agentmods.dev

gemini-search

gemini-search is a skill for Claude Code from signalcompose/claude-tools. It costs 41 tokens per session (766 once invoked), scanned C, original, MIT.

A skill that performs web searches through Google's Antigravity command-line tool, formerly called Gemini CLI.

In plain words
What is it for?
Use it to look up the latest information, API references, documentation, current events, and other up-to-date web content.
Why use it?
It helps retrieve current information when built-in knowledge may be outdated, especially for documentation, recent events, or changing web data.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; mentions Claude Code; mentions Gemini CLI.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ask-gemini plugin — 1 skill, 1 command shipped together

not rated 4repo 12d ago C scan 41 tokens original MIT

Good fit Use it to look up the latest information, API references, documentation, current events, and other up-to-date web content.

Compare 6 skills from other repositories ↓
View source ↗ signalcompose/claude-tools
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add signalcompose/claude-tools
Claude Code
/plugin install ask-gemini

Made for: Claude Code.

Or install ask-gemini, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/signalcompose/claude-tools/gemini-search/github.svg)](https://agentmods.dev/skills/signalcompose/claude-tools/gemini-search)
Your own site
<a href="https://agentmods.dev/skills/signalcompose/claude-tools/gemini-search"><img src="https://agentmods.dev/badge/skills/signalcompose/claude-tools/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.

agentmods 80×15 button for gemini-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/signalcompose/claude-tools/gemini-search"><img src="https://agentmods.dev/badge/skills/signalcompose/claude-tools/gemini-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 766 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00766
Opus 5 $0.00020 $0.00383
Sonnet 5 $0.00008 $0.00153
Haiku 4.5 $0.00004 $0.00077

Measured 8d ago against content hash 25bff2a6b168, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

gemini-search scanned grade C with 2 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 8d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://antigravity.google/cli/install.sh | bash

Makes network callslowCapability

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

curl -fsSL https://antigravity.google/cli/install.sh | bash
plugins/ask-gemini/skills/gemini-search/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Search Skill (Antigravity CLI)

Overview

This skill enables web search using Google Antigravity CLI (agy), the successor to the Gemini CLI. Use it when you need:

  • Latest information not in training data
  • Current documentation or API references
  • Recent news or events
  • Up-to-date web data

Note: Google transitioned Gemini CLI to Antigravity CLI. Gemini CLI stopped serving requests on 2026-06-18 for AI Pro/Ultra and free-tier users, so this skill now drives the agy binary.

Prerequisites

Antigravity CLI (agy) must be installed and signed in. Run the check script first:

${CLAUDE_PLUGIN_ROOT}/scripts/check-gemini.sh

If agy is missing, install it and sign in:

curl -fsSL https://antigravity.google/cli/install.sh | bash
agy   # one-time browser sign-in

Usage

Basic Web Search

${CLAUDE_PLUGIN_ROOT}/scripts/gemini-search.sh "<search query>"

IMPORTANT: agy needs write access to its config/cache under ~/.gemini/antigravity-cli/, which Claude Code's sandbox blocks. When running the script via the Bash tool, set dangerouslyDisableSandbox: true; otherwise agy exits non-zero with shell command errors even though it is installed and signed in.

Examples

# Search for latest Claude Code features
${CLAUDE_PLUGIN_ROOT}/scripts/gemini-search.sh "Claude Code latest features 2026"

# Look up current API documentation
${CLAUDE_PLUGIN_ROOT}/scripts/gemini-search.sh "OpenAI API rate limits 2026"

# Research recent news
${CLAUDE_PLUGIN_ROOT}/scripts/gemini-search.sh "AI regulation updates January 2026"

Workflow

  1. Check Prerequisites

    • Verify Antigravity CLI (agy) installation
    • Ensure sign-in is complete

  2. Execute Search

    • Run gemini-search.sh with query
    • Wait for results (120s timeout)

  3. Process Results

    • Summarize key findings
    • Note relevant sources
    • Highlight latest information

Error Handling

Error Solution
agy not found Install: curl -fsSL https://antigravity.google/cli/install.sh | bash
Not signed in Run agy once to complete browser sign-in
Legacy Gemini CLI only Migrate to agy (see install above); optionally agy plugin import gemini
Timeout Retry with a more specific query

Read the full file on GitHub · 103 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. 8d ago First seen · 103 lines · 41 tokens per session scan C 25bff2a6b168

Subscribe to this mod's changes

gemini-search is a skill published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 766 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens