lg:create

lg:create is a command for Claude Code from TheLobbi/claude. It costs 22 tokens per session (2,719 once invoked), scanned A, original, MIT.

A project generator for LangGraph, a Python framework for building workflows and AI agents as graphs. It creates the files and setup for agents, workflows, or multi-agent systems.

In plain words
What is it for?
Use it to start a new project, choose a graph pattern, add memory or checkpoints, configure an LLM provider, and optionally expose the project through a command-line interface, MCP, or FastAPI.
Why use it?
It avoids starting a LangGraph project from an empty folder and prepares configuration, dependencies, tests, documentation, and optional interfaces in one process.

Command for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: mentions Claude Code.

Part of the langgraph-architect plugin — 5 commands, 12 agents, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/thelobbi/claude/create
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install langgraph-architect, the plugin that ships this one along with the rest of its 5 commands, 12 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lg:create

README.md
[![agentmods](https://agentmods.dev/badge/commands/thelobbi/claude/create.svg)](https://agentmods.dev/commands/thelobbi/claude/create)
Your own site
<a href="https://agentmods.dev/commands/thelobbi/claude/create"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/create.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.02719
Opus 5 $0.00011 $0.01359
Sonnet 5 $0.00004 $0.00544
Haiku 4.5 $0.00002 $0.00272

Measured today against content hash ceb18c0ae39d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lg:create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/plugins/langgraph-architect/commands/create.md · 446 lines

How it starts

The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lg:create - LangGraph Project Creator

Create production-ready LangGraph projects with best practices built-in.

Workflow Steps

  1. Validate Input

    • Check project name validity
    • Verify output path exists
    • Validate flag combinations
  2. Generate Project Structure

    • Create directory structure based on type
    • Generate pyproject.toml with dependencies
    • Create .env.example file
    • Setup configuration files
  3. Generate Core Components

    • Create state schema
    • Generate graph definition
    • Implement chosen pattern
    • Add memory/checkpoint system
  4. Add Integrations

    • Setup LLM provider configuration
    • Add tool definitions
    • Configure streaming (if enabled)
    • Setup LangSmith tracing (if enabled)
  5. Generate Wrappers

    • Create CLI wrapper (if --cli)
    • Create MCP server wrapper (if --mcp)
    • Add FastAPI server (optional)
  6. Create Tests

    • Generate test files
    • Add example test cases
    • Create test fixtures
  7. Generate Documentation

    • Create README.md
    • Add architecture diagram
    • Document API/CLI usage
    • Add deployment guide
  8. Setup Development Environment

    • Create virtual environment
    • Install dependencies
    • Run initial tests
    • Verify graph structure

Architecture Patterns

ReAct Pattern

# Reasoning and Acting loop
graph = StateGraph(AgentState)
graph.add_node("agent", agent_node)
graph.add_node("tools", tool_node)
graph.add_edge(START, "agent")
graph.add_conditional_edges("agent", should_continue)
graph.add_edge("tools", "agent")

Supervisor Pattern

# Supervisor delegates to workers
graph = StateGraph(State)
graph.add_node("supervisor", supervisor_node)
graph.add_node("worker_1", worker_1_node)
graph.add_node("worker_2", worker_2_node)
graph.add_conditional_edges("supervisor", route_to_worker)

Swarm Pattern

# Autonomous agents collaborate
graph = StateGraph(SwarmState)
for agent in agents:
    graph.add_node(agent.name, agent.node)
    graph.add_edge(agent.name, "coordinator")
graph.add_conditional_edges("coordinator", route_next)

Read the full file on GitHub · 446 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 446 lines · 22 tokens per session scan A ceb18c0ae39d

Subscribe to this mod's changes

lg:create is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,719 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other commands, from other repositories

design-context-extract

Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…

yonatangross/orchestkit · 84 tokens

design-import

Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…

yonatangross/orchestkit · 74 tokens

dev

One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…

yonatangross/orchestkit · 76 tokens

design-ship

One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…

yonatangross/orchestkit · 84 tokens

Hexagonal.Gatekeeper

Your role is to perform a deep, architecture-focused code review on a specific branch. You must validate that all changes strictly follow Hexagonal Architecture (Ports & Adapters) principles and align with the existing codebase patterns.

redhat-community-ai-tools/UnifAI · 0 tokens

gen-release-notes

Generate professional release notes following the Keep a Changelog standard.

existential-birds/amelia · 9 tokens