gemini-cli

An open-source terminal coding agent from Google that uses Gemini to inspect a project and act on coding tasks. It can also run without an interactive screen and return structured JSON for other programs.

In plain words
What is it for?
Use it to complete coding tasks with terminal tools, connect model capabilities through MCP servers, run scripted or headless jobs, and consume JSON results.
Why use it?
It lets developers use an AI coding assistant from a terminal or connect it to graphical tools and automated workflows.

Agent

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 agents/marcinbunsch/overseer/gemini-cli
Clone the repo
git clone --depth 1 https://github.com/marcinbunsch/overseer
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,149 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.04149
Opus 5 $0.00000 $0.02074
Sonnet 5 $0.00000 $0.00830
Haiku 4.5 $0.00000 $0.00415

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

Security

Grade B, and why

gemini-cli 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Stored in `~/.gemini/settings.json` (global) or `.gemini/settings.json` (project-scoped).
docs/agents/gemini-cli.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini CLI

Gemini CLI is an open-source AI coding agent from Google that brings Gemini directly into the terminal. It uses a ReAct (reason and act) loop with built-in tools and MCP servers to complete tasks. For GUI integrations, Gemini CLI supports a headless non-interactive mode with structured JSON output over stdout.

Source: https://github.com/google-gemini/gemini-cli

Quick Start

Installation

# npm (recommended)
npm install -g @google/gemini-cli

# Or run directly with npx
npx @google/gemini-cli

Requires Node.js 20+.

Authentication

# API key (simplest)
export GEMINI_API_KEY=your-api-key

# Google Cloud credentials
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

# Google Cloud project (for Vertex AI)
export GOOGLE_CLOUD_PROJECT=your-project-id
export GOOGLE_CLOUD_LOCATION=us-central1

Also supports:

  • API Key: GEMINI_API_KEY or GOOGLE_API_KEY environment variable
  • Google Cloud: Service account via GOOGLE_APPLICATION_CREDENTIALS
  • Vertex AI: GOOGLE_CLOUD_PROJECT + GOOGLE_CLOUD_LOCATION

Platform Support

  • macOS & Linux — fully supported
  • Windows — via WSL

CLI Commands

Interactive Mode

gemini                                    # Launch interactive TUI
gemini -i "Tell me about this project"   # Interactive with initial prompt
gemini -m gemini-2.5-pro                 # Override model

Non-Interactive (Headless) Mode

gemini -p "Fix the login bug"                              # Single prompt, exits after
gemini -p "Explain this code" --output-format json          # Structured JSON output
gemini -p "Refactor auth" --output-format stream-json       # NDJSON streaming events
echo "Summarize this" | gemini                              # Pipe input via stdin
cat README.md | gemini -p "Summarize this documentation"    # Combined file + prompt

Session Management

gemini --resume                    # Resume most recent session
gemini --resume 1                  # Resume by index
gemini --resume <session-uuid>     # Resume specific session by UUID
gemini --list-sessions             # List available sessions
gemini --delete-session <id>       # Delete a session

Read the full file on GitHub · 523 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 · 523 lines · 0 tokens per session scan B bbcacaaceada

Subscribe to this mod's changes

gemini-cli is an agent published in the GitHub repository marcinbunsch/overseer (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,149 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens