Everything Claude Code — 38 Agents 156 Skills System

What it is

Everything Claude Code is a community-built plugin that bundles 38 specialized AI agents and 156 skills into a single installable package for Claude Code. It covers 12 language ecosystems and was an Anthropic hackathon winner.

The target audience is developers who use Claude Code daily and want ready-made agents for tasks like code review, testing, refactoring, and documentation across multiple languages without configuring each one individually.

How it saves time or tokens

Instead of writing custom prompts for each task, you get pre-tuned agents that already know the context for their specialty. Each agent carries its own skill set, so you skip the prompt-engineering loop. The multi-agent orchestration routes your request to the right specialist, reducing wasted tokens on generic completions.

How to use

1. Install the plugin from the Claude Code plugin marketplace:

/plugin marketplace add affaan-m/everything-claude-code

1. The 38 agents and 156 skills activate automatically based on your project context.
2. Use natural language in Claude Code as usual. The orchestrator routes to the matching agent.

Example

# Install via plugin marketplace
/plugin marketplace add affaan-m/everything-claude-code

# Once installed, agents activate by context.
# For example, opening a Python file triggers the Python specialist agent.
# Opening a Rust file triggers the Rust agent.

Related on TokRepo

• AI Tools for Coding — Browse more coding-focused AI tools and workflows
• Prompt Library — Curated prompts that pair well with multi-agent setups

Key considerations

When evaluating Everything Claude Code for your workflow, consider the following factors. First, assess whether your team has the technical prerequisites to adopt this tool effectively. Second, evaluate the maintenance burden against the productivity gains. Third, check community activity and documentation quality to ensure long-term viability. Integration with your existing toolchain matters more than feature count alone. Start with a small pilot project before rolling out across the organization. Monitor resource usage during the initial adoption phase to identify bottlenecks early. Document your configuration decisions so team members can onboard independently.

Common pitfalls

• Installing on a machine with limited RAM may slow down agent initialization since 38 agents load context on demand.
• Not all 12 language ecosystems may be relevant to your project; unused agents add no overhead but can clutter skill listings.
• The plugin depends on a specific Claude Code version; check compatibility before updating either the plugin or Claude Code itself.