An agent description for using Google’s Gemini CLI through FreeRide. Gemini CLI is a terminal program for interacting with Google’s Gemini models, while FreeRide translates its requests for configured upstream providers.

Use it to install and launch Gemini CLI through FreeRide, including one-shot prompts. It documents the request format and the commands needed to connect the two tools.

It explains how to run Gemini CLI without a Google Cloud account or Gemini API key when FreeRide is available. It also clarifies why the gateway must translate Google’s API format.

gemini — Agent for coding agents by Shaivpidadi: An agent description for using Google’s Gemini CLI through…

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/shaivpidadi/freeridev3/gemini

Clone the repo

git clone --depth 1 https://github.com/Shaivpidadi/FreeRideV3

Or install freeride, the plugin that ships this one along with the rest of its 1 skill, 5 agents.

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/agents/shaivpidadi/freeridev3/gemini.svg)](https://agentmods.dev/agents/shaivpidadi/freeridev3/gemini)

Your own site

<a href="https://agentmods.dev/agents/shaivpidadi/freeridev3/gemini"><img src="https://agentmods.dev/badge/agents/shaivpidadi/freeridev3/gemini.svg" alt="Measured on agentmods" height="20"></a>

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 1,724 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 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	$0.00000	$0.01724
Opus 5	$0.00000	$0.00862
Sonnet 5	$0.00000	$0.00345
Haiku 4.5	$0.00000	$0.00172

Measured 4d ago against content hash 57b34bd51d72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

gemini scanned grade D with 3 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sSL https://api.free-ride.xyz/install.sh | sh

Reads agent configuration directoriesmediumAgent snooping

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

On first run, the wrapper also writes `~/.gemini/settings.json` with `{"selectedAuthType": "gemini-api-key"}` so the interactive auth-method picker doesn't fire. An existing settings.json is left alone — a user who ran `

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sSL https://api.free-ride.xyz/install.sh | sh

docs/agents/gemini.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Gemini CLI

The official terminal agent from Google (npm install -g @google/gemini-cli). FreeRide makes it work without a Google Cloud account or GEMINI_API_KEY — the gateway translates Google's Generative Language API protocol to free upstream providers.

TL;DR

curl -sSL https://api.free-ride.xyz/install.sh | sh
npm install -g @google/gemini-cli
freeride run gemini

Or for one-shot non-interactive:

freeride run gemini --skip-trust --prompt 'explain this repo'

You're in a Gemini session, routed through free providers. No GEMINI_API_KEY or Google sign-in needed.

How it works

Gemini CLI speaks Google's native Generative Language API — not OpenAI-compatible. Requests go to URLs like:

POST https://generativelanguage.googleapis.com/v1beta/models/<model>:generateContent
POST https://generativelanguage.googleapis.com/v1beta/models/<model>:streamGenerateContent?alt=sse

Body shape is {contents: [...], tools: [{functionDeclarations: [...]}], generationConfig, systemInstruction} — different keys, different nesting from OpenAI.

The gateway hosts the same path shapes locally and:

Parses Google's camelCase JSON (via Pydantic's to_camel alias generator)
Flattens Tool.functionDeclarations[] into OpenAI's tools[]
Maps tool_config.function_calling_config.mode (AUTO/NONE/ANY) → OpenAI tool_choice (auto/none/required)
Hoists systemInstruction into a leading role=system message
Handles both newer (functionResponse under role=user) and legacy (role=function) tool-result conventions
Routes through the same failover machinery as everything else
Translates the response back to {candidates, usageMetadata, modelVersion} shape
Streams in Google's "incremental complete responses" SSE format (each chunk a full GeminiGenerateResponse with partial content)

Model field in the URL (gemini-2.0-flash, gemini-2.5-pro, etc.) is rewritten to auto before dispatch — we don't host Google's proprietary models. The originally-requested model id is echoed back as modelVersion on the response so the CLI's UI stays coherent.

Read the full file on GitHub · 118 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.

4d ago First seen · 118 lines · 0 tokens per session scan D 57b34bd51d72

Subscribe to this mod's changes

gemini is an agent published in the GitHub repository Shaivpidadi/FreeRideV3 (42 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,724 tokens. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

HuggingFace Writing and docs ai-gateway claude hermes openai openclaw

AGENTS

Every ProcessingContext carries an AgentMemory instance at context.memory. It is the single source of truth for everything shared between steps, tasks, sub-agents, and tools. Do not introduce a parallel result map in any executor — read and write through context.memory.

nodetool-ai/nodetool · 0 tokens

gemini

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade D, and why

Downloads and executes remote codehighSupply chain

Reads agent configuration directoriesmediumAgent snooping

Makes network callslowCapability

How it starts

Google Gemini CLI

TL;DR

How it works

What this file has done since we first saw it

Other agents, from other repositories

AGENTS

agent

index

classifier

enhanceprompt

extractor