langchain-community-plugin CLAUDE.md

Repository guidance for a Claude Code add-on that helps build LangChain and LangGraph applications. LangChain and LangGraph are developer tools for building applications that use large language models, such as chatbots and automated agents.

In plain words
What is it for?
It helps create agents, retrieval-augmented generation (RAG) pipelines that search stored information, and processing chains for tasks such as summarising or extracting data.
Why use it?
It gives the coding agent project structure, development rules, and review guidance in one place, reducing setup and consistency work.

Instructions file

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 instructions/codeblockz/langchain-community-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/Codeblockz/langchain-community-plugin
Per session 697 This file is loaded in full into every session.
When invoked 697 The same file — it is already loaded in full.
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 $0.00697 $0.00697
Opus 5 $0.00349 $0.00349
Sonnet 5 $0.00139 $0.00139
Haiku 4.5 $0.00070 $0.00070

Measured 2d ago against content hash e043a6f9a548, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

langchain-community-plugin CLAUDE.md 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 2d 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.

CLAUDE.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This is a Claude Code plugin for LangChain and LangGraph development. It provides skills, commands, and reviewer agents to help build AI applications with best practices.

Plugin Structure

langchain-community-plugin/
├── .claude-plugin/
│   ├── plugin.json               # Plugin manifest (name, version, keywords)
│   └── .mcp.json                 # MCP server configuration (LangChain docs)
├── skills/                       # Core guidance loaded contextually
│   ├── langgraph/               # AI agents with StateGraph and create_agent
│   ├── langchain-rag/           # RAG pipelines with vector stores
│   └── langchain-chains/        # LCEL chains for summarization/extraction
├── commands/                     # Slash commands for scaffolding
│   ├── new-agent.md             # /langchain-community:new-agent
│   ├── add-tool.md              # /langchain-community:add-tool
│   ├── new-rag.md               # /langchain-community:new-rag
│   └── new-chain.md             # /langchain-community:new-chain
└── agents/                       # Reviewer subagents (haiku model)
    ├── langgraph-reviewer.md    # Reviews agent code for common mistakes
    └── rag-reviewer.md          # Reviews RAG code for common mistakes

Architecture

Skills (skills/<name>/SKILL.md): Main guidance documents with YAML frontmatter containing name and description. Each skill has a references/ subdirectory with detailed documentation for specific patterns (e.g., state-patterns.md, vector-stores.md).

Commands (commands/<name>.md): Slash commands that scaffold new code. Use YAML frontmatter for command metadata.

Agents (agents/<name>.md): Reviewer agents that analyze code for issues. Configured with YAML frontmatter specifying name, description, model (haiku), color, and available tools.

MCP Servers (.claude-plugin/.mcp.json): Configures external MCP servers. The plugin includes the official LangChain docs MCP server (https://docs.langchain.com/mcp) for accessing up-to-date documentation directly.

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 697 tokens per session scan A e043a6f9a548

Subscribe to this mod's changes

langchain-community-plugin CLAUDE.md is an instructions file published in the GitHub repository Codeblockz/langchain-community-plugin (3 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 697 tokens to every session, about $0.0035 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 2026-08-31.