gemini-api-dev

gemini-api-dev is a skill for Claude Code from oyi77/1ai-skills. It costs 52 tokens per session (2,896 once invoked), scanned A, original, MIT.

A development guide for building applications with Google Gemini, Google's AI models, through its programming interfaces. It covers text, images, audio, video, PDFs, streaming responses, tool calls, and Google Search grounding.

In plain words
What is it for?
Use it when adding Gemini chat, multimodal input, streaming, function calling, or Google Search grounding to a Python or TypeScript application.
Why use it?
It helps developers handle Gemini-specific API patterns without having to work them out from scattered documentation. It also clarifies which Gemini features apply to different kinds of input and output.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the 1ai-skills plugin — 187 skills, 4 commands, 4 agents shipped together

Install

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.

agentmods
npx agentmods add skills/oyi77/1ai-skills/gemini-api-dev
Any agent
npx skills add oyi77/1ai-skills --skill gemini-api-dev
Clone the repo
git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 187 skills, 4 commands, 4 agents.

Wrote 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.

agentmods badge for gemini-api-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/gemini-api-dev.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/gemini-api-dev)
Your own site
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/gemini-api-dev"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/gemini-api-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02896
Opus 5 $0.00026 $0.01448
Sonnet 5 $0.00010 $0.00579
Haiku 4.5 $0.00005 $0.00290

Measured 2d ago against content hash e1b084f8c2bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gemini-api-dev scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| "I will just use curl" | SDK handles retries, streaming, auth, and type safety |
core/gemini-api-dev/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Api Dev

When to Use

Trigger phrases:

  • "gemini api dev"

  • "When building apps powered by Google Gemini models"

  • "When processing multimodal inputs (text + images + audio + video)"

  • "When implementing function calling or tool use with Gemini"

  • When building apps powered by Google Gemini models

  • When processing multimodal inputs (text + images + audio + video)

  • When implementing function calling or tool use with Gemini

  • When using Gemini for grounding with Google Search

When NOT to Use

  • For OpenAI-compatible APIs (use OpenAI skills)
  • For local model inference (use Ollama skills)
  • For fine-tuning (use Vertex AI training skills)

Overview

The Google Gemini API provides access to Google's most capable AI models — Gemini 2.5 Pro, 2.5 Flash, and Gemini Nano — through a unified SDK. It supports text generation, multimodal understanding (images, audio, video, PDFs), function calling, and grounding with Google Search. The API is available via the google-genai Python SDK and @google/genai TypeScript SDK, both providing first-class async support, streaming generators, and type-safe response handling.

Gemini 2.5 Pro excels at complex reasoning, code generation, and multi-turn conversations with a 1-million-token context window. Gemini 2.5 Flash is optimized for speed and cost-efficiency while maintaining strong reasoning capabilities, making it suitable for high-volume production workloads. Nano models run on-device for Android and Chrome, handling summarization, smart reply, and text classification without network calls.

The API architecture follows a content-based message model: each request sends contents arrays with role (user or model) and parts — which can be text, inline_data (base64-encoded images/audio), file_data (PDFs, videos), function_call, or function_response. Configuration options include systemInstruction for persona setting, temperature (0.0–2.0), topP, topK, maxOutputTokens, stopSequences, and safetySettings for content filtering.

Read the full file on GitHub · 283 lines

Changes

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.

  1. 2d ago First seen · 283 lines · 52 tokens per session scan A e1b084f8c2bc

Subscribe to this mod's changes

gemini-api-dev is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,896 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.