Install Gemini CLI and run your first prompt
Read the field note below to see how we apply this pattern in real Gemini CLI projects.
Turn this cable into a shipping system.
We help teams deploy reliable AI workflows with architecture, implementation, and hardening support.
Install Gemini CLI and run your first prompt
The first time we ran Gemini CLI we expected it to behave like a browser-based chat. It doesn't. It's a terminal agent that reads your project, runs commands, and edits files — the same category as Claude Code, not the same category as gemini.google.com.
What we tried
We installed it, opened a project directory, and typed a question. It answered. Then we typed an instruction to edit a file. It edited it, explained what it did, and waited for the next instruction. That's the loop.
What happened
The thing that surprised us was how much context it picked up without being told. It reads the directory structure, infers the stack from config files, and adjusts its answers accordingly. A bare question like "how should I add auth?" landed differently in a Next.js project than in a Flask project — without us specifying anything.
What we learned
Install:
npm install -g @google/gemini-cli
Requires Node.js 18+. Verify with:
gemini --version
Authenticate:
gemini auth
Opens a browser OAuth flow. One-time setup per machine. Uses your Google account — no separate API key needed for personal use. For team or CI use, set GEMINI_API_KEY instead.
Run it:
cd your-project
gemini
Always start from your project root. Gemini CLI reads files relative to where you launch it. Starting from ~ gives it no useful context.
First useful action:
Type /help to see all slash commands. The ones worth knowing immediately:
/tools— list what it can do (read files, run shell, search web)/memory— show what it's retaining across turns/stats— token usage for the current session@filename— attach a specific file to your next prompt
GEMINI.md:
The single highest-leverage thing you can do on day one is create a GEMINI.md in your project root. Gemini CLI reads it automatically on every session start. Without it, you re-explain your stack, conventions, and constraints on every session. Day 2 covers what to put in it.
Next
- Next cable — Your first GEMINI.md: what to put in it and why.
Quick answers
What do I get from this cable?
You get a dated field note that explains how we handle this onboarding workflow in real Gemini CLI projects.
How much time should I budget?
Typical effort is 10 min. The cable is marked beginner.
How do I install the artifact?
This cable is guidance-only and does not ship an installable artifact.
How fresh is the guidance?
The cable is explicitly last verified on 2026-04-17, and includes source links for traceability.
More from @frenxt
Your first GEMINI.md
Every session without a `GEMINI.md` starts from zero. You re-explain your stack. You re-explain your conventions. You catch mistakes that your context would have prevented. A well…
Team GEMINI.md: shared AI conventions for multi-developer projects
When one engineer's Gemini CLI session produces different code shape than another's, the root cause is almost always context — not the tool. One person has a `GEMINI.md` with nami…