Get started with Baxter

Baxter is a plain-text harness — a folder you drop into any project. No accounts, no subscriptions, no special tooling, and no git command required — download it, unzip it, and you're in.

What you'll have at the end of this guide

  • Baxter installed and reading your codebase
  • Your first artefact generated and saved to git
  • A clear understanding of the core skills (templated artefacts) and the power skills (slash commands)

Most important step — where does my code go?

coderepo/

Copy or symlink your project's source code into coderepo/. A full codebase, part of one, or a starter scaffold all work — Baxter analyses whatever is there. Nothing built yet? Write a BRD first; it's the one artefact that doesn't need code.

# Copy your project in
cp -r /path/to/your/project coderepo/

# Or symlink it (keeps one copy on disk)
ln -s /path/to/your/project coderepo/src

Gitignored and never committed — your code stays private to your machine. The same applies to artefacts/: everything generated stays local, never pushed to GitHub.

Full folder layout, and codebase-vs-no-codebase reasoning →

1

Download the harness

No git command needed.

Unzip it, then use it standalone or copy the folder into an existing project repo. The harness is self-contained — it does not affect your project's code or CI.

Prefer git? git clone https://github.com/glovarix/agentic-ba.git

2

Add your codebase

Copy or symlink your project's source code into coderepo/. This is what Baxter reads to verify every artefact — required for everything except an initial BRD.

cp -r /path/to/your/project coderepo/

Your code never leaves your machine

Everything inside coderepo/ is gitignored — it is never committed or pushed. If your codebase is large, a symlink works just as well as a copy.

Baxter reads coderepo/ to verify every artefact against your real codebase — checking technical feasibility, logic consistency, data model implications, role and permission logic, and flagging missing edge cases.

3

Open in your AI agent

Open the folder in your AI agent. Baxter's instructions are already in the right file for each tool — the agent loads them automatically with no setup.

Recommended for beginners

VS Code + the Claude Code extension

If you are new to this, install VS Code and add the Claude Code extension from the marketplace. You get a familiar editor with Baxter running in a side panel — no terminal required. Open the agentic-ba folder, open the Claude Code panel, and start pasting requests.

It works just as well in the Claude Code CLI, Cursor, or VS Code with GitHub Copilot — each picks up its own instruction file:

Tool Instruction file loaded automatically
VS Code + Claude Code extension (recommended) CLAUDE.md
Claude Code (CLI) CLAUDE.md
Cursor .cursor/rules/baxter.mdc
GitHub Copilot .github/copilot-instructions.md
Any agent following the agents.md standard AGENTS.md

The instruction files are identical (both Claude Code editions read CLAUDE.md). A pre-commit hook keeps them in sync — edit CLAUDE.md and the others update automatically on your next commit. Run this once after cloning to activate it:

git config core.hooksPath .githooks
4

Paste a request — any raw text

example requests — paste exactly as received

"The login page returns a 500 error when the user submits without a password"

"Write up the BRD for recurring invoices"

"I need test cases for the billing module — mandatory fields and role access"

"Add a print to PDF button to the customer profile page"

Baxter classifies the request, tells you which template it will use, and asks for a one-word confirmation before generating anything. You can reply with the artefact code (e.g. BR), a number, or just proceed.

That's it — you're running. The detail lives in Docs.

Or browse all documentation →

Baxter The Agentic BA

Ready to work with Baxter?

Open source and free. Drop the harness into any project, open it in Claude Code, Cursor, or GitHub Copilot, and paste your first raw request.