context-engineering-kit
Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.
Context Engineering Kit is a hand-crafted collection of Claude Code plugins and agent skills that improve AI coding assistant output quality through advanced context engineering patterns. It provides token-efficient, scientifically-validated techniques including reflexion loops, spec-driven development, code review automation, and multi-agent orchestration. Compatible with Claude Code, Cursor, Antigravity, Gemini CLI, and other AI coding assistants, the kit offers granular plugin installation so developers can add only the capabilities they need. Each plugin focuses on specific improvements like test-driven development, git workflow automation, or continuous improvement analysis.
Key Features
Use Cases
- 01Implementing features with automatic reflection and quality verification to catch missed requirements before shipping
- 02Generating production-ready code from specifications with 95-99% accuracy on complex multi-file changes
- 03Automating comprehensive pull request reviews with specialized agents analyzing security, bugs, and code quality
- 04Managing test-driven development workflows with anti-pattern detection and coverage analysis
- 05Performing root cause analysis on bugs using Kaizen techniques like Five Whys and Fishbone diagrams
- 06Creating git commits and pull requests with conventional commit messages and proper formatting
Related Plugins
View moreandrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
context-engineering-kit — FAQ
What is Context Engineering Kit?+
Context Engineering Kit is a collection of Claude Code plugins and agent skills that use advanced context engineering techniques to improve AI coding assistant output quality. It includes reflexion loops, spec-driven development, code review automation, and multi-agent orchestration patterns based on peer-reviewed research.
How do I install Context Engineering Kit in Claude Code?+
Run '/plugin marketplace add NeoLabHQ/context-engineering-kit' to add the marketplace, then install individual plugins with '/plugin install <plugin-name>@NeoLabHQ/context-engineering-kit' (e.g., '/plugin install reflexion@NeoLabHQ/context-engineering-kit'). Each plugin loads only its specific agents and skills.
Which AI coding clients work with Context Engineering Kit?+
The kit supports Claude Code (full experience with per-plugin installation), Cursor, Codex, OpenCode (via npx skills), Gemini CLI, and Antigravity CLI. Different installation methods provide varying levels of functionality, with Claude Code offering the most complete feature set including sub-agents.
Do I need API keys or paid services to use Context Engineering Kit?+
No external API keys are required. The kit works with your existing AI coding assistant and its configured models. Some features like GitHub integration require the GitHub CLI (gh) to be installed and authenticated.
Is Context Engineering Kit free to use?+
Yes, Context Engineering Kit is open source under the GPL 3.0 license and free to use. It incurs standard token costs from your AI assistant provider based on the model and complexity of operations.
What's the difference between reflexion, SADD, and SDD plugins?+
Reflexion adds lightweight reflection loops (1k-5k token overhead) for self-correction. SADD (Subagent-Driven Development) uses fresh sub-agents per task with quality gates (1.5x-5x token cost, 83-92% accuracy). SDD (Spec-Driven Development) creates detailed arc42 specifications first (5x-35x token cost, 93-99% accuracy for complex tasks).
How do I install context-engineering-kit?+
Open the source repository on GitHub and follow its README. context-engineering-kit is a plugin — MCP Agents Market links you directly to the official repo.
Is context-engineering-kit free?+
context-engineering-kit is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.