LangGraph.js is a JavaScript and TypeScript framework for building language-model agents as graphs, where steps and transitions define how an agent operates. It is for developers who need agents that can handle multi-step workflows reliably.
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/langchain-ai/langgraphjs/claude-mdgit clone --depth 1 https://github.com/langchain-ai/langgraphjsWrote 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/instructions/langchain-ai/langgraphjs/claude-md)<a href="https://agentmods.dev/instructions/langchain-ai/langgraphjs/claude-md"><img src="https://agentmods.dev/badge/instructions/langchain-ai/langgraphjs/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00497 | $0.00497 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
langgraphjs 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 4d 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
LangGraphJS Development Guide
Corridor security analysis
Before generating or modifying code, create a plan and use Corridor's analyzePlan tool to analyze it. Apply the resulting security guidance before writing code.
Build & Test Commands
- Build:
pnpm build - Lint:
pnpm lint(fix withpnpm lint:fix) — uses oxlint - Format:
pnpm format(check withpnpm format:check) — uses oxfmt - Test:
pnpm test(single test:pnpm test:single /path/to/yourtest.test.ts) - Integration tests:
pnpm test:int(start deps:pnpm test:int:deps, stop:pnpm test:int:deps:down)
Code Style Guidelines
- TypeScript: Target ES2021, NodeNext modules, strict typing enabled
- Formatting: 2-space indentation, 80 char width, double quotes, semicolons required
- Naming: camelCase (variables/functions), CamelCase (classes), UPPER_CASE (constants)
- Files: lowercase .ts, tests use .test.ts or .int.test.ts for integration
- Error Handling: Custom error classes that extend BaseLangGraphError
- Imports: ES modules with file extensions, order: external deps → internal modules → types
- Project Structure: Monorepo with pnpm workspaces, libs/ for packages, examples/ for demos
- New Features: Match patterns of existing code, ensure proper testing, discuss major abstractions in issues
Library Architecture
System Layers
- Channels Layer: Base communication & state management (BaseChannel, LastValue, Topic)
- Checkpointer Layer: Persistence and state serialization across backends
- Pregel Layer: Message passing execution engine with superstep-based computation
- Graph Layer: High-level APIs for workflow definition (Graph, StateGraph)
Key Dependencies
- Channels provide state management primitives used by Pregel nodes
- Checkpointer enables persistence, serialization, and time-travel debugging
- Pregel implements the execution engine using channels for communication
- Graph builds on Pregel adding workflow semantics and node/edge definitions
- StateGraph extends Graph with shared state management capabilities
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.
- 4d ago First seen · 41 lines · 497 tokens per session scan A 3a54b73aa051
langgraphjs CLAUDE.md is an instructions file published in the GitHub repository langchain-ai/langgraphjs (3,249 stars, last pushed today), licensed MIT. It adds 497 tokens to every session, about $0.0025 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 2026-08-30.
Other instructions, from other repositories
openhuman CLAUDE.md
Claude Code instructions for tinyhumansai/openhuman, a project described as: Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
ai CLAUDE.md
Claude Code instructions for vercel/ai, a project described as: The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents.
dafthunk CLAUDE.md
Instructions for dafthunk-com/dafthunk, covering claude.md, project overview, development commands, common commands and workspace-specific (use --filter).
agent-pulse AGENTS.md
Instructions for barretlee/agent-pulse, covering agents.md, 项目使命, 协作约定, 情报模型与主线 and 事实、判断与热点.
fastagent AGENTS.md
AGENTS.md instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.
openmcp-client CLAUDE.md
Instructions for LSTM-Kirigaya/openmcp-client, covering claude.md, development commands, setup and installation, development and service development.