Scenario: Starting a brand-new project (greenfield)

When to use #

You have no code yet. You want a fresh repo scaffolded with the aidokit workflow, then walk straight into your first task inside an AI CLI. This is the fastest path from zero to a running Intake → Plan → Build loop.

At a glance #

%%{init: {
  "theme": "base",
  "themeVariables": {
    "fontFamily": "ui-sans-serif, system-ui, -apple-system, Segoe UI, sans-serif",
    "fontSize": "14px",
    "primaryColor": "#eff6ff",
    "primaryTextColor": "#0f172a",
    "primaryBorderColor": "#2563eb",
    "lineColor": "#475569",
    "secondaryColor": "#f1f5f9",
    "tertiaryColor": "#ffffff",
    "clusterBkg": "#f8fafc",
    "clusterBorder": "#cbd5e1"
  }
}}%%
flowchart LR
  classDef actor    fill:#ede9fe,stroke:#6d28d9,color:#1e1b4b,stroke-width:1.2px;
  classDef cli      fill:#dbeafe,stroke:#1d4ed8,color:#0c1f4a,stroke-width:1.4px;
  classDef adapter  fill:#cffafe,stroke:#0e7490,color:#083344;
  classDef pack     fill:#dcfce7,stroke:#15803d,color:#052e16;
  classDef core     fill:#fef9c3,stroke:#a16207,color:#422006;
  classDef artifact fill:#f1f5f9,stroke:#475569,color:#0f172a;
  classDef stop     fill:#fee2e2,stroke:#b91c1c,color:#7f1d1d,stroke-dasharray:4 3;
  classDef ok       fill:#ecfdf5,stroke:#047857,color:#064e3b;
  classDef external fill:#fff7ed,stroke:#c2410c,color:#431407;
  you(["you"]):::actor
  mk["mkdir + git init"]:::cli
  init["aidokit init"]:::cli
  emitted["/ + docs/ + agent-artifacts/"]:::artifact
  cli["your AI CLI"]:::external
  you --> mk --> init --> emitted --> cli

Step-by-step #

1. Create the project directory #

mkdir my-app && cd my-app
git init

Expected: a clean directory with an empty .git/.

2. Scaffold the workflow #

npx aidokit init --adapter <claude-code|codex|copilot> --tier standard --stack node-ts --yes

Pre-v1.0: replace npx aidokit with node /path/to/aidokit/packages/cli/dist/bin/aidokit.js.

Expected: the picked adapter's engine directory (.claude/, .codex/, or .copilot/), plus docs/, agent-artifacts/, .aido/adapter.md written in ~18s.

3. Open your AI CLI #

If Claude Code

claude

If Codex

codex

If Copilot

gh copilot

Expected: the CLI loads with the scaffolded skills, agents, and slash commands available.

4. Kick off the workflow #

Inside the AI CLI:

/intake "describe your project in one paragraph"

Expected: Intake stops before any code; review the brief in agent-artifacts/, approve, then run /implement-task.

Common mistakes #

Skipping git init — aidokit refuses to scaffold into a non-git directory.
Forgetting --yes in CI contexts; it accepts defaults but never bypasses security-sensitive prompts.
Running /implement-task before approving the Intake brief — the hard-stop gate blocks it.