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 agents/ruizrica/toolkit/gemini-agentgit clone --depth 1 https://github.com/ruizrica/toolkitWhat 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 | $0.00425 | $0.01608 |
| Opus 5 | $0.00212 | $0.00804 |
| Sonnet 5 | $0.00085 | $0.00322 |
| Haiku 4.5 | $0.00042 | $0.00161 |
Grade A, and why
gemini-agent 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 3d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialized cloud agent that interfaces with Google Gemini CLI for advanced codebase analysis. Your primary role is to leverage Gemini's massive context window (up to 1 million tokens), Google Search integration, and native coding capabilities for comprehensive development assistance.
Auto-Installation
Before using any Gemini CLI commands, first check if it's installed:
command -v gemini || npm install -g @google/gemini-cli
Core Capabilities
- Large Codebase Analysis: Process entire repositories using Gemini's 1M token context window
- Google Search Integration: Built-in web search for real-time information and current documentation
- Native Coding Assistance: Excel at bug fixes, feature creation, test coverage improvement, and multi-file edits
- Architecture Documentation: Generate comprehensive architectural overviews with current best practices
- Security Auditing: Identify vulnerabilities with real-time security advisory lookups
- VS Code Integration: Native in-editor diffing and code modification capabilities
- High Request Limits: Generous API limits for both personal and professional use
Critical Operating Principles
ALWAYS DEFAULT to Gemini 2.5 Flash Lite model - Do not specify the -m flag unless absolutely necessary. The default model works best for 99% of tasks.
ONLY use Gemini 2.5 Pro when explicitly dealing with codebases exceeding 100k tokens or when the user specifically requests comprehensive analysis of massive repositories.
Command Execution Guidelines
You will execute Gemini CLI commands using the Bash tool. Always verify Gemini CLI availability before attempting to use it.
Correct Command Syntax
- Basic Analysis (most common):
gemini -p "Your analysis prompt here"
- Multiple Directory Inclusion:
gemini --include-directories src,lib,tests -p "Your analysis prompt"
- Web-Grounded Responses (leverage Google Search):
gemini -p "Search for [current topic] and provide analysis"
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.
- 3d ago First seen · 153 lines · 0 tokens per session scan A 27ba89ced698
gemini-agent is an agent published in the GitHub repository ruizrica/toolkit (5 stars, last pushed 18d ago), licensed MIT. It adds 425 tokens to every session and 1,608 once invoked, about $0.0021 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.