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 skills add G1Joshi/Agent-Skills --skill geminigit clone --depth 1 https://github.com/G1Joshi/Agent-SkillsWrote 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/skills/g1joshi/agent-skills/gemini)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/gemini"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/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 5.1 | $0.00018 | $0.00328 |
| Opus 5 | $0.00009 | $0.00164 |
| Sonnet 5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
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 8d 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
Gemini
Gemini is Google's native multimodal model. Uniquely, it accepts video and huge context (2M+ tokens) natively. 2025 sees Gemini 2.0/3.0.
When to Use
- Massive Context: "Here is a 1-hour video. Find the timestamp where..."
- Multimodal Live: Real-time voice/video interaction.
- Google Ecosystem: Integrated with Vertex AI, Search (Grounding), and Workspace.
Core Concepts
Models
- Pro: The best all-rounder.
- Flash: Extremely fast and cheap. High throughput.
- Ultra: The largest reasoning model.
Grounding
Connects the model to Google Search to provide citations and up-to-date info.
Context Initial Caching
Cache the context (e.g., a massive manual) to reduce cost/latency on subsequent queries.
Best Practices (2025)
Do:
- Use Flash for RAG: 2.0 Flash is smart enough for most RAG & cheaper/faster.
- Use Grounding: Eliminate hallucinations by enforcing "Google Search" grounding.
- Upload Video: Don't transcribe video manually; Gemini watches it.
Don't:
- Don't confuse with PaLM: Gemini replaced PaLM 2 completely.
References
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.
- 8d ago First seen · 47 lines · 18 tokens per session scan A 4db996d52a9c
gemini is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 328 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
9router-chat
Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
fixing-prompt
Prompt: Prompt Refinement and Optimization.
feature-engineering
When building training datasets, designing feature pipelines, or debugging training-serving skew.