What is gemini-search?

A web-search tool that uses Google Search through the Gemini service and returns a combined answer with sources.

Use it to find current information online and receive a sourced summary of the results.

It reduces the need to open and compare many search results yourself. It keeps the original question when building the search.

gemini-search — Skill for Claude Code and Codex by StrinGhost

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.

Any agent

npx skills add StrinGhost/gemma-skills --skill gemini-search

Clone the repo

git clone --depth 1 https://github.com/StrinGhost/gemma-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stringhost/gemma-skills/gemini-search/github.svg)](https://agentmods.dev/skills/stringhost/gemma-skills/gemini-search)

Your own site

<a href="https://agentmods.dev/skills/stringhost/gemma-skills/gemini-search"><img src="https://agentmods.dev/badge/skills/stringhost/gemma-skills/gemini-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/stringhost/gemma-skills/gemini-search"><img src="https://agentmods.dev/badge/skills/stringhost/gemma-skills/gemini-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 568 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00568
Opus 5.5	$0.00009	$0.00227
Sonnet 5.5	$0.00004	$0.00114
Haiku 4.5	$0.00002	$0.00057

Measured 2mo ago against content hash 0e3718b42455, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-search 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 2mo 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.

skills/gemini-search/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Search

This skill searches the live web using Google Search grounding via the Gemini API and returns a direct answer with sources.

Instructions

You MUST call the run_js tool using index.html.

Exact payload schema

Pass data as a JSON string with exactly one field:

query: String, Required.

Mandatory query construction rules

You MUST preserve the user's original question as literally as possible.
You MUST preserve the user's original intent.
You MUST NOT convert a factual question into a prediction, opinion, or generic topic.
You MUST NOT replace a full question with vague keywords when the original question is already clear.
If the user asks about whether, is, did, has, current, latest, status, qualify, qualified, going to, or similar status/outcome wording, you MUST keep that wording in the query field.
If the user already wrote a clear search-style question, copy it with minimal changes.
If unsure, prefer the user's longer literal question over a shorter rewritten query.

Do NOT do this

Do NOT rewrite Will Italy go to the next World Cup? into Italy World Cup prediction
Do NOT rewrite Did Company X raise funding? into Company X funding
Do NOT rewrite Is Product Y available in Singapore? into Product Y Singapore

Good examples

User: Can you search whether Italy will go to next world cup or not
- query: Can you search whether Italy will go to next world cup or not
User: Did OpenAI just raise a new funding round?
- query: Did OpenAI just raise a new funding round?
User: Is the Nintendo Switch 2 available in Singapore yet?
- query: Is the Nintendo Switch 2 available in Singapore yet?
User: What's the latest on OpenAI's funding round?
- query: What's the latest on OpenAI's funding round?

After the tool returns

Answer the user's question directly.
Keep the answer concise and factual.
Cite sources inline or in a short sources list.
If an error is returned, report it clearly and suggest checking the Gemini API key and permissions.

Read the full file on GitHub · 52 lines

Files

What ships with it

2 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.

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.

2mo ago First seen · 52 lines · 22 tokens per session scan A 0e3718b42455

Subscribe to this mod's changes

gemini-search is a skill published in the GitHub repository StrinGhost/gemma-skills (54 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 568 once invoked, about $0.0001 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 2026-08-30.

Gemma Research ai ai-skills gemini gemma-4 skills

gemini-search next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gemini-searchStrinGhost/gemma-skills	Skill	54	7mo ago	Apache-2.0	A	22	Claude Code, Codex
remotion-best-practicesguanyang/open-agent-hub	Skill	986	yesterday	MIT	A	116	Claude Code
gemini-watermark-removerGargantuaX/gemini-watermark-remover	Skill	5.7k	11d ago	MIT	A	47	Codex
remotion-captionsguanyang/open-agent-hub	Skill	986	yesterday	MIT	A	13	Claude Code, Codex
whalechan-image-characterNeko3000/deepseek-whalechan	Skill	518	10d ago	MIT	A	60	Codex
academy-guideguanyang/open-agent-hub	Skill	986	yesterday	MIT	A	208	Claude Code
gemma-devgoogle-gemma/gemma-skills	Skill	1.0k	9d ago	Apache-2.0	A	44	Claude Code, Codex