Skip to content

laywill/awesome-claude-code-subagents

BranchesTags
 
 

Repository files navigation

An awesome collection of Claude Code subagents.

Subagent Count Last Update GitHub forks

Awesome Claude Code Subagents

This repository serves as the definitive collection of Claude Code subagents, specialized AI assistants designed for specific development tasks. Organized into 24 categories with a risk-tiered structure for production-safe automation.

Installation

As Claude Code Plugin (Recommended)

claude plugin marketplace add laywill/awesome-claude-code-subagents
claude plugin install <plugin-name>

Examples:

claude plugin install laywill-research-discovery         # category 01 Research and Discovery
claude plugin install laywill-architecture-design        # category 02 Architecture and Design
claude plugin install laywill-analysis-review            # category 03 Analysis and Review
claude plugin install laywill-documentation              # category 04 Documentation
claude plugin install laywill-planning-estimation        # category 05 Planning and Estimation
claude plugin install laywill-business-product           # category 06 Business and Product Ownership
claude plugin install laywill-language-specialists       # category 07 Language Specialists
claude plugin install laywill-general-development        # category 08 Development Generalists
claude plugin install laywill-testing-qa                 # category 09 Testing and QA
claude plugin install laywill-refactoring-modernization  # category 10 Refactoring and Modernization of legacy code
claude plugin install laywill-bug-fixing-debugging       # category 11 Debugging and bug fixing
claude plugin install laywill-frontend-ui                # category 12 Frontend and UI
claude plugin install laywill-developer-experience       # category 13 Developer Experience
claude plugin install laywill-data-database              # category 14 Data, Database, and Datalake specialists
claude plugin install laywill-data-science-ai            # category 15 Data Science, AI and ML
claude plugin install laywill-dependency-management      # category 16 Dependency Management
claude plugin install laywill-build-ci-cd                # category 17 Build Agents, and CI/CD
claude plugin install laywill-api-service-integration    # category 18 API Service Integration
claude plugin install laywill-infrastructure-code        # category 19 Infrastructure as Code
claude plugin install laywill-security-secrets           # category 20 Security and Secrets management
claude plugin install laywill-specialized-domains        # category 21 Specialised Industries and Domains
claude plugin install laywill-deployment-release         # category 22 Deployment and Release
claude plugin install laywill-production-ops             # category 23 Production and Operations
claude plugin install laywill-production-data-ops        # category 24 Production Data Operations

See Categories below for all available plugins.

Manual Installation

  1. Clone this repository
  2. Copy desired agent files to:
    • ~/.claude/agents/ for global access
    • .claude/agents/ for project-specific use
  3. Customize based on your project requirements

Interactive Installer

git clone https://github.com/laywill/awesome-claude-code-subagents.git
cd awesome-claude-code-subagents
./install-agents.sh

This interactive script lets you browse categories, select agents, and install/uninstall them with a single command.

Option 3: Standalone Installer (no clone required)

curl -sO https://raw.githubusercontent.com/laywill/awesome-claude-code-subagents/main/install-agents.sh
chmod +x install-agents.sh
./install-agents.sh

Downloads agents directly from GitHub without cloning the repository. Requires curl.


Uninstall

Run the /plugins command to see which plugins you have installed, or the /agents command to see which agents Claude Code currently has access to.

As Claude Code Plugin (Recommended)

claude plugin uninstall <plugin-name>

Examples:

claude plugin install laywill-research-discovery         # category 01 Research and Discovery

Manual Uninstallation

  1. Delete no-longer desired agent files from:
    • ~/.claude/agents/ for agents with global access
    • .claude/agents/ for project-specific agents

Interactive Installer

git clone https://github.com/laywill/awesome-claude-code-subagents.git
cd awesome-claude-code-subagents
./install-agents.sh

This interactive script lets you browse categories, select agents, and uninstall them with a single command.

🔒 Risk Tiers at a Glance

Tier Icon Categories Risk Level Key Characteristics
1 🟢 01–06 Low (Read-Only/Advisory) Analysis, research, planning, documentation
2 🟡 07–13 Medium (Local Code) Development, testing, refactoring
3 🟠 14–17 Medium-High (Data/Deps/Build) Database, dependencies, CI/CD
4 🔴 18–21 High (External Systems) APIs, infrastructure, security
5 ⛔ 22–24 Critical (Production) Deployment, operations, data migration

📚 Categories

🟢 01. Research and Discovery

Plugin: laywill-research-discovery

Research and discovery subagents explore new technologies, assess feasibility, analyze markets and trends, and conduct deep investigations. They help teams understand the landscape before committing to major decisions.

🟢 02. Architecture and Design

Plugin: laywill-architecture-design

Architecture and design subagents design systems, APIs, databases, and data flows. They create blueprints for scalable, maintainable solutions before implementation begins.

🟢 03. Analysis and Review

Plugin: laywill-analysis-review

Analysis and review subagents audit code quality, security, performance, accessibility, and compliance. They identify risks and improvements before code reaches production.

🟢 04. Documentation

Plugin: laywill-documentation

Documentation subagents create and maintain API docs, ADRs, runbooks, READMEs, changelogs, and technical guides. They ensure knowledge is captured and accessible.

🟢 05. Planning and Estimation

Plugin: laywill-planning-estimation

Planning and estimation subagents help teams scope work, estimate effort, plan migrations and releases, and assess risks. They enable better project management and delivery confidence.

🟢 06. Business and Product

Plugin: laywill-business-product

Business and product subagents support business strategy, market analysis, UX research, legal compliance, content marketing, and financial modeling. They bridge technology and business decisions.

🟡 07. Language and Framework Specialists

Plugin: laywill-language-specialists

Language and framework specialists provide expert knowledge for specific programming languages and frameworks. They handle language-specific idioms, best practices, and optimization techniques.

34 language specialists including: Angular, C++, C#, Django, .NET Core, .NET Framework, Elixir, Flutter, F#, Go, Haskell, Java, JavaScript, Kotlin, Laravel, Lua, Next.js, OCaml, PHP, PowerShell (5.1, 7, modules, UI), Python, R, Rails, React, Rust, Spring Boot, SQL, Swift, TypeScript, Vue, WordPress

View all 34 language specialists →

🟡 08. General Development

Plugin: laywill-general-development

General development subagents handle core development roles including backend, frontend, fullstack, mobile, CLI, game, and UI development. They provide broad development expertise across platforms.

🟡 09. Testing and QA

Plugin: laywill-testing-qa

Testing and QA subagents create automated tests, chaos experiments, fixtures, and coverage reports. They ensure code quality through comprehensive testing strategies.

🟡 10. Refactoring and Modernization

Plugin: laywill-refactoring-modernization

Refactoring and modernization subagents improve code quality by reducing technical debt, applying design patterns, upgrading frameworks, and modernizing language features.

🟡 11. Bug Fixing and Debugging

Plugin: laywill-bug-fixing-debugging

Bug fixing and debugging subagents diagnose and fix bugs, analyze logs and stack traces, and hunt regressions. They help teams resolve production issues quickly.

🟡 12. Frontend and UI

Plugin: laywill-frontend-ui

Frontend and UI subagents build responsive components, manage themes, handle internationalization, and refactor styles. They ensure polished, accessible user interfaces.

🟡 13. Developer Experience and Tooling

Plugin: laywill-developer-experience

Developer experience and tooling subagents improve build processes, optimize git workflows, manage team communication, and enhance prompt engineering. They make development faster and smoother.

🟠 14. Data and Database

Plugin: laywill-data-database

Data and database subagents design schemas, optimize queries, manage migrations, generate test data, and validate data integrity. They ensure reliable data layer performance.

🟠 15. Data Science and AI

Plugin: laywill-data-science-ai

Data science and AI subagents build machine learning models, analyze data, architect LLM solutions, and handle MLOps. They bring intelligent capabilities to applications.

🟠 16. Dependency and Package Management

Plugin: laywill-dependency-management

Dependency and package management subagents manage dependencies, handle upgrades, patch vulnerabilities, resolve lockfiles, publish packages, and manage monorepos.

🟠 17. Build and CI/CD

Plugin: laywill-build-ci-cd

Build and CI/CD subagents design pipelines, write workflows, configure environments, optimize builds, and publish artifacts. They automate and accelerate software delivery.

🔴 18. API and Service Integration

Plugin: laywill-api-service-integration

API and service integration subagents generate API clients, integrate third-party services, build SDK wrappers, configure webhooks, and set up message queues.

🔴 19. Infrastructure as Code

Plugin: laywill-infrastructure-code

Infrastructure as code subagents manage cloud infrastructure, Kubernetes, containerization, networking, and platform engineering. They ensure reliable, scalable infrastructure.

🔴 20. Security and Secrets

Plugin: laywill-security-secrets

Security and secrets subagents harden systems, conduct penetration testing, manage secrets and certificates, handle IAM policies, and configure CORS. They protect applications and data.

🔴 21. Specialized Domains

Plugin: laywill-specialized-domains

Specialized domains subagents handle blockchain, embedded systems, fintech, IoT, Microsoft 365, and payment integration. They bring domain-specific expertise to niche areas.

⛔ 22. Deployment and Release

Plugin: laywill-deployment-release

Deployment and release subagents manage deployments, handle blue-green and canary strategies, manage feature flags, and control rollbacks. They enable safe, controlled releases.

⛔ 23. Production Ops and Observability

Plugin: laywill-production-ops

Production ops and observability subagents manage incidents, configure monitoring and logging, build dashboards, manage SLAs, and handle scaling. They ensure systems run smoothly in production.

⛔ 24. Production Data Ops

Plugin: laywill-production-data-ops

Production data ops subagents manage data migrations, anonymization, backup and restore, replication, and retention policies. They ensure data safety and compliance in production.


🤖 Understanding Subagents

Subagents are specialized AI assistants that enhance Claude Code's capabilities by providing task-specific expertise. They act as dedicated helpers that Claude Code can call upon when encountering particular types of work.

What Makes Subagents Special?

Independent Context Windows Every subagent operates within its own isolated context space, preventing cross-contamination between different tasks and maintaining clarity in the primary conversation thread.

Domain-Specific Intelligence Subagents come equipped with carefully crafted instructions tailored to their area of expertise, resulting in superior performance on specialized tasks.

Shared Across Projects After creating a subagent, you can utilize it throughout various projects and distribute it among team members to ensure consistent development practices.

Granular Tool Permissions You can configure each subagent with specific tool access rights, enabling fine-grained control over which capabilities are available for different task types.

Core Advantages

  • Memory Efficiency: Isolated contexts prevent the main conversation from becoming cluttered with task-specific details
  • Enhanced Accuracy: Specialized prompts and configurations lead to better results in specific domains
  • Workflow Consistency: Team-wide subagent sharing ensures uniform approaches to common tasks
  • Security Control: Tool access can be restricted based on subagent type and purpose

Getting Started with Subagents

1. Access the Subagent Manager

/agents

2. Create Your Subagent

  • Choose between project-specific or global subagents
  • Let Claude generate an initial version, then refine it to your needs
  • Provide detailed descriptions of the subagent's purpose and activation triggers
  • Configure tool access (leave empty to inherit all available tools)
  • Customize the system prompt using the built-in editor (press e)

3. Deploy and Utilize Your subagent becomes immediately available. Claude Code will automatically engage it when suitable, or you can explicitly request its help:

Implicitly requesting an agent:

> Have the code-reviewer subagent analyze my latest commits

Explicitly requesting an agent with @agent syntax:

> Have the @"code-reviewer (agent)" analyze my latest commits

Subagent Storage Locations

Type Path Availability Precedence
Project Subagents .claude/agents/ Current project only Higher
Global Subagents ~/.claude/agents/ All projects Lower

Note: When naming conflicts occur, project-specific subagents override global ones.

📖 Subagent Structure

Each subagent follows a standardized template:

---
name: subagent-name
description: When this agent should be invoked
tools: Read, Write, Edit, Bash, Glob, Grep
model: sonnet
---

You are a [role description]...

## Key steps to summarise what to do
[When invoked:]

## Define agent specific behaviour in detail
[Agent-specific checklists, patterns, guidelines]

## Communication Protocol
[Inter-agent communication specs]

## Development Workflow
[Structured implementation phases]

📝 Contributing

Contributions are welcome! Please follow these guidelines:

  1. New Subagent: Create a new .md file in the appropriate category directory
  2. Update Category README: Add your subagent to the category's README.md
  3. Update Main README: Add a link in this file under the correct category
  4. Plugin Update: Verify the .claude-plugin/plugin.json includes your agent
  5. Test: Verify the agent works as intended in Claude Code

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Support

  • Questions? Open an issue on GitHub
  • Found a bug? Report it with a detailed example
  • Want to suggest improvements? We'd love to hear your ideas!

Built with ❤️ by the Claude Code community

About

A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases

github.com/laywill/laywill

Resources

Readme

License

MIT license

Contributing

Contributing
Activity

Stars

2 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases 4

v2.2.0 Latest
Mar 4, 2026
+ 3 releases

Packages

 
 
 

Contributors

Languages

  • Shell 100.0%