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.
npx agentmods add instructions/aaronhuff/awesome-gemini/gemini-mdgit clone --depth 1 https://github.com/aaronhuff/awesome-geminiWrote 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.
[](https://agentmods.dev/instructions/aaronhuff/awesome-gemini/gemini-md)<a href="https://agentmods.dev/instructions/aaronhuff/awesome-gemini/gemini-md"><img src="https://agentmods.dev/badge/instructions/aaronhuff/awesome-gemini/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00554 | $0.00554 |
| Opus 5 | $0.00277 | $0.00277 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
awesome-gemini 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Welcome to the Gemini Documentation
This repository contains a collection of guides and "gems" to help you get the most out of the Gemini family of models.
Introduction to Gemini
Gemini is a family of multimodal AI models developed by Google. They are capable of understanding and processing text, code, images, and video.
Getting Started
To learn how to write effective prompts for Gemini, please refer to our Prompting Best Practices guide. For hands-on tutorials and practical examples, check out the Gemini API Cookbook.
Project Structure
This repository is organized into two main categories:
- Gems: These are pre-built custom instructions that you can use to create specialized AI assistants. They are located in the
gems/directory. - Guides: These are in-depth tutorials and walkthroughs that explain how to use Gemini for a variety of tasks. They are located in the
guides/directory.
When adding new content, please make sure to place it in the appropriate directory. If you are adding a new set of custom instructions, it should be a "gem". If you are adding a tutorial or a "how-to" article, it should be a "guide".
Gems
Gems are pre-built custom instructions that you can use to create specialized AI assistants.
- Adaptive Fitness Coach: A personal fitness coach that creates customized workout and nutrition plans.
- Financial Advisor: A personal finance assistant that helps you manage your budget, savings, and investments.
- Google Workspace Assistant: Turn Gemini into a powerful productivity assistant for Google Workspace.
Guides
Our guides provide in-depth information on how to use Gemini for a variety of tasks.
- AI Studio Guide: Learn how to use Google AI Studio to prototype and test your prompts.
- Gemini Code Review Guide: See how to use Gemini to automatically review your code on GitHub.
- Jules: Your AI Coding Partner: Learn how to interact with Jules, your AI software engineer.
- Learning Tools Guide: Explore how to use Gemini as a personalized learning companion.
- Prompting Best Practices: Learn how to write effective prompts for Gemini.
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.
- 4d ago First seen · 40 lines · 554 tokens per session scan A a6234435e55a
awesome-gemini GEMINI.md is an instructions file published in the GitHub repository aaronhuff/awesome-gemini (3 stars, last pushed 1y ago), licensed MIT. It adds 554 tokens to every session, about $0.0028 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 2026-08-31.
Other instructions, from other repositories
desmond CLAUDE.md
Claude Code instructions for llegomark/desmond, covering claude.md, project overview, development commands, essential commands and build notes.
gemini-cli-desktop AGENTS.md
Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
gemini-cli-desktop CLAUDE.md
Instructions for Piebald-AI/gemini-cli-desktop, covering claude.md, project overview, key features, architecture and rust workspace structure.
gemini-rules-repo GEMINI.md
Instructions for sanpicule/gemini-rules-repo, covering gemini 開発ルール, 1. コミットメッセージ, 2. セキュリティ, 3. ブランチモデル and ブランチの種類.
render-claude-context CLAUDE.md
Instructions for czottmann/render-claude-context, covering claude.md, project overview, key files, core architecture and file processing system (index.js:7-30).
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.