josephhampton/awesome-gemini-cli-subagents — explained in plain English
Analysis updated 2026-05-18
Delegate a security review of a code diff to the security-auditor subagent automatically.
Install a focused test-automator agent that only writes meaningful unit and integration tests.
Use language specific agents like rust-pro or react-pro for idiomatic code in that language.
Share a curated set of project-level subagents with your team for consistent workflows.
| josephhampton/awesome-gemini-cli-subagents | gsvps/gsnode | hailoc12/ai_native_company | |
|---|---|---|---|
| Stars | 46 | 46 | 46 |
| Language | Shell | Shell | Shell |
| Setup difficulty | easy | easy | easy |
| Complexity | 1/5 | 2/5 | 1/5 |
| Audience | developer | ops devops | pm founder |
Figures from each repo's GitHub metadata at analysis time.
Requires an existing Gemini CLI installation to use the subagents.
This repository is a curated library of 51 ready made specialist helpers, called subagents, for Gemini CLI. Gemini CLI is a command line tool that can hand off parts of a task to smaller, focused assistants instead of doing everything itself, and this project gives you a large set of those assistants already written and ready to drop into your setup. Each subagent is a single markdown file that defines one area of expertise, such as reviewing code for security problems, writing tests, designing an API, working with Kubernetes, or reviewing a Rust project. Every subagent gets its own separate conversation space so a big task does not clutter your main chat, and each one only has access to the specific tools it needs, so for example a security reviewing agent can be limited to only reading files, never writing them. The collection is organized into nine groups covering things like core application development, specific programming languages, cloud infrastructure and DevOps, testing and quality, security, data and AI work, developer tooling, specialized domains, and higher level product or orchestration roles. Because each subagent is defined with a name, a description of when to use it, an optional list of allowed tools, and settings like which model or temperature to use, Gemini CLI can automatically pick the right one when you describe a task in plain language. Getting started just means cloning the repository and running an install script that copies every agent into a shared folder on your computer, so they become available in any project you work on. You can also copy individual agent files into a specific project folder if you only want a few of them, or if you want to share a particular set with your team. Once installed, you simply describe what you want, such as asking to review a code change for security issues, and Gemini CLI delegates that request to the matching specialist automatically. The project is released under the CC0 public domain license, so it is free for anyone to use, copy, or build on without restriction.
A library of 51 ready-made specialist AI helpers for Gemini CLI, covering coding, security, testing, and infrastructure.
Mainly Shell. The stack also includes Shell, Gemini CLI, Markdown.
This work is placed in the public domain. You may use, copy, modify, and distribute it for any purpose without asking permission.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.