Package Exports

@qubiit/lmagent
@qubiit/lmagent/install.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@qubiit/lmagent) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

🧠 LMAgent: The Universal AI Agent Runtime

██╗     ███╗   ███╗ █████╗  ██████╗ ███████╗███╗   ██╗████████╗
██║     ████╗ ████║██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝
██║     ██╔████╔██║███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║   
██║     ██║╚██╔╝██║██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║   
███████╗██║ ╚═╝ ██║██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║   
╚══════╝╚═╝     ╚═╝╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝   
                                                  by QuBit

"Separate the reasoning from the execution."
LMAgent is the foundational runtime that empowers your AI Agents with standardized Skills, Rules, and Workflows across any IDE (Cursor, Windsurf, VSCode, Zed, Qodo).

🚀 Quick Start Guide

Get your universal agent infrastructure up and running in minutes.

📋 Prerequisites

Node.js 18+ installed.
An existing project (or create one with npm init).

Option A: Per-Project Setup (Recommended)

Use npx to run LMAgent without installing it globally. This ensures you always use the latest version and keeps your project dependencies clean.

# 1. Initialize LMAgent (Copies AGENTS.md, CLAUDE.md & Configs)
#    This gives your AI Agent the "Context" it needs to understand the skills.
npx @qubiit/lmagent init

# 2. Install Skills & Rules to your IDE
#    This configures .cursor, .vscode, or .windsurf with the actual executable prompts.
npx @qubiit/lmagent install

# 3. Verify System Status
npx @qubiit/lmagent doctor

Option B: Global Installation

If you prefer having the lmagent command available globally in your terminal:

# 1. Install Global Package
npm install -g @qubiit/lmagent

# 2. Run Commands Directly
lmagent init
lmagent install
lmagent doctor

Option C: Local Development (Contributors)

If you are developing the LMAgent framework itself:

git clone https://github.com/QuBit/lmagent.git
cd lmagent
npm install
npm link
lmagent install

🛠️ CLI Reference

LMAgent includes a powerful CLI to manage your AI context.

Command	Usage	Description
`init`	`npx @qubiit/lmagent init`	Initializes the project. Copies `AGENTS.md` (catalog) and `CLAUDE.md` to your root.
`install`	`npx @qubiit/lmagent install`	Core Command. Installs selected Skills, Rules & Workflows into your IDE configuration (Cursor, VSCode, Windsurf, etc.).
`update`	`npx @qubiit/lmagent update`	Alias for `install`. Use this to refresh your skills when new versions are released.
`doctor`	`npx @qubiit/lmagent doctor`	Verifies your environment, checking for correct file structures using `validate_skills` logic.
`validate`	`npx @qubiit/lmagent validate`	Scans all `SKILL.md` files for syntax errors or missing required fields.
`create-skill`	`npx @qubiit/lmagent create-skill`	Interactive wizard to generate a new Skill structure best practices.

🏛️ The 3-Pillar Architecture

LMAgent organizes AI capabilities into three distinct pillars, enforcing a clear separation of concerns.

graph TD
    A["🤖 AI Agent"] --> B("🛠️ Skills")
    A --> C("📜 Rules")
    A --> D("⚡ Workflows")
    
    B --> B1["{ide}/skills/"]
    B --> B2["Executable Tools & Scripts"]
    
    C --> C1["{ide}/rules/"]
    C --> C2["Behavioral Guardrails & Context"]
    
    D --> D1["{ide}/workflows/"]
    D --> D2["Standard Operating Procedures (SOPs)"]

1. 🛠️ Skills (Capabilities)

Executable units that allow the Agent to interact with the world.
Location: {ide}/skills/ or ~/.agents/skills/

Skill Name	Description	Tools Included
ai-agent-engineer	Expert in building LLM-based systems & MCP servers.	`create-agent`, `scaffold-mcp`
api-designer	Design REST/GraphQL contracts, OpenAPI standards.	`scaffold-api`, `lint-openapi`
architect	System design, scalable patterns, cloud infrastructure.	`design-system`, `review-architecture`
automation-engineer	n8n workflows, Zapier integration, scripting.	`deploy-n8n`, `check-webhook`
backend-engineer	API design, Database schema, Authentication.	`scaffold-api`, `optimize-query`
bmad-methodology	Scale-Adaptive Intelligence, project kickoff, complexity classification.	`classify-level`, `kickoff-project`
browser-agent	Web automation, scraping, UI testing with Playwright.	`scrape-site`, `automate-flow`
code-reviewer	Static analysis, logic verification, clean code standards.	`review-pr`, `analyze-complexity`
data-engineer	ETL pipelines, SQL optimization, Data warehousing.	`analyze-schema`, `run-migration`
devops-engineer	CI/CD, Docker, Kubernetes, Terraform.	`docker-build`, `k8s-deploy`
document-generator	Programmatic PDF/DOCX/XLSX generation.	`gen-pdf`, `gen-report`
frontend-engineer	React, Next.js, Tailwind, State Management.	`scaffold-component`, `check-accessibility`
git-workflow	Branch management, conventional commits, release flow.	`feature-start`, `release-prep`
mcp-builder	Build MCP servers, tools, and resources.	`new-mcp-server`, `test-tool`
mobile-engineer	React Native, Expo, iOS/Android build pipelines.	`build-ios`, `debug-android`
orchestrator	High-level task planning and agent coordination.	`plan-task`, `delegate-subtask`
performance-engineer	Profiling, load testing, optimization.	`run-lighthouse`, `profile-memory`
product-manager	PRD generation, user stories, roadmap planning.	`generate-user-story`, `prioritize-backlog`
prompt-engineer	Optimizing system prompts and LLM interactions.	`optimize-prompt`, `eval-prompt`
qa-engineer	E2E testing (Playwright), Unit tests, QA strategy.	`run-playwright`, `generate-test-plan`
scrum-master	Agile ceremonies, sprint planning, retrospective.	`start-sprint`, `generate-retro`
security-analyst	Vulnerability scanning, code auditing, OWASP.	`scan-vulnerabilities`, `audit-code`
seo-auditor	Technical SEO, Core Web Vitals, accessibility audit.	`audit-seo`, `check-meta`
spec-driven-dev	Spec-first development pipeline: SPECIFY → PLAN → TASKS → IMPLEMENT → VERIFY.	`create-spec`, `validate-spec`
supabase-expert	Supabase architecture, RLS, Edge Functions.	`init-supabase`, `deploy-edge`
swe-agent	Autonomous issue resolution, trajectory logging, Edit-Lint-Test loops.	`resolve-issue`, `trajectory-log`
systematic-debugger	Methodical 4-phase debugging (RCA).	`debug-session`, `analyze-logs`
tech-lead	Code review, technical decision making, mentoring.	`review-pr`, `enforce-standards`
technical-writer	Documentation, API refs, user guides.	`generate-docs`, `update-readme`
testing-strategist	Test planning, pyramid strategy, coverage goals.	`plan-testing`, `define-coverage`
ux-ui-designer	Design systems, user flow, prototyping.	`analyze-ux`, `generate-palette`

2. 📜 Rules (Context & Guardrails)

Constraints and guidelines that shape Agent behavior.
Location: {ide}/rules/ or ~/.agents/rules/

Rule File	Description
_bootstrap.md	⭐ Entry point: Startup check, skill activation, critical rules for ALL IDEs.
agents-ia.md	Core guidelines for building AI Agents (Tool-first, Stateless, Observable).
api-design.md	REST/GraphQL standards, error handling, versioning best practices.
automations-n8n.md	Best practices for building robust n8n workflows.
code-style.md	Linter configuration, naming conventions, project structure.
documentation.md	Standards for code comments, READMEs, and architectural decision records (ADRs).
security.md	Critical: Input validation, secret management, OWASP Top 10 prevention.
stack.md	Approved technology stack and library choices for the project.
testing.md	Mandatory Test-Driven Development (TDD) workflows and coverage requirements.
workflow.md	General git flow and contribution guidelines.

3. ⚡ Workflows (SOPs)

Step-by-step guides for complex tasks.
Location: {ide}/workflows/ or ~/.agents/workflows/

Workflow Name	Purpose
bugfix-backend.md	Protocol for diagnosing, fixing, and verifying server-side bugs.
documentation.md	Guide for updating and maintaining project documentation.
generate-prd.md	Template and instructions for creating Product Requirement Documents.
ideation.md	Brainstorming process for new features or products.
new-agent-ia.md	End-to-end guide for creating a new AI Agent from scratch.
new-automation.md	Steps to design and deploy a new automation (n8n/script).
new-feature.md	Standard flow: Ticket -> Design -> Implementation -> Test -> PR.
optimize-performance.md	Systematic approach to identifying and fixing bottlenecks.
resolve-github-issue.md	Standard flow for addressing GitHub Issues.
security-review.md	Checklist for pre-deployment security audits.
spec-driven.md	Development methodology based on detailed specifications (Spec-First).
testing-strategy.md	Defining the testing pyramid and strategy for a feature.
third-party-integration.md	Guide for securely integrating external APIs and SDKs.

💎 Features & IDE Support

🌍 Centralized "Brain" (`~/.agents`)

LMAgent creates a Single Source of Truth in your home directory.

Update Once, Reflect Everywhere: Modify a rule in ~/.agents/rules/code-style.md, and every project using Symlinks updates instantly.
Zero-Copy Efficiency: No more valid/duplicate .md files cluttering every repo.

🧩 Multi-IDE Support

🤝 Contributing

We welcome contributions to expand the Universal Agent Brain. Check out CONTRIBUTING.md to add new Skills, Rules, or IDE support.

🛠️ Creating New Skills

Need a custom agent? Use the interactive generator:

# Verify structure of existing skills
npx @qubiit/lmagent validate

# Create a new skill interactively
npx @qubiit/lmagent create-skill

This will generate the standard directory structure and SKILL.md template for you.

Built with ❤️ by QuBit

@qubiit/lmagent