Install · Plugins · Github Action · Docs

Context Engineering Kit

Hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint, focused on improving agent result quality and predictability.

Marketplace is based on prompts used daily by our company developers for a long time, while adding plugins from benchmarked papers and high-quality projects.

Supported Agents

Universal support based on agentskills.io and openskills standards.

Agent	How it works	Status
Claude Code	Native plugin system	✅ Native
Cursor	openskills → AGENTS.md	✅ Universal
Windsurf	openskills → AGENTS.md	✅ Universal
Cline	openskills → AGENTS.md	✅ Universal
OpenCode	Native skill support	✅ Native
Amp Code	openskills → AGENTS.md	✅ Universal

Key Features

Simple to Use - Easy to install and use without any dependencies. Contains automatically used skills and self-explanatory commands.
Token-Efficient - Carefully crafted prompts and architecture, preferring commands with sub-agents over skills when possible, to minimize populating context with unnecessary information.
Quality-Focused - Each plugin is focused on meaningfully improving agent results in a specific area.
Granular - Install only the plugins you need. Each plugin loads only its specific agents, commands, and skills. Each without overlap and redundant skills.
Scientifically proven - Plugins are based on proven techniques and patterns that were tested by well-trusted benchmarks and studies.

Quick Start

Step 1: Install Marketplaces and Plugin

Claude Code

Open Claude Code and add the Context Engineering Kit marketplace

/plugin marketplace add NeoLabHQ/context-engineering-kit

This makes all plugins available for installation, but does not load any agents or skills into your context.

Install any plugins, for example reflexion

/plugin install reflexion@NeoLabHQ/context-engineering-kit

Each installed plugin loads only its specific agents, commands, and skills into Claude's context.

Cursor, Windsurf, Cline, OpenCode

Commands installation is available for Cursor and OpenCode:

Cursor

Cursor does not support sub-agents, so the script installs only commands that do not use them.

Install per project to the .claude/commands directory by default (Cursor uses the .claude/commands folder for some reason):

curl -fsSL https://raw.githubusercontent.com/NeoLabHQ/context-engineering-kit/refs/heads/master/.bin/install-commands.sh | bash

Install globally to ~/.cursor/commands directory:

curl -fsSL https://raw.githubusercontent.com/NeoLabHQ/context-engineering-kit/refs/heads/master/.bin/install-commands.sh | bash -s -- --global

OpenCode

Install per project to .opencode/commands directory:

curl -fsSL https://raw.githubusercontent.com/NeoLabHQ/context-engineering-kit/refs/heads/master/.bin/install-commands.sh | bash -s -- --agent opencode

Install globally to ~/.config/opencode/commands directory:

curl -fsSL https://raw.githubusercontent.com/NeoLabHQ/context-engineering-kit/refs/heads/master/.bin/install-commands.sh | bash -s -- --agent opencode --global

Use OpenSkills to install skills for broad range of agents:

npx openskills install NeoLabHQ/context-engineering-kit
npx openskills sync

Step 2: Use Plugin

> claude "implement user authentication"
# Claude implements user authentication, then you can ask it to reflect on implementation

> /reflexion:reflect
# It analyses results and suggests improvements
# If issues are obvious, it will fix them immediately
# If they are minor, it will suggest improvements that you can respond to
> fix the issues

# If you would like it to avoid issues that were found during reflection to appear again,
# ask claude to extract resolution strategies and save the insights to project memory
> /reflexion:memorize

Alternatively, you can use the reflect word in

...

neolabhq/context-engineering-kit

README