What is vibes GEMINI.md?

A repository instruction file containing guidance for using Gemini CLI, Google's command-line assistant, to plan and work through coding tasks.

Use it when working on the repository's Marp presentation or when following its Gemini-based task, role, and context prompts.

It gives the assistant project context and repeatable prompting patterns for breaking complex work into smaller steps.

vibes GEMINI.md — Instructions file for Gemini CLI by wandb: A repository instruction file containing guidance for using Gemini…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/wandb/vibes/gemini-md

Clone the repo

git clone --depth 1 https://github.com/wandb/vibes

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wandb/vibes/gemini-md.svg)](https://agentmods.dev/instructions/wandb/vibes/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/wandb/vibes/gemini-md"><img src="https://agentmods.dev/badge/instructions/wandb/vibes/gemini-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 693 This file is loaded in full into every session.

When invoked 693 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00693	$0.00693
Opus 5	$0.00347	$0.00347
Sonnet 5	$0.00139	$0.00139
Haiku 4.5	$0.00069	$0.00069

Measured 2d ago against content hash fc811ec7b85d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibes GEMINI.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

GEMINI.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Instructions

This repo contains a presentation defined in slides.md. We use marp to render it. After making any changes you can run pnpm slides to regenerate the presentation at index.html.

The below information is less for you and more for users of the repo so please disregard instructions below this line.

=================================

Gemini CLI Prompting Guide

Basic Usage

gemini "Your prompt here"

Agentic Prompting Techniques

1. Task Decomposition

Break complex tasks into smaller, manageable steps:

gemini "I need to build a web scraper. First, help me understand what libraries I should use for Python web scraping."

2. Role-Based Prompting

Assign specific roles to get targeted responses:

gemini "Act as a senior software engineer. Review this code and suggest improvements: [paste code]"

3. Chain of Thought

Ask Gemini to show its reasoning:

gemini "Think step by step: How would you debug a memory leak in a Node.js application?"

4. Context Setting

Provide relevant context for better responses:

gemini "I'm working on a React TypeScript project using Vite. How should I configure environment variables for different deployment environments?"

5. Iterative Refinement

Build on previous responses:

gemini "Based on your previous suggestion about using React Query, show me how to implement error handling for API calls."

Code-Specific Prompts

Code Review

gemini "Review this function for potential bugs, performance issues, and best practices: [code]"

Documentation

gemini "Generate comprehensive JSDoc comments for this TypeScript class: [code]"

Testing

gemini "Create unit tests for this function using Jest: [code]"

Refactoring

gemini "Refactor this code to use modern JavaScript features and improve readability: [code]"

Best Practices

Be Specific: Include file types, frameworks, and constraints
Provide Context: Mention your project structure and requirements
Ask for Alternatives: Request multiple approaches when possible
Request Explanations: Ask "why" to understand the reasoning
Iterate: Build on responses to refine solutions

Read the full file on GitHub · 108 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 108 lines · 693 tokens per session scan A fc811ec7b85d

Subscribe to this mod's changes

vibes GEMINI.md is an instructions file published in the GitHub repository wandb/vibes (37 stars, last pushed 1y ago), licensed Apache-2.0. It adds 693 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.

Building agents Planning

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vibes GEMINI.md