Context Engineering for AI Development
Give your AI assistants (Cursor, Claude, Copilot, Codex, Gemini, Aider, Continue, Windsurf) structured context through markdown files. ContextKit creates a knowledge base that ensures AI generates code matching your exact patterns, style, and architecture—no more hallucinated code or mismatched conventions.
ContextKit is a CLI tool that provides context-engineering capabilities by creating .contextkit/ directories with project standards, guidelines, and patterns that AI assistants read automatically.
The problem: LLMs are great at syntax, not at your conventions. Generic AI output requires manual fixes for style, structure, and architecture.
The solution: ContextKit provides your AI with:
- Glossary of project terminology and business terms (e.g.,
checkout,customer,order) - Standards for code style, testing patterns, and architecture
- Templates with canonical component shapes
Update .md files as your project evolves; the AI follows.
Works with: Cursor • Claude Code • GitHub Copilot • Codex CLI • Gemini CLI • Aider • Continue • Windsurf
Each platform gets auto-loaded bridge files (CLAUDE.md, AGENTS.md, GEMINI.md, .windsurfrules, etc.) so your AI tools read project standards automatically.
Requirements: Node.js 14.x+ (16.x+ recommended) and npm/yarn. Optional: Git for hooks, AI tools for usage.
# Step 1: Install globally (recommended)
npm i -g @nolrm/contextkit
# Step 2: Navigate to your project and install
cd your-project
contextkit installThis creates .contextkit/ with skeleton context files (blank templates to be filled by AI):
.contextkit/
standards/ # Skeleton files: code-style.md, testing.md, architecture.md, ai-guidelines.md, workflows.md
# Real files: glossary.md (universal), README.md (overview)
commands/ # analyze.md (project analysis & customization)
templates/ # example component template
Generate content with AI (recommended):
ck analyze
# AI scans your codebase and generates content for the skeleton files
# or in Cursor chat: @.contextkit/commands/analyze.mdck analyze, manually review and edit the generated content to match your exact needs. The AI provides a starting point, but you must customize it.
Perfect for teams where members use different AI tools:
# First team member (any tool) - sets up the project
contextkit install
# Each team member adds their platform
ck claude # creates CLAUDE.md + .claude/rules/
ck cursor # creates .cursor/rules/ (scoped .mdc files)
ck copilot # creates .github/copilot-instructions.md
ck codex # creates AGENTS.md
ck gemini # creates GEMINI.md + .gemini/settings.json
ck aider # creates CONVENTIONS.md + .aider/rules.md
ck continue # creates .continue/rules/ + config.yaml
ck windsurf # creates .windsurfrules + .windsurf/rules/
ck vscode # alias for copilotEach platform generates bridge files that the AI tool auto-reads. If a bridge file already exists (e.g., you have a custom CLAUDE.md), ContextKit appends its section below your content instead of overwriting. Share your .contextkit/standards/*.md files with the team and everyone gets the same context.
Prompt
"Add checkout flow for customer"
What the AI does with ContextKit
- Reads
glossary.md→checkout= checkout process;customer= customer account - Applies
code-style.md→ strict TS, functional components - Follows
testing.md→ numbered test cases
Result (diff)
- const Checkout = () => <button>Buy</button>
+ export function CheckoutFlow({ customer }: { customer: string }) {
+ // Uses customer from glossary context
+ return <div>Checkout for {customer}</div>
+ }Cursor — rules auto-load from .cursor/rules/
@.contextkit/commands/analyze.md
Claude Code — reads CLAUDE.md + .claude/rules/ automatically
claude "create checkout flow for customer"GitHub Copilot — reads .github/copilot-instructions.md automatically
@.contextkit Create checkout flow for customer
Codex CLI — reads AGENTS.md automatically
codex "create checkout flow for customer"CLI (Chat with AI)
ck ai "create checkout flow for customer"- 🧠 Context Engineering - Structured MD files your AI reads automatically
- 🔍 Smart Analysis - AI generates standards content based on your codebase
- 🌍 Project Agnostic - Works with React, Vue, Node.js, PHP, Python, Rust, monorepos—any project type
- 🤖 Multi-Platform - Works with Cursor, Claude Code, Copilot, Codex, Gemini, Aider, Continue, Windsurf
- 🛡️ Safe Install - Backs up existing files with rollback support
- ⚡ Zero Config - Auto-detects package managers and AI tools
- ✅ Policy Enforcement - Configurable validation with
ck check - 📝 Corrections Tracking - Track AI performance issues with corrections log
- 🔄 Workflow Orchestration - Structured workflows with
ck run - 📦 Registry System - Share standards across teams with
ck publish/pull - 📊 Observability Dashboard - Visual metrics and compliance tracking
# Installation & Setup
ck install # set up .contextkit in this repo
ck claude # add Claude Code integration (CLAUDE.md + rules)
ck cursor # add Cursor integration (scoped .mdc rules)
ck copilot # add GitHub Copilot integration
ck codex # add Codex CLI integration (AGENTS.md)
ck gemini # add Gemini CLI integration (GEMINI.md)
ck aider # add Aider integration (CONVENTIONS.md)
ck continue # add Continue integration
ck windsurf # add Windsurf integration (.windsurfrules)
ck vscode # alias for copilot
# Analysis & Updates
ck analyze # customize standards to your project
ck update # pull latest updates
ck status # check install & integrations
# Validation & Compliance
ck check # validate installation & policy compliance
ck check --strict # treat warnings as errors
# Corrections Logging
ck note "message" # add note to corrections log
ck note "AI issue" --category "AI Behavior" --priority HIGH
# Workflow Orchestration
ck run <workflow> # run structured workflow
ck run create-component # example workflow
ck run create-component --interactive # interactive mode
# Registry & Versioning
ck publish --name @company/react-standards --version 1.0.0
ck pull @company/react-standards@1.0.0
ck pull @company/react-standards@latest --backup
# Observability
ck dashboard # start web dashboard
ck dashboard --no-server # CLI metrics only
# AI Usage (loads .contextkit context automatically)
ck "create a button" # quick AI chat with context
ck ai "create a button" # explicit AI command• 🐛 Issues • 💬 Discussions
MIT
Marlon Maniti
GitHub: @nolrm