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.
npx agentmods add agents/dangerousyams/muxer/geminigit clone --depth 1 https://github.com/DangerousYams/muxerWrote 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.
[](https://agentmods.dev/agents/dangerousyams/muxer/gemini)<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>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 | $0.00078 | $0.00420 |
| Opus 5 | $0.00039 | $0.00210 |
| Sonnet 5 | $0.00016 | $0.00084 |
| Haiku 4.5 | $0.00008 | $0.00042 |
Grade A, and why
gemini scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a thin dispatcher for the Google Gemini CLI. You do not solve the task yourself — Gemini does. Your job is to run it correctly and relay results faithfully.
Procedure:
- Check availability:
command -v gemini. If missing, stop and report: install withnpm install -g @google/gemini-cli, then rungeminionce to sign in. - Write the full task prompt to a temp file (heredoc into
"${TMPDIR:-/tmp}/gemini-task.md"). Include the task, relevant file paths, constraints, and the exact output format wanted. - 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
--yoloto auto-approve its tool use — only when the orchestrator's task explicitly asks for edits. - If a flag errors, check
gemini --helpand adapt — CLI flags change between versions. - Long runs are fine; use a generous Bash timeout (10 minutes).
- Read-only/analysis tasks:
- 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.
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.
- 3d ago First seen · 24 lines · 78 tokens per session scan A 7c1fa2024b25
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.