Agent Smith
About
Agent Smith is a CLI tool that auto-generates an AGENTS.md file from your codebase. AGENTS.md is an open standard for giving AI coding assistants context about a project, adopted by 60,000+ projects and supported by tools like Cursor, GitHub Copilot, Claude Code, VS Code, and…
Details
- Author
- jpoindexter
- Downloads
- 378
- Categories
- Developer Tools, AI
Jump to
- Scans codebase for components, hooks, API routes, and more
- Detects frameworks like Next.js, shadcn/ui, and Prisma
- Generates AGENTS.md with approximately 11K tokens by default
- Multiple output modes: compact, compress, minimal, XML
- Integrates automatically with AI coding tools (no config needed)
- Supports dry-run preview and custom output file location
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Agent SmithCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Run directly with npx @jpoindexter/agent-smith in your project directory or install globally with npm install -g @jpoindexter/agent-smith. Use agentsmith (default), or specify a directory with agentsmith ./my-project. Additional flags include --dry-run (preview without writing), --output <file> (custom output), --force (overwrite existing), and output mode flags: --compact, --compress, --minimal, --xml, and a file tree visualization.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"agent smith": {
"agentsmith": {
"command": "npx",
"args": [
"-y",
"@jpoindexter/agent-smith",
"--mcp"
]
}
}
}
}McpServers
{
"agentsmith": {
"command": "npx",
"args": [
"-y",
"@jpoindexter/agent-smith",
"--mcp"
]
}
}┏━┓┏━╸┏━╸┏┓╻╺┳╸ ┏━┓┏┳┓╻╺┳╸╻ ╻ ┣━┫┃╺┓┣╸ ┃┗┫ ┃ ┗━┓┃┃┃┃ ┃ ┣━┫ ╹ ╹┗━┛┗━╸╹ ╹ ╹ ┗━┛╹ ╹╹ ╹ ╹ ╹
Auto-generate AGENTS.md from your codebase
Stop writing AGENTS.md by hand. Run agentsmith and it scans your codebase to generate a comprehensive context file that AI coding tools read automatically.
- Cursor
- GitHub Copilot
- Claude Code
- VS Code
- Gemini CLI
- And 20+ more tools
AI tools automatically discover and readAGENTS.mdfiles - no configuration needed.
Instead of writing AGENTS.md manually, agentsmithscans your codebaseand generates it:
npx @jpoindexter/agent-smith agentsmith Scanning /Users/you/my-project... ✓ Found 279 components ✓ Found 5 components with CVA variants ✓ Found 37 color tokens ✓ Found 14 custom hooks ✓ Found 46 API routes (8 with schemas) ✓ Found 87 environment variables ✓ Detected Next.js (App Router) ✓ Detected shadcn/ui (26 Radix packages) ✓ Found cn() utility ✓ Found mode/design-system ✓ Detected 6 code patterns ✓ Found existing CLAUDE.md ✓ Found .ai/ folder (12 files) ✓ Found prisma schema (28 models) ✓ Scanned 1572 files (11.0 MB, 365,599 lines) ✓ Found 17 barrel exports ✓ Found 15 hub files (most imported) ✓ Found 20 Props types ✓ Found 40 test files (12% component coverage) ✓ Generated AGENTS.md ~11K tokens (9% of 128K context) Help improve agentsmith → github.com/jpoindexter/agentsmith/issues
# Run directly (no install needed) npx @jpoindexter/agent-smith # Or install globally npm install -g @jpoindexter/agent-smith
# Generate AGENTS.md in current directory agentsmith # Generate for a specific directory agentsmith ./my-project # Preview without writing (dry run) agentsmith --dry-run # Custom output file agentsmith --output CONTEXT.md # Force overwrite existing file agentsmith --force
Any feedback is helpful — bugs, ideas, questions, or just telling us what you're building.
Runagentsmith feedbackand pick what you want to do: report a bug, request a feature, ask a question, share an idea, or show what you built. Bug reports auto-collect diagnostics and pre-fill the issue for you.
Privacy:agentsmith does not collect, send, or store any data. Everything runs locally on your machine. The feedback command gathers some basic info (tool versions, OS, aggregate file counts) to help with bug reports — but nothing is sent anywhere automatically. You see exactly what's collected and you choose whether to include it. Don't feel like sharing logs? A simple description is just as valuable.
- Report a bug
- Request a feature
- Ask a question
- Share an idea
- Show and tell
# Default - comprehensive output (~11K tokens) agentsmith # Compact - fewer details (~20% smaller) agentsmith --compact # Compress - signatures only (~40% smaller) agentsmith --compress # Minimal - ultra-compact (~3K tokens) agentsmith --minimal # XML format (industry standard, matches Repomix) agentsmith --xml # Include file tree visualization agentsmith --tree
Now detectsZod validation schemasandTypeScript typesfrom your API routes:
- POST /api/contact - Request: contactSchema { name: string (max: 100, min: 1, "Name is required") email: string (email: Invalid email address) subject: "sales" | "support" | "billing" | ... }
AI agents can now see your API contracts instead of guessing field names!
Analyzes your codebase complexity and recommends AI model effort levels:
Complexity by Area: - 🔴 Database: Maximum effort (most capable model) - 🟡 API Routes: Standard effort (balanced model) - 🟢 Utilities: Minimal effort (fast, low-cost model)
- Global schema caching: O(n²) → O(n) for shared schemas
- 20-40% fasteron large codebases
Extracts GraphQL schema definitions from.graphqland.gqlfiles.
Works withany AI provider(Claude, GPT, Gemini) - no hardcoded model names.
# Copy output to clipboard agentsmith --copy # Include uncommitted git changes agentsmith --include-diffs # Split large repos into chunks agentsmith --split-output 100kb # Creates AGENTS-001.md, AGENTS-002.md, etc. # Include security audit (npm audit) agentsmith --security # Monorepo support - generate for each package agentsmith --monorepo # Start as MCP server for AI tool integration agentsmith --mcp
agentsmith can run as an MCP (Model Context Protocol) server for AI tool integration:
5 MCP Resources(live subscriptions with caching):
- agents://agents-md- Auto-generated AGENTS.md
- agents://api-schemas- All API route schemas
- agents://database-schema- Database models with fields and relations
- agents://graphql-schemas- GraphQL type definitions
- agents://complexity-report- Codebase complexity analysis
Createagentsmith.config.jsonin your project root:
{ "output": "AGENTS.md", "exclude": [ "/test/", "/stories/", "/fixtures/" ] }
- TL;DR- Stack, component count, key imports, high-impact files
- Getting Started- Auto-generated setup instructions
- Project Overview- Framework, language, styling, statistics
- Critical Rules- With WRONG/RIGHT code examples
- Components- Full inventory grouped by category
- Hub Files- Most imported files (changes have wide impact)
- Unused Components- Potentially dead code warnings
- Preferred Imports- Barrel imports for cleaner code
- Custom Hooks- With client-only markers
- API Routes- Grouped by path with methods, auth, and request/response schemas
- GraphQL Schemas- Type definitions from .graphql/.gql files
- Database Models- Fields and relations
- Environment Variables- Required vs optional
- Code Patterns- Detected patterns with examples
- Design Tokens- Color tokens with usage guidance
- AI Recommendations- Model effort levels based on codebase complexity
- Commands- npm scripts
- Security- Vulnerabilities and outdated packages (with --security)
# AGENTS.md > Auto-generated by agentsmith ## TL;DR - Stack: Next.js 16.0.10 + TypeScript 5 + Tailwind 4.0.9 + shadcn/ui - Components: 279 total — USE EXISTING, don't create new - Key imports: cn() from @/lib/utils, mode from @/design-system - High-impact files: design-system/index, utils, button, card - Database: prisma with 28 models - API: 46 routes (31 protected) ## Getting Started
// WRONG <div className="rounded border p-4">...</div> // RIGHT <Card><CardContent>...</CardContent></Card>
// WRONG className="bg-blue-500 text-white" // RIGHT className="bg-primary text-primary-foreground"
## Why? AI coding tools work better when they understand your codebase: - ❌ AI generates bg-blue-500 instead of your bg-primary token - ❌ AI creates a new Button when you already have one with 9 variants - ❌ AI ignores your patterns and conventions With AGENTS.md: - ✅ AI knows your components and uses them - ✅ AI follows your design tokens - ✅ AI matches your patterns ## Comparison | Tool | Focus | Approach | |------|-------|----------| | agentsmith | AGENTS.md generation | Scans codebase, generates context | | Repomix | Code packing | Packs files into single XML | | Code2Prompt | Prompt building | Builds prompts from code | agentsmith is specifically designed for the AGENTS.md standard with opinionated rules about component reuse and design tokens. ## Works great in - Next.js + Tailwind + shadcn/ui projects - React apps with component libraries - Any TypeScript codebase with reusable components ## License MIT --- A theft.studio project
```
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
