agentmods.dev

omni-cli GEMINI.md

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

6 7mo ago B scan 900 tokens original Apache-2.0
View the source file mabelisle/omni-cli
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/mabelisle/omni-cli/gemini-md
Clone the repo
git clone --depth 1 https://github.com/mabelisle/omni-cli

Made for: Gemini CLI.

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. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00900 $0.00900
Opus 5 $0.00450 $0.00450
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 2d ago against content hash 4a5e1eadd343, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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. 2d 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 (6 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 900 tokens to every session, about $0.0045 per session on Opus 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.

ContainersDevOps and cloudclaude-codecli-wrappercopilot-clidocker-containergemini-cliproductivity-tool
Related

Other instructions, from other repositories

docker-gemini-cli GEMINI.md

Instructions for naoyoshinori/docker-gemini-cli, covering 1. core functionality, 2. project structure and key files, 2.1. image variants, 2.2. automation and 3. documentation.

naoyoshinori/docker-gemini-cli · 267 tokens

Project-AMBER AGENTS.md

Instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.

JJHbrams/Project-AMBER · 400 tokens

Project-AMBER project-guides.instructions.md

Project coding guidelines, todo monitoring rules, and context for AI agents working on Project Engram.

JJHbrams/Project-AMBER · 253 tokens

generative-commit-message-for-ai-tool CLAUDE.md

Instructions for UNILORN/generative-commit-message-for-ai-tool, covering claude.md, project overview, build and development commands, architecture and core packages.

UNILORN/generative-commit-message-for-ai-tool · 607 tokens

ai-cli-in-docker AGENTS.md

AGENTS.md instructions for vladborovtsov/ai-cli-in-docker, a project described as: Collection of AI CLI wrappers: Run AI CLI tools (OpenAI Codex, Google Gemini, OpenCode, Claude Code) inside Docker to keep your host clean while persisting CLI auth/config on your machine.

vladborovtsov/ai-cli-in-docker · 4 tokens

all-agents-mcp CLAUDE.md

Instructions for Dokkabei97/all-agents-mcp, covering claude.md, project overview, build & development commands, architecture and entry flow.

Dokkabei97/all-agents-mcp · 1,721 tokens