JSON) or in the cloud?
2. Do you need visualization (charts/graphs) in the terminal?
3. What specific metrics matter? (Caffeine content, brand, time of day?)

After the interview, Geoffrussy generates a devplan.md. This is the DevUssy Artifact. It contains the architectural blueprint and a step-by-step execution plan.

04. Execution

Once you approve the plan, Geoffrussy begins the orchestration loop.

The Planner

Reads the specplan.md. Uses Claude Opus 4.5 to reason about dependencies and architectural integrity.

The Executor

Dispatches tasks to GLM 4.7 or Llama 5. These models are fast, cheap, and perfect for writing implementation code.