agentmods.dev

omni-cli: Instructions file for Gemini CLI

GEMINI.md

omni-cli GEMINI.md is an instructions file for Gemini CLI from mabelisle/omni-cli. It costs 900 tokens per session, scanned B, original, Apache-2.0.

A project guide for Omni-CLI, a Docker-based environment that lets you access several AI command-line tools through SSH or a direct container session. Docker packages the tools and their settings in an isolated environment.

In plain words
What is it for?
Use it when changing the Docker image, startup script, user and group mapping, SSH service, installed AI tools, or container management in Omni-CLI.
Why use it?
It explains how the container, user permissions, SSH setup, and startup scripts fit together, making changes less likely to break access or mounted files.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Codex; built for aider; mentions Gemini CLI.

This is mabelisle/omni-cli's own configuration. It tells Gemini CLI how to work on omni-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything omni-cli configures →

not rated 7repo 9mo ago B scan 900 tokens original Apache-2.0
View source ↗ mabelisle/omni-cli
Reuse

Borrowing it

Nothing to install: this file belongs to mabelisle/omni-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mabelisle/omni-cli/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/mabelisle/omni-cli

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.

agentmods badge for omni-cli GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mabelisle/omni-cli/gemini-md/github.svg)](https://agentmods.dev/instructions/mabelisle/omni-cli/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/mabelisle/omni-cli/gemini-md"><img src="https://agentmods.dev/badge/instructions/mabelisle/omni-cli/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omni-cli GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mabelisle/omni-cli/gemini-md"><img src="https://agentmods.dev/badge/instructions/mabelisle/omni-cli/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 900 This file is loaded in full into every session.
When invoked 900 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00900 $0.00900
Opus 5.5 $0.00360 $0.00360
Sonnet 5.5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 1mo ago against content hash 4a5e1eadd343, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

omni-cli GEMINI.md scanned grade B with 1 finding 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

* **Security:** Never run as root effectively; use `entrypoint.sh` to drop privileges or run as the `omni` user.
GEMINI.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Omni-CLI Context

Project Overview

Omni-CLI is a Dockerized, neural interface environment designed to unify access to various AI CLI tools (Gemini, Codex, Copilot, Aider). It provides a secure, sandboxed workspace that can be accessed via SSH or direct Docker attachment. The project is built on top of a lightweight Node.js image and includes custom shell scripts for project management and tool invocation.

Architecture & Core Components

Docker Structure

  • Base Image: node:25-slim (Debian-based).
  • Multi-Stage Build: Uses a builder stage for installing global npm packages (@google/gemini-cli, etc.) to keep the final image clean.
  • User Management:
    • The default node user (UID 1000) is removed in the final stage to avoid conflicts.
    • A custom omni user is created.
    • Runtime Mapping: entrypoint.sh dynamically updates the omni user's UID/GID to match the host system (via PUID/PGID env vars), ensuring correct file permissions for mounted volumes.

Key Scripts

  • entrypoint.sh: The container entrypoint. Handles:
    • User ID mapping (usermod/groupmod).
    • SSH host key generation.
    • Directory permission fixes.
    • Starting sshd or executing command arguments.
  • omni-cli.sh: The interactive "Neural Interface".
    • A generic bash script providing a menu-driven UI.
    • Manages projects in the /data directory.
    • Wraps AI CLI tool execution.

Building and Running

Build

docker build -t omni-cli .

Run (Development/Testing)

The container is designed to be persistent. It requires mapping volumes for data and configuration.

docker run -d \
  --name omni-cli \
  -p 2222:22 \
  -v $(pwd)/omni-data:/data \
  -v $(pwd)/omni-config:/config \
  -e PUID=$(id -u) \
  -e PGID=$(id -g) \
  omni-cli

Access

  • SSH: ssh omni@localhost -p 2222 (Password: changeme or as configured).
  • Interactive Shell: The omni-cli menu launches automatically upon login (configured in .profile).

Read the full file on GitHub · 79 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.

  1. 1mo ago First seen · 79 lines · 900 tokens per session scan B 4a5e1eadd343

Subscribe to this mod's changes

omni-cli GEMINI.md is an instructions file published in the GitHub repository mabelisle/omni-cli (7 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 900 tokens to every session, about $0.0036 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeContainersDevOps and cloudcli-wrappercopilot-clidocker-containergemini-cliproductivity-tool
Related

Other instructions, from other repositories

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 · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens