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.
/plugin marketplace add TheLobbi/claudenpx agentmods add plugins/thelobbi/claude/langgraph-architectgit clone --depth 1 https://github.com/TheLobbi/claudeWrote 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.
[](https://agentmods.dev/plugins/thelobbi/claude/langgraph-architect)<a href="https://agentmods.dev/plugins/thelobbi/claude/langgraph-architect"><img src="https://agentmods.dev/badge/plugins/thelobbi/claude/langgraph-architect.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
langgraph-architect 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.
What it actually says
{
"name": "langgraph-architect",
"version": "1.1.0",
"description": "Expert LangGraph/LangChain agent builder with MCP integration, workflow orchestration, and CLI accessibility. Creates production-ready AI agents that are reachable via command line and Claude Code.",
"author": {
"name": "Brookside BI"
},
"license": "MIT",
"homepage": "https://github.com/Lobbi-Docs/claude",
"repository": "https://github.com/Lobbi-Docs/claude.git",
"keywords": [
"langgraph",
"langchain",
"agent-builder",
"workflow-orchestration",
"state-machine",
"multi-agent",
"mcp",
"model-context-protocol",
"ai-agents",
"graph-builder",
"checkpointing",
"memory-management",
"tool-integration",
"subgraph",
"supervisor-pattern",
"cli-agents"
],
"commands": {
"agent": "commands/agent.md",
"create": "commands/create.md",
"deploy": "commands/deploy.md",
"edge": "commands/edge.md",
"mcp": "commands/mcp.md",
"memory": "commands/memory.md",
"node": "commands/node.md",
"test": "commands/test.md"
},
"agents": {
"cli-wrapper-specialist": "agents/cli-wrapper-specialist.md",
"context-engineer": "agents/context-engineer.md",
"deployment-specialist": "agents/deployment-specialist.md",
"edge-designer": "agents/edge-designer.md",
"graph-architect": "agents/graph-architect.md",
"mcp-bridge-specialist": "agents/mcp-bridge-specialist.md",
"memory-architect": "agents/memory-architect.md",
"node-specialist": "agents/node-specialist.md",
"orchestration-master": "agents/orchestration-master.md",
"state-engineer": "agents/state-engineer.md",
"subgraph-composer": "agents/subgraph-composer.md",
"tool-integrator": "agents/tool-integrator.md"
},
"categories": [
"orchestration",
"agents",
"ai-ml"
],
"provides": {
"commands": 8,
"agents": 12,
"skills": 0
}
}
What it installs
The manifest is a name and a version. 5 commands, 12 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 378 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command lg:edge A 21 tokens
- Command lg:mcp A 23 tokens
- Command lg:node A 34 tokens
- Command lg:agent A 23 tokens
- Command lg:create A 22 tokens
- Agent graph-architect A 18 tokens
- Agent CLI Wrapper Specialist A 21 tokens
- Agent Context Engineer A 19 tokens
- Agent memory-architect A 20 tokens
- Agent orchestration-master A 25 tokens
- Agent Subgraph Composer A 21 tokens
- Agent mcp-bridge-specialist A 21 tokens
- Agent state-engineer A 19 tokens
- Agent tool-integrator A 24 tokens
- Agent edge-designer A 23 tokens
- Agent node-specialist A 24 tokens
- Agent Deployment Specialist C 20 tokens
- MCP server langgraph-agents A not measured
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.
- today First seen · 64 lines scan A eb222ba6c66f
langgraph-architect is a plugin published in the GitHub repository TheLobbi/claude (21 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
elastic-observability
Elastic Observability skills - OpenTelemetry instrumentation and migration (.NET, Java, Python), LLM observability, log search, SLOs, and service health.
defang
Deploy Docker Compose apps to your own cloud account using Defang. Includes a /defang:deploy skill and Defang MCP server integration.
tailscale
Tailscale CLI reference and safe patterns for exposing local services over a tailnet.
cybrix-deploy
Deploy the current static site to a live HTTPS URL via Cybrix. Detects Next.js export, Astro, Vite, Hugo, Eleventy, and plain HTML. Returns a live URL on .cbrx.cc in under 60 seconds.
spacelift
Procedural guide and references for working with Spacelift via the spacelift-local MCP - manage stacks, runs, policies, spaces, integrations, and the lifecycle of cloud resources through Intent (OpenTofu/Terraform).
axcient
Every x360Recover endpoint, plus the fleet-wide backup-health answers the API alone can't give — offline, joined, and agent-ready.