gemini

A connector for Google's Gemini command-line tool, which lets you use Gemini from a terminal and from code through agents-wire.

In plain words
What is it for?
Use it to ask Gemini to perform tasks such as summarising a pull request. Install the Gemini CLI separately, sign in, and connect it through agents-wire.
Why use it?
It lets an application send tasks to Gemini without manually running the command-line tool each time. It also provides a way to inspect and, when supported, request available models and effort settings.

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/pivanov/agents-wire/gemini
Clone the repo
git clone --depth 1 https://github.com/pivanov/agents-wire
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 509 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00509
Opus 5 $0.00000 $0.00254
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 2d ago against content hash 41fa3153a280, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini 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 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.

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.

apps/docs/agents/gemini.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini CLI

Agent ID: gemini

Google's Gemini CLI. Speaks ACP via a peer-installed bridge package.

Install

npm install -g @google/gemini-cli
gemini auth login

The @google/gemini-cli package must be installed as a peer - it is not bundled with agents-wire.

Quick Start

import { agents } from "@pivanov/agents-wire";

const result = await agents.ask(
  "gemini",
  "Summarize this PR",
  {
    permission: "auto-allow",
  },
);

console.log(result.text);

Model Selection

options.model is forwarded as ACP modelPreference (best-effort). The gemini --acp bridge does not accept CLI model flags, so model selection depends entirely on whether the ACP bridge implements setSessionConfigOption. options.effort is sent via the same mechanism (best-effort).

To see which models Gemini currently advertises for a session, read session.configOptions:

import { createSession } from "@pivanov/agents-wire";

const session = await createSession("gemini");
const opts = session.configOptions ?? [];
const modelOpt = opts.find((o) => o.configId === "model" && o.type === "select");

if (modelOpt && modelOpt.type === "select") {
  console.log(modelOpt.options); // live model list from the agent
}

Capabilities

Feature Supported
ask / stream / session
askJson
MCP stdio
MCP http/sse
Session listing (listSessions)
Tool call interception

Cost Tracking

Gemini reports per-turn costUsd. Full cost tracking and maxCostUsd budget enforcement work.

Auth Failure Detection

If gemini auth login hasn't been run or credentials have expired, the SDK throws AgentUnauthenticatedError.

Gotchas

  • The @google/gemini-cli package is a peer dependency - install it separately.
  • Session listing is not supported; listSessions() throws CapabilityNotSupportedError.
  • Gemini CLI requires a Google account with the Gemini API enabled, or a paid API key.

Read the full file on GitHub · 77 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 · 77 lines · 0 tokens per session scan A 41fa3153a280

Subscribe to this mod's changes

gemini is an agent published in the GitHub repository pivanov/agents-wire (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 509 tokens. 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.

Related

Other agents, from other repositories

codex-execute

Implement a SPECIFIC, well-defined plan or plan-step with Codex. Use ONLY when the user has a written plan, plan-step, named files, or acceptance criteria to execute ("execute this via codex", "implement this plan", "/codex:execute", or a --plan file is in context). Do NOT use when the user is stuck/exploring (use…

greenpolo/cc-multi-cli-plugin · 98 tokens

cursor-delegate

Delegate a SPECIFIC, well-defined implementation task or plan step to Cursor in agent mode on the Auto model. Cursor is the fast lane for mechanical writing — long file writes (200+ lines), pattern-following across many files, bulk refactors. Supports autonomous multi-step runs via --until-done. Pair with…

greenpolo/cc-multi-cli-plugin · 84 tokens

cursor-research

Delegate read-only EXTERNAL web/documentation research to Cursor. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. Cursor runs read-only (ask mode) with web search + fetch and returns findings…

greenpolo/cc-multi-cli-plugin · 92 tokens

opencode-research

Delegate read-only EXTERNAL web/documentation research to OpenCode. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. OpenCode runs read-only (ask mode) with web search + fetch and returns…

greenpolo/cc-multi-cli-plugin · 97 tokens

codex-rescue

Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…

greenpolo/cc-multi-cli-plugin · 99 tokens

cursor-explore

Delegate quick read-only CODEBASE exploration to Cursor. Use to answer questions about the current repository ("where is X handled?", "how does Y flow?", "summarize the adapter layer") without spending Claude's tokens reading files. Cursor runs read-only (ask mode) using semantic search, grep, and its Explore…

greenpolo/cc-multi-cli-plugin · 90 tokens