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 cnemri/google-genai-skills --skill google-genai-sdk-pythongit clone --depth 1 https://github.com/cnemri/google-genai-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/cnemri/google-genai-skills/google-genai-sdk-python)<a href="https://agentmods.dev/skills/cnemri/google-genai-skills/google-genai-sdk-python"><img src="https://agentmods.dev/badge/skills/cnemri/google-genai-skills/google-genai-sdk-python.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 | $0.00048 | $0.00390 |
| Opus 5 | $0.00024 | $0.00195 |
| Sonnet 5 | $0.00010 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
google-genai-sdk-python 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 9d 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
Google GenAI Python SDK Skill
Use this skill to write high-quality, idiomatic Python code for the Gemini API.
Reference Materials
Identify the user's task and refer to the relevant file:
- Setup & Client: Installation, auth, client initialization.
- Models: Recommended models (Flash, Pro, Lite, Imagen, Veo).
- Text Generation: Basic inference, streaming, system instructions, safety.
- Chat: Multi-turn conversations and history.
- Reasoning: Thinking config (
thinking_level/thinking_budget), thought signatures. - Structured Output: JSON schemas, Pydantic models, Enums.
- Multimodal Inputs: Images, audio, video, PDFs, media resolution.
- Tools: Function calling, code execution, Google Search grounding.
- Media Generation: Image generation/editing (Imagen), video generation (Veo).
- Source Code: Raw SDK source code for deep inspection.
Core Principles
- Unified SDK: Always use
google-genai. - Stateless Models: Use
client.modelsfor single requests. - Stateful Chats: Use
client.chatsfor conversations. - Types: Import from
google.genai.types.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/chat.md 779 B
- references/media_generation.md 1.0 KB
- references/models.md 1.1 KB
- references/multimodal_inputs.md 1.1 KB
- references/reasoning.md 1.5 KB
- references/setup.md 895 B
- references/source_code.md 1.3 KB
- references/structured_output.md 1.1 KB
- references/text_generation.md 1.5 KB
- references/tools.md 1.1 KB
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.
- 9d ago First seen · 30 lines · 48 tokens per session scan A 303836ac986d
google-genai-sdk-python is a skill published in the GitHub repository cnemri/google-genai-skills (126 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 390 once invoked, about $0.0002 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
accelerate
Run PyTorch training across GPUs with minimal changes.
developing-genkit-python
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
minicpm5-deploy-transformers
Run MiniCPM5-1B or MiniCPM5-2B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "model.generate" with MiniCPM5.
azure-mgmt-fabric-py
Azure Fabric Management SDK for Python. Use for managing Microsoft Fabric capacities and resources. Triggers: "azure-mgmt-fabric", "FabricMgmtClient", "Fabric capacity", "Microsoft Fabric", "Power BI capacity".