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.
npx agentmods add instructions/codeblockz/langchain-community-plugin/claude-mdgit clone --depth 1 https://github.com/Codeblockz/langchain-community-pluginWhat 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.
| Model | Per session | Once 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 |
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.
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.
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.
- 2d ago First seen · 55 lines · 697 tokens per session scan A e043a6f9a548
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.
Other instructions, from other repositories
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
flock AGENTS.md
Instructions for Onelevenvy/flock, covering agents.md, project overview, build & development commands, rust backend and build the cli.
dawnai AGENTS.md
Instructions for cacheplane/dawnai, covering agents.md, what this is (and isn't), workspace map, definition of done and conventions.
TradingAgents-Telegram CLAUDE.md
Instructions for IvanWng97/TradingAgents-Telegram, covering tradingagents-telegram — architecture reference, layout, architecture (for code reviewers), request lifecycle (manual /watch tap) and state ownership.
daiv AGENTS.md
Instructions for srtab/daiv, covering agents.md, commands (verified), single test / pattern, translations and repo map (only what's non-obvious).
fullstack-langgraph-nextjs-agent CLAUDE.md
Instructions for agentailor/fullstack-langgraph-nextjs-agent, covering claude.md, essential development commands, setup (requires postgres and minio running), development and database.