Get Started

Quickstart

From zero to your first verified task in under 10 minutes.

Total: ~8 minutes· No external services required

Before you begin — checklist

  • Git installed
  • A project directory (any language)
  • Cursor, Claude Code, Gemini CLI, Codex, or OpenCode installed
1
1 min

Clone galdr

Clone the repo to your home directory. One-time setup per machine.

bash
git clone https://github.com/wrm3/galdr.git ~/galdr
2
1 min

Copy template into your project

Copy the galdr system files into your project root.

bash
# macOS / Linux
cp -r ~/galdr/template_full/. /path/to/your-project/

# Windows (PowerShell)
Copy-Item -Recurse -Force "$HOME\galdr\template_full\*" ".\"
3
2 min

Initialize galdr in your IDE

Open your project in your AI IDE. Run the setup command — the agent will ask your project name, mission, and tech stack.

chat
@g-setup

After setup, run @g-status to confirm everything loaded.

chat
@g-status
4
1 min

Create your first task

Pick something small and concrete — a bug fix, a new endpoint, a UI component. Pass it as an argument.

chat
@g-task-new Fix the broken 404 page styling

Galdr creates .galdr/tasks/task001_fix_404_page_styling.md with acceptance criteria. Review it — edit the criteria if needed.

5
2 min

Implement the task

Run the implementation command. The agent reads the task, implements it, checks each acceptance criterion, and marks the task [🔍].

chat
@g-go-code
Important: [🔍]means "awaiting verification" — it is NOT done yet. The task stays in this state until a separate verification pass confirms it.
6
1 min

Verify in a new session

Open a new chat window (new agent session). Run the review command. This is the adversarial gate — a structurally separate agent checks the implementation.

chat
@g-go-review

If all criteria pass: the task is marked [✅] complete. If something fails: it goes back to pending with a FAIL note, and you repeat from step 5.

🎉 You just completed your first galdr cycle

Create → Implement → Verify → Complete. That's the core loop. Everything else in galdr — constraints, PCAC topology, vault memory, skill packs — builds on top of this foundation.

Next steps