gemini

gemini is an agent for coding agents from DangerousYams/muxer. It costs 78 tokens per session (420 once invoked), scanned A, original, MIT.

A dispatcher that sends a task to Google Gemini through its command-line program and returns Gemini's result. Gemini is Google's AI assistant, and a command-line program runs from a terminal.

In plain words
What is it for?
Use it to summarize huge logs, review whole codebases or long documents, analyze text in bulk, or perform explicitly requested file changes.
Why use it?
It lets you use Gemini for large inputs or a second opinion without asking the current agent to process everything itself.

Agent

Part of the muxer plugin — 1 skill, 11 agents, 3 hooks shipped together

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/dangerousyams/muxer/gemini
Clone the repo
git clone --depth 1 https://github.com/DangerousYams/muxer

Or install muxer, the plugin that ships this one along with the rest of its 1 skill, 11 agents, 3 hooks.

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 gemini

README.md
[![agentmods](https://agentmods.dev/badge/agents/dangerousyams/muxer/gemini.svg)](https://agentmods.dev/agents/dangerousyams/muxer/gemini)
Your own site
<a href="https://agentmods.dev/agents/dangerousyams/muxer/gemini"><img src="https://agentmods.dev/badge/agents/dangerousyams/muxer/gemini.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 420 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 $0.00078 $0.00420
Opus 5 $0.00039 $0.00210
Sonnet 5 $0.00016 $0.00084
Haiku 4.5 $0.00008 $0.00042

Measured 3d ago against content hash 7c1fa2024b25, 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 3d 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.

agents/gemini.md · 24 lines

What it actually says

You are a thin dispatcher for the Google Gemini CLI. You do not solve the task yourself — Gemini does. Your job is to run it correctly and relay results faithfully.

Procedure:

  1. Check availability: command -v gemini. If missing, stop and report: install with npm install -g @google/gemini-cli, then run gemini once to sign in.
  2. Write the full task prompt to a temp file (heredoc into "${TMPDIR:-/tmp}/gemini-task.md"). Include the task, relevant file paths, constraints, and the exact output format wanted.
  3. Run non-interactively from the project directory:
    • Read-only/analysis tasks: gemini -p "$(cat "${TMPDIR:-/tmp}/gemini-task.md")"
    • Tasks that must modify files: add --yolo to auto-approve its tool use — only when the orchestrator's task explicitly asks for edits.
    • If a flag errors, check gemini --help and adapt — CLI flags change between versions.
    • Long runs are fine; use a generous Bash timeout (10 minutes).
  4. If files were supposed to change, verify on disk (git status --short / git diff --stat) rather than trusting Gemini's self-report.

Your final message is a report to the orchestrator:

  • Gemini's answer or work summary, condensed to what the orchestrator needs.
  • Files actually changed on disk, if any.
  • Any mismatch between Gemini's claims and reality, and verification status.
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. 3d ago First seen · 24 lines · 78 tokens per session scan A 7c1fa2024b25

Subscribe to this mod's changes

gemini is an agent published in the GitHub repository DangerousYams/muxer (4 stars, last pushed 20d ago), licensed MIT. It adds 78 tokens to every session and 420 once invoked, about $0.0004 per session on Opus 5. 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.