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 skills add kaushik-holla/agent-skills --skill langgraph-patternsgit clone --depth 1 https://github.com/kaushik-holla/agent-skillsWrote 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/skills/kaushik-holla/agent-skills/langgraph-patterns)<a href="https://agentmods.dev/skills/kaushik-holla/agent-skills/langgraph-patterns"><img src="https://agentmods.dev/badge/skills/kaushik-holla/agent-skills/langgraph-patterns/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/skills/kaushik-holla/agent-skills/langgraph-patterns"><img src="https://agentmods.dev/badge/skills/kaushik-holla/agent-skills/langgraph-patterns.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.05345 |
| Opus 5 | $0.00034 | $0.02672 |
| Sonnet 5 | $0.00014 | $0.01069 |
| Haiku 4.5 | $0.00007 | $0.00534 |
Grade A, and why
langgraph-patterns 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 8d 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 — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LangGraph Patterns
Canonical, copy-paste recipes for LangGraph >= 1.0 (verified against 1.0.x and 1.1.x). Every snippet here is a minimal working pattern you can extend; do not paste them into production verbatim without adapting names and types to the project.
The snippets use a recurring example graph (a research assistant with clarity → research → validator → synthesis nodes) purely to make the patterns concrete. Swap in your own domain.
myappis a placeholder for your package name.
When To Use
- Designing a new graph (consult sections 1-7 first).
- Implementing a node, router, or interrupt (sections 4-8, 11).
- Wiring tools, MCP servers, or providers (sections 12-13).
- Adding subgraphs, fan-out parallelism, async streaming, or tracing (sections 14-17).
- Debugging a graph that "feels off" (section 18: common mistakes catalog with fixes).
- Writing tests against a graph (section 19).
0. Install and Imports
Pin minimum versions in pyproject.toml:
[project]
dependencies = [
"langgraph>=1.0,<2",
"langchain-core>=0.3",
"langchain-openai>=0.2",
"pydantic>=2.7",
]
[project.optional-dependencies]
sqlite = ["langgraph-checkpoint-sqlite>=2.0"] # only if you persist via SqliteSaver
Imports cheat-sheet (all from the public API):
from typing import Annotated, Literal, TypedDict, Any
from pydantic import BaseModel, Field
from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
from langchain_openai import ChatOpenAI
from langgraph.graph import StateGraph, START, END
from langgraph.graph.message import add_messages
from langgraph.types import Command, interrupt
from langgraph.checkpoint.memory import MemorySaver
from langgraph.checkpoint.sqlite import SqliteSaver # optional
If an import path is not in the list above, double-check it; internal modules move between minor versions.
1. Typed State with add_messages Reducer
The standard State shape. The Annotated[..., add_messages] reducer is what enables append-style conversation history; without it, every node's return value overwrites prior messages.
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.
- 8d ago First seen · 622 lines · 68 tokens per session scan A c8d1285a5994
langgraph-patterns is a skill published in the GitHub repository kaushik-holla/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 5,345 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…