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 PracticalSwan/agent-skills --skill gemini-api-devgit clone --depth 1 https://github.com/PracticalSwan/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/practicalswan/agent-skills/gemini-api-dev)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/gemini-api-dev"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/gemini-api-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/gemini-api-dev"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/gemini-api-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 443 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00101 | $0.05828 |
| Opus 5.5 | $0.00040 | $0.02331 |
| Sonnet 5.5 | $0.00020 | $0.01166 |
| Haiku 4.5 | $0.00010 | $0.00583 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 502 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-4-argon: 1M tokens, most powerful model for complex reasoning, coding, and researchgemini-3.8-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-flash-lite: cost-efficient, fastest performance for high-frequency, lightweight tasksgemini-3.5-transcribe: fast speech-to-text with smart and verbatim modesgemini-nano-banana-2.1(Nano Banana 2.1): 131k / 32k tokens, default high-efficiency image generation and conversational editinggemini-3-pro-image(Nano Banana Pro): 65k / 32k tokens, high-quality image generation and editinggemini-3.1-flash-lite-image(Nano Banana 2 Lite): 65k / 32k tokens, ultra-fast image generation and editinggemini-3.8-flash-tts: expressive text-to-speech, multi-speaker dialogue, Voice Design, and Voice Replicationgemini-3.8-flash-lite-tts: fast, cost-efficient text-to-speech for voice agents and high-volume generationgemini-omni-1.1-flash: video generation, first-frame-to-video, first-and-last-frame transitions, video extensions (up to 40s), video editing, and reference-guided generationgemma-4-31b-it: Gemma 4 dense model, 31B parametersgemma-4-26b-a4b-it: Gemma 4 MoE model, 26B total / 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-2.5-*,gemini-2.0-*,gemini-1.5-*are legacy and deprecated. Never use them. If a user asks for a deprecated model, usegemini-3.8-flashinstead and note the substitution.
Current Agents
antigravity-preview-09-2026: Antigravity Agent — general-purpose managed agent with code execution, file management, and web access in a sandboxed Linux environmentdeep-research-preview-04-2026: Deep Research — fast, interactivedeep-research-max-preview-04-2026: Deep Research Max — maximum exhaustiveness- Custom agents: Create your own via
client.agents.create()
What ships with it
3 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.
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.
- 4d ago Changed · +5 lines e4ff2c6c8c42
- 1mo ago Changed · +2 lines b6d6f94dfd5c
- 1mo ago Changed · +271 lines 7de0f6c2cc96
- 1mo ago First seen · 224 lines · 101 tokens per session scan A 66b906bb30bc
gemini-api-dev is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed 5d ago), licensed MIT. It adds 101 tokens to every session and 5,828 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
gemini-api-dev
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice design, voice replication, streaming responses, background research tasks, function calling, structured output, or migrating from…
data-engineering
A guide to data engineering, the work of collecting, moving, processing, and checking data. It covers workflow tools such as Airflow, Dagster, and Prefect, plus streaming and data-quality tools.
gdal-api
Use when programming against GDAL/OGR in C, C++, Python, Java, or .NET — raster/vector I/O, gdal.UseExceptions, OGRSpatialReference transforms, gdal.Translate / gdal.Warp, VRT/COG, or fixing "no driver registered" and UnsatisfiedLinkError; C++ gdal-config, Maven org.gdal:gdal 3.13.0, NuGet MaxRev.Gdal.Core.
microservices-expert
Expert-level microservices architecture, patterns, service mesh, and distributed systems. Use when the user mentions distributed systems, service mesh, or architecture, or when the task involves Microservices Principles, Architecture Patterns, Communication, or Data Management.
api-design-expert
Expert-level API design principles, REST, GraphQL, versioning, and API best practices. Use when the user mentions REST, GraphQL, API versioning, or API security, or when the task involves API Design Principles, API Styles, or Documentation.
fastapi-expert
Expert-level FastAPI development for high-performance Python APIs with async support. Use when the user mentions Python, API, async, REST, OpenAPI, or Pydantic, or when the task involves FastAPI Features.