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.
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWrote 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/postindustria-tech/agentic-toolkit/langgraph-dev)<a href="https://agentmods.dev/plugins/postindustria-tech/agentic-toolkit/langgraph-dev"><img src="https://agentmods.dev/badge/plugins/postindustria-tech/agentic-toolkit/langgraph-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/postindustria-tech/agentic-toolkit/langgraph-dev"><img src="https://agentmods.dev/badge/plugins/postindustria-tech/agentic-toolkit/langgraph-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
langgraph-dev 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 1mo ago.
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-dev",
"version": "0.1.0",
"description": "Comprehensive toolkit for building agentic systems using LangGraph and LangChain, with tutorial-grounded patterns and best practices",
"author": {
"name": "Postindustria Tech",
"email": "[email protected]"
},
"homepage": "https://github.com/postindustria-tech/agentic-toolkit",
"repository": "https://github.com/postindustria-tech/agentic-toolkit",
"keywords": [
"langgraph",
"langchain",
"agents",
"workflows",
"rag",
"agentic-systems",
"state-management",
"multi-agent",
"testing"
],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 21 skills, 5 commands, 1 agent travel with it, and installing the plugin installs all of them — 1,584 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill langgraph-checkpointing-and-persistence A 110 tokens
- Skill conditional-routing-in-langgraph A 67 tokens
- Skill deployment-patterns-for-langgraph A 90 tokens
- Skill error-recovery-in-langgraph A 61 tokens
- Skill langgraph-dev-basic-rag A 62 tokens
- Skill streaming-execution-in-langgraph A 79 tokens
- Skill Memory Store and Knowledge Management A 110 tokens
- Skill graph-construction-in-langgraph A 75 tokens
- Skill multi-agent-supervisor-pattern A 66 tokens
- Skill parallel-execution-in-langgraph A 67 tokens
- Skill prompt-engineering-for-langgraph A 67 tokens
- Skill state-management-in-langgraph A 69 tokens
- Skill subgraphs-and-composition-in-langgraph A 90 tokens
- Skill corrective-rag-crag A 58 tokens
- Skill langgraph-dev-human-in-the-loop A 97 tokens
- Skill langgraph-dev-testing-agentic-systems A 55 tokens
- Skill performance-optimization-for-langgraph A 52 tokens
- Skill react-agents-in-langgraph A 54 tokens
- Skill tool-calling-in-langgraph A 58 tokens
- Skill structured-output-with-pydantic A 59 tokens
- Skill document-processing-for-rag A 54 tokens
- Command create-deployment A 16 tokens
- Command create-tests A 16 tokens
- Command create-workflow A 19 tokens
- Command create-agent A 15 tokens
- Command create-state A 18 tokens
- Agent workflow-validator A 0 tokens
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.
- 1mo ago First seen · 24 lines scan A 6f06cd3be7c8
langgraph-dev is a plugin published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 11d ago), 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 2026-08-31.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.