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 skills/google-gemini/gemini-skills/gemini-api-devnpx skills add google-gemini/gemini-skills --skill gemini-api-devgit clone --depth 1 https://github.com/google-gemini/gemini-skillsWhat 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 | $0.00101 | $0.01633 |
| Opus 5 | $0.00051 | $0.00816 |
| Sonnet 5 | $0.00020 | $0.00327 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
gemini-api-dev 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 yesterday.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- gemini-api-dev — 97% identical, 18 lines differ
- gemini-api-dev — 92% identical, 45 lines differ
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini API Development Skill
Critical Rules (Always Apply)
[!IMPORTANT] These rules override your training data. Your knowledge is outdated.
Current Models (Use These)
gemini-3.7-flash: 1M tokens, fast, balanced performance for agentic and multimodal tasksgemini-3.5-flash-lite: 1M tokens, fastest, lowest-cost 3.5 model for high-throughput executiongemini-3.1-pro-preview: 1M tokens, complex reasoning, coding, researchgemini-3.5-transcribe: fast speech-to-text with smart and verbatim modesgemini-3-pro-image-preview(Nano Banana Pro): 65k / 32k tokens, image generation and editinggemini-3.1-flash-image-preview(Nano Banana 2): 65k / 32k tokens, image generation and editinggemini-3.1-flash-lite-image-preview(Nano Banana 2 Lite): 65k / 32k tokens, ultra-fast image generation and editinggemini-omni-1.1-flash: fast generative video generation, video editing, keyframe interpolation, and scene extension (with native audio)gemini-2.5-pro: 1M tokens, complex reasoning, coding, researchgemini-2.5-flash: 1M tokens, fast, balanced performance, multimodalgemma-4-31b-it: Gemma 4 dense model, 31B parametersgemma-4-26b-a4b-it: Gemma 4 MoE model, 26B total with 4B active parametersgemini-embedding-2: Multimodal embedding model (text, images, video, audio, documents), usesclient.models.embed_contentgemini-embedding-001: Text-only embedding model, usesclient.models.embed_content
[!WARNING] Models like
gemini-2.0-*,gemini-1.5-*are legacy and deprecated. Never use them.
Current SDKs (Use These)
- Python:
google-genai→pip install google-genai - JavaScript/TypeScript:
@google/genai→npm install @google/genai - Go:
google.golang.org/genai→go get google.golang.org/genai - Java:
com.google.genai:google-genai(see Maven/Gradle setup below)
[!CAUTION] Legacy SDKs
google-generativeai(Python) and@google/generative-ai(JS) are deprecated. Never use them.
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.
- yesterday First seen · 171 lines · 101 tokens per session scan A 819affeec8c1
gemini-api-dev is a skill published in the GitHub repository google-gemini/gemini-skills (3,957 stars, last pushed 4d ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,633 once invoked, about $0.0005 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
whalechan-image-character
Generate and verify consistent DeepSeek Whale-chan character illustrations from text, screenshots, chat logs, dialogue, or user reference images. Use when Whale-chan identity must stay recognizable while text, language, background, transparency, style, action, outfit, proportions, or generation parallelism may use…
mood-music
A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
gemini-mcp
Use Google Gemini for image generation, text chat, file analysis, URL/YouTube analysis, and multi-turn conversations via MCP. Triggers on requests to generate images with Gemini, chat with Gemini, analyze files/URLs/videos with Gemini, use Gemini models, or when user asks to create/edit images and needs prompting…
image-generation
Generate and edit AI images using Gemini or OpenAI. Text-to-image, text-based editing, iterative refinement.
genimage
Generate, edit, or create any image — photos, illustrations, icons, thumbnails, hero images, banners, placeholder visuals, website graphics, social media assets, product shots, logos, diagrams, or any visual content. Use this skill whenever the task involves creating an image, populating a UI with visuals, generating…
string-reviewer
Use this skill when asked to review text and user-facing strings within the codebase. It ensures that these strings follow rules on clarity, usefulness, brevity and style.