awesome-agent-tools

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 5 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This project is a curated list (often called an "awesome list") and marketplace of AI agent skills, MCP servers, and development tools. It serves as a directory to help developers discover and install pre-built components for platforms like Claude Code, Codex, and Cursor.

Security Assessment
The overall risk is Low. The automated code scan reviewed five files and found no dangerous patterns, hardcoded secrets, or requests for dangerous permissions. Because this is primarily a collection of links and installation instructions rather than an active application, the repository itself does not natively execute shell commands, access local files, or make independent network requests. However, since the installation guides instruct users to run commands (like git clone and bash scripts) that pull third-party code, the actual security risk depends entirely on the external tools being installed. Users should vet individual tools before adding them.

Quality Assessment
The repository appears to be very new but actively maintained, with its latest push occurring today. However, it suffers from low visibility, having only 5 GitHub stars, which indicates a very small user base and limited community testing so far. There is a minor flag regarding licensing: the automated scan detected "NOASSERTION," even though the documentation claims an MIT license. This usually means the license text is missing or improperly formatted in the repository files, which is a minor administrative oversight rather than a security issue.

Verdict
Safe to use as a discovery directory, but vet individual third-party tools before installing them.
SUMMARY

Curated Skills, MCP servers, and tools for AI agents.

README.md

Awesome Agent Tools 🤖✨

The hybrid marketplace for AI agent development: original skills, curated tools, and cross-platform support.

For developers building with AI agents | Original Skills + Curated Tools | Cross-Platform

Supports: Claude Code (⭐ Recommended) | Codex | Cursor | Windsurf | Antigravity

Awesome
License: MIT
PRs Welcome

English | 中文


Why This Collection?

Unlike other lists, we offer:

  • 🔀 Hybrid Marketplace: Original skills we built + carefully curated third-party tools
  • 👨‍💻 For Developers: Built by developers, for developers building with AI agents
  • 🌐 Cross-Platform: Works with Claude Code, Codex, Cursor, Windsurf, Antigravity, and more
  • ⚡ Multi-Type: Skills + MCP Servers + Agents + Plugins (not just one category)
  • ✨ Quality-First: Every tool is vetted and tested, not a link dump
  • 🎯 Agent Development: Special focus on agent workflows, parallel execution, and automation

✨ Features

  • 🎯 Curated Collection - Only high-quality, well-tested tools and skills
  • 🔧 Cross-Platform - Works with Claude Code, Codex, Cursor, Windsurf, Antigravity
  • 📦 Easy Installation - Simple one-command setup for most tools
  • 🌍 Community-Driven - Open source and welcoming contributions
  • 🚀 MCP-Powered - Leverages the Model Context Protocol standard
  • 📚 Well-Documented - Clear instructions and examples for everything

Quick Install

Claude Code (⭐ Recommended)

# Install as marketplace (browse all skills)
/plugin marketplace add Awakehsh/awesome-agent-tools
/plugin install awesome-agent-tools@awesome-agent-tools

# Or add to settings manually
# Add to ~/.claude/settings.json:
# {
#   "extraKnownMarketplaces": {
#     "awesome-agent-tools": {
#       "source": {
#         "source": "github",
#         "repo": "Awakehsh/awesome-agent-tools"
#       }
#     }
#   },
#   "enabledPlugins": {
#     "awesome-agent-tools@awesome-agent-tools": true
#   }
# }

# Or install individual skill
claude skill add https://github.com/Awakehsh/awesome-agent-tools/tree/main/skills/learn

Codex

# Install a single skill (in Codex CLI chat, not your shell)
$skill-installer https://github.com/Awakehsh/awesome-agent-tools/tree/main/skills/learn

# Restart Codex to pick up new skills
# Install all skills (recommended if this repo will keep adding skills)
git clone https://github.com/Awakehsh/awesome-agent-tools ~/awesome-agent-tools
mkdir -p ~/.codex/skills

# Option A (recommended): symlink all skills for easy updates via `git pull`
for d in ~/awesome-agent-tools/skills/*; do ln -s "$d" ~/.codex/skills/; done

# Option B: copy all skills (no symlinks)
# cp -R ~/awesome-agent-tools/skills/* ~/.codex/skills/

# Update later
# (cd ~/awesome-agent-tools && git pull) && restart Codex

Cursor / Windsurf / Antigravity

# Import from GitHub URL in settings
# Or configure MCP server integration
# See detailed guide below

Detailed setup: Cross-Platform Guide


🤖 Agent Development Highlights

Special features for building AI agent systems:

Feature Description Platform
Custom Sub-Agents Independent contexts for specialized tasks (guide) Claude Code
Parallel Execution Run multiple agents simultaneously (examples) Claude Code
Agent Skills Reusable skill bundles for agents Claude Code, Codex
MCP Integration Connect agents to external tools & data sources All platforms
Workflow Automation Slash commands, hooks, and agent orchestration Claude Code

New to agents? Check out our Agent Development Guide for workflows, patterns, and best practices.


📦 What's Included

🎯 Editor's Picks (Quick Wins)

Start here if you're new - these tools deliver immediate value:

Tool Type What It Does Platform
ralph-loop Official Plugin Overnight automated development with iterative loops Claude Code
learn Original Skill Auto-capture insights to project memory (CLAUDE.md, AGENTS.md) All
context-engineering-kit Community Tool Advanced context engineering, 8-21% quality improvement All
codex-cli Original Skill Call OpenAI Codex from Claude Code for plan review Claude Code
awesome-mcp-servers Curated List 79k+ stars - The definitive MCP server collection All
superpowers Skill Framework 35k+ stars - Complete AI agent development workflow (TDD, code review, debugging) Claude Code
everything-claude-code Config Collection Battle-tested agents/skills/commands/hooks from hackathon winner Claude Code

🛠️ Original Tools

Open-source contributions from this repository:

Skills (3)

context-architect

Context engineering tool for building AI agent systems — design system prompts, tool sets, examples, and runtime context management.

  • Purpose: Transform requirements into production-ready Context Engineering Packages through guided workflows
  • Philosophy: Context-first design — manage the entire information state (prompts, tools, examples, retrieval, compaction), not just instructions
  • Use Cases:
    • Design multi-agent orchestration systems with context isolation and sub-agent summary constraints
    • Plan token budgets, tool sets, and few-shot examples with engineering rigor
    • Manage long-horizon agent sessions with compaction, note-taking, and Just-in-Time retrieval strategies
  • Key Benefit: Goes beyond prompt engineering to full context engineering — based on Anthropic's context engineering research
  • Install: claude skill add https://github.com/Awakehsh/awesome-agent-tools/tree/main/skills/context-architect

Learn more →

codex-cli

Call OpenAI Codex CLI from Claude Code for plan review and code analysis.

  • Use Cases: Plan review, code analysis, technical discussions, multi-round iteration
  • Install: claude skill add https://github.com/Awakehsh/awesome-agent-tools/tree/main/skills/codex-cli

Learn more →

learn

Universal learning system that extracts insights from conversations and updates project memory files.

  • Use Cases: Capture learnings, auto-route to docs (CLAUDE.md, AGENTS.md), cross-platform sync
  • Install: claude skill add https://github.com/Awakehsh/awesome-agent-tools/tree/main/skills/learn

Learn more →

Agents (1)

tech-scout

Technical research specialist. Searches industry solutions, design patterns, and bug fixes from GitHub and web sources.

  • Purpose: Parallel research during development workflows
  • Philosophy: Don't waste time reinventing - learn from industry solutions first
  • Use Cases:
    • Feature planning - Search architecture patterns and design approaches
    • Bug debugging - Find solutions for errors and common problems
    • Technology comparison - Research pros/cons of libraries and frameworks
  • Key Benefit: Runs independently without blocking main workflow, returns structured reports with comparisons and sources
  • Install: Copy agents/tech-scout/ to ~/.claude/agents/ or install via marketplace

Learn more → | All Agents Documentation →

MCP Servers (Coming Soon)

  • Custom integrations
  • Specialized tooling
  • Watch this space!

🌟 Curated Recommendations (30+ Tools)

Carefully vetted third-party tools organized by category:

See the full curated list: AWESOME.md

Categories:

  • 🎯 Official Skills - From Anthropic, OpenAI
  • 🌟 Community Skills - Trusted developers
  • 🔧 MCP Servers - Official and community-built
  • 🛠️ Tools & Utilities - Installers, frameworks, resources

📚 Guides & Documentation


Use Cases

Category Examples
Development Code generation, refactoring, testing, debugging
Content Documentation, translation, technical writing
Research Data analysis, summarization, literature review
Automation CI/CD, task automation, monitoring

Platform Support

Platform SKILL.md MCP Memory Files Recommended
Claude Code CLAUDE.md ⭐ Best
Codex AGENTS.md Great
Cursor .cursorrules Great
Windsurf .windsurfrules Good
Antigravity .agent/rules/ Good

Why we recommend Claude Code: Best skill management, excellent MCP support, great documentation.


Claude Code Tips

Claude Code has powerful built-in features you might not know:

Feature Description
/skills Create custom skills directly in CLI
/agents Create custom sub-agents with independent contexts (learn more)
CLAUDE.md Project memory that prevents repeated mistakes
Slash Commands Store workflows in .claude/commands/ for automation
Parallel Agents Run multiple agents simultaneously for independent tasks (learn more)
Plan Mode Read-only codebase analysis before making changes

Pro tip from Anthropic team: Add mistakes to CLAUDE.md so Claude learns and doesn't repeat them.

Learn more: Official Docs | Creator's Workflow


Codex Tips

Codex skill loading is folder-based. A skill lives at ~/.codex/skills/<skill-name>/SKILL.md.

Tip Description
$skill-installer ... Run this in the Codex CLI chat (not your shell), then restart Codex
Verify install Check ~/.codex/skills/<skill-name>/SKILL.md exists
Create a new skill Make ~/.codex/skills/<skill-name>/SKILL.md (YAML frontmatter + Markdown)
Reload skills Restart Codex after adding or editing a skill folder

Resources

Official Documentation

Community Resources


Contributing

We welcome contributions! Here's how you can help:

  • Add Your Own Skill - Share your custom-built skills
  • Recommend Tools - Suggest great third-party skills and servers
  • Improve Documentation - Fix typos, add examples
  • Report Issues - Found a bug? Let us know!

See CONTRIBUTING.md for detailed guidelines.


License

MIT License. See LICENSE for details.

  • Our Content: Original skills and documentation are MIT licensed
  • Third-Party Content: Tools in AWESOME.md maintain their original licenses

⬆ Back to Top

Made with ❤️ by the community

Report Bug · Request Feature · Contribute

Yorumlar (0)

Sonuc bulunamadi