awesome-claude

Name: awesome-claude
Author: webfuse-com

Issues

A curated list of awesome things related to Anthropic Claude

1,658stars

384forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/webfuse-com/awesome-claude

Getting Started

Guides for using ai agents skills like awesome-claude.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportIssues

Last scanned: 4/28/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "awesome-lint: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "basic-ftp: Basic FTP has Path Traversal Vulnerability in its downloadToDir() method",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "brace-expansion: brace-expansion: Zero-step sequence causes process hang and memory exhaustion",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "git-clone: Command injection in git-clone",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "got: Got allows a redirect to a UNIX socket",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "js-yaml: js-yaml has prototype pollution in merge (<<)",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "markdown-link-check: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "undici: Undici has an unbounded decompression chain in HTTP responses on Node.js Fetch API via Content-Encoding leads to resource exhaustion",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "validator: validator.js has a URL validation bypass vulnerability in its isURL function",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "xmlbuilder2: Vulnerability found",
      "severity": "medium"
    }
  ],
  "status": "FAILED",
  "scannedAt": "2026-04-28T06:29:56.596Z",
  "semgrepRan": false,
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is awesome-claude?

awesome-claude is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by webfuse-com. A curated list of awesome things related to Anthropic Claude. It has 1,658 GitHub stars.

Is awesome-claude safe to use?

awesome-claude failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.

How do I install awesome-claude?

Clone the repository with "git clone https://github.com/webfuse-com/awesome-claude" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is awesome-claude written in?

awesome-claude is primarily written in TypeScript. It is open-source under webfuse-com on GitHub, so you can review or fork the full source.

Are there alternatives to awesome-claude?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh awesome-claude against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

244,886

vox-director ghost-os

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

Awesome Claude

AI assistant by Anthropic for complex reasoning, code generation, and analysis tasks.

Claude is a large language model developed by Anthropic that excels at complex reasoning, code generation, and analysis tasks. Built with Constitutional AI principles, Claude provides reliable assistance for programming, writing, research, and problem-solving while maintaining safety and accuracy.

📋 Contents

🏢 Official Anthropic Resources
🛠️ Claude Code & Model Context Protocol (MCP)
⭐ Community Curated Lists
🧩 Extensions & Integrations
💻 Applications
📚 Educational Resources
👥 Community

Building with the Web? Check out awesome-webmcp - a curated list of awesome things related to the WebMCP W3C standard.

🏢 Official Anthropic Resources

The authoritative source for everything Claude - directly from Anthropic

🧠 Current Models (2026)

Claude Fable 5 (Jun 9, 2026) - Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work. State-of-the-art on nearly all tested benchmarks — software engineering, knowledge work, vision, and scientific research — with its lead growing on longer, more complex tasks (highest score on Cognition's FrontierBench, first model past 90% on Anthropic's core long-running analytics benchmark, strongest finance model Anthropic has tested). Thinking is always on; the raw chain of thought is never returned. Safety classifiers route high-risk requests (cybersecurity, bio/chem, model distillation — under 5% of sessions) to Opus 4.8. Requires 30-day data retention (not available under zero data retention). Claude Mythos 5 is the same underlying model with safeguards lifted for authorized users (Project Glasswing). Announcement | Docs | System Card
Claude Opus 5 (Jul 24, 2026) - The model to start with for complex agentic coding and enterprise work, and a step change over Opus 4.8 on deep reasoning, long-horizon agentic execution, and test-time compute scaling — at half the price of Fable 5. Thinking is now on by default (omit thinking and you get adaptive), the full low→max effort ladder is supported, and the minimum cacheable prompt drops to 512 tokens. Fast mode (speed: "fast") is available on the Claude API only. Announcement | Migration guide | System Card
Claude Sonnet 5 (Jun 30, 2026) - The best combination of speed and intelligence, reaching what used to be Opus-tier quality on coding and agentic tasks. First Sonnet-tier model with the xhigh effort level and high-resolution vision (2,576px long edge). Uses the newer tokenizer, so the same text produces ~30% more tokens than Sonnet 4.6 — re-baseline your token budgets when you migrate. Announcement | System Card
Claude Haiku 4.5 (Oct 2025) - Still the fastest model with near-frontier intelligence. Perfect for high-volume, real-time, and sub-agent tasks. Announcement

Key specs (API):

Fable 5: claude-fable-5 • $10/$50 per MTok • 1M context / 128K max output
Opus 5: claude-opus-5 • $5/$25 per MTok • 1M context / 128K max output
Sonnet 5: claude-sonnet-5 • $3/$15 per MTok ($2/$10 introductory through Aug 31, 2026) • 1M context / 128K max output
Haiku 4.5: claude-haiku-4-5 • $1/$5 per MTok • 200K context / 64K max output

Model IDs from the 4.6 generation onward are dateless but still pinned snapshots, not evergreen pointers — see Model IDs and versioning. Full comparison: Models overview | Pricing

Previous generations (still active)

Claude Opus 4.8 (May 28, 2026) - Highly autonomous, strong on long-horizon agentic work, knowledge work, and memory, with clearer and warmer writing than 4.7. Introduced Dynamic Workflows in Claude Code (plan work, run hundreds of parallel subagents in one session, verify before returning), effort control on claude.ai, and mid-conversation system messages via the Messages API. Still the recommended fallback for Fable 5 refusals. Announcement | What's new | System Card
Claude Opus 4.7 (Apr 16, 2026) - Introduced high-resolution vision (images up to ~3.75 MP / 2,576px long edge), the xhigh effort level, and task budgets. Announcement | System Card
Claude Opus 4.6 (Feb 5, 2026) - Introduced the 1M token context window and adaptive thinking. Announcement | System Card
Claude Sonnet 4.6 (Feb 17, 2026) - The previous speed/cost balance pick, superseded by Sonnet 5. Announcement

Migrating? Extended thinking with a fixed budget_tokens, the sampling parameters (temperature/top_p/top_k), and last-assistant-turn prefills all return a 400 on the Claude 5 family. Use adaptive thinking plus the effort parameter instead, and structured outputs in place of prefills. Full list: Migration guide.

🔌 API & Developer Platform

Claude Developer Console - API keys, prompt testing, usage monitoring, Claude Code sessions.
Official Documentation - Full reference for Messages API, tool use, computer use, prompt caching, structured outputs, citations, MCP Connector, and Claude Code.
Models & Pricing - Latest model IDs, pricing, context windows, thinking features, and cloud provider IDs.

🔧 SDKs & Development Tools

Official Client SDKs - Full feature parity: messages, tools, streaming, caching, computer use.

anthropic-sdk-python - Python SDK with async support and type hints.
anthropic-sdk-typescript - TypeScript/JavaScript SDK for Node.js and browsers.
anthropic-sdk-java - Java/Kotlin SDK with modern features.
anthropic-sdk-go - Go SDK with idiomatic design.
anthropic-sdk-ruby - Ruby SDK.
anthropic-sdk-csharp - C#/.NET SDK (Beta).
anthropic-sdk-php - PHP SDK (Beta).

Agent SDKs - Build custom autonomous agents with Claude Code capabilities.

claude-agent-sdk-python - Python Agent SDK. Docs
claude-agent-sdk-typescript - TypeScript Agent SDK.

Starters

Claude Cookbook - Official notebooks and recipes for common patterns (RAG, tool use, Skills, MCP).
Claude Quickstarts - Ready-to-deploy example apps.

☁️ Cloud Providers

Official access to Claude models through cloud providers (all carry the Claude 5 family — Fable 5 / Opus 5 / Sonnet 5)

Amazon Bedrock - Fully managed access to the latest Claude models (Fable 5, Opus 5, Sonnet 5, Haiku 4.5). Claude 5 models are served through the Messages-API Bedrock endpoint and take an anthropic. ID prefix (e.g. anthropic.claude-opus-5). Supports cross-region inference, latency optimizations, fine-tuning, agents, guardrails, and deep AWS integration. (Note: Managed Agents and Anthropic server-side tools are not available on Bedrock — use Claude API + tool use there.)
Claude Platform on AWS - Anthropic-operated access via AWS infrastructure: SigV4 auth, IAM access control, AWS Marketplace billing, and same-day API parity with the first-party API. Model IDs are the bare first-party strings (no `anthropi