LangGraph 101 is a collection of hands-on notebooks that teach the fundamentals and advanced patterns of building agents with LangChain, LangGraph, and Deep Agents. It is for developers learning to create agents with tools, memory, streaming, human oversight, multi-agent designs, and production workflows. The catalogue add-ons support workflows for the repository's agent-building topics.
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 langchain-ai/langgraph-101 --skill twitter-postgit clone --depth 1 https://github.com/langchain-ai/langgraph-101Wrote 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/langchain-ai/langgraph-101/twitter-post)<a href="https://agentmods.dev/skills/langchain-ai/langgraph-101/twitter-post"><img src="https://agentmods.dev/badge/skills/langchain-ai/langgraph-101/twitter-post/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/langchain-ai/langgraph-101/twitter-post"><img src="https://agentmods.dev/badge/skills/langchain-ai/langgraph-101/twitter-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00518 |
| Opus 5.5 | $0.00014 | $0.00207 |
| Sonnet 5.5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
twitter-post 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter/X Post Skill
Single Tweet Format
- Maximum 280 characters
- Lead with the most compelling point
- Use numbers or data when possible
- End with a link placeholder or call-to-action
- 1-2 hashtags max (optional)
Thread Format (for longer content)
- Tweet 1: Hook + preview of what's coming (e.g., "A thread on X:" or "Here's what I found:")
- Tweets 2-N: One idea per tweet, numbered (1/, 2/, 3/)
- Final tweet: Summary + call-to-action + link
- Keep each tweet self-contained (people share individual tweets)
- 4-8 tweets is the sweet spot for engagement
Tone
- Concise and punchy
- Opinionated takes perform better than neutral summaries
- Use plain language -- no corporate speak
- Contrarian or surprising angles get more engagement
Tips
- Front-load the value (no throat-clearing or preambles)
- Use line breaks within tweets for readability
- Avoid hashtags in threads (they look spammy) -- save them for single tweets
- Numbers and lists catch the eye in a feed
Example Single Tweet
AI agents that manage their context window well outperform those with 10x more tools.
The secret isn't more capabilities -- it's smarter context engineering.
Example Thread
Thread: What makes AI agents actually work in production? 🧵
1/ It's not the model size. It's context management.
The best agents treat their context window like RAM -- offloading to filesystem, summarizing aggressively, loading info on demand.
2/ Subagents are the key to scaling.
Instead of one agent doing everything, delegate to specialists. The main agent only sees the summary, not 50 intermediate tool calls.
3/ Skills > giant system prompts.
Progressive disclosure: load detailed instructions only when the task needs them. Your agent's prompt stays clean until it matters.
4/ Memory needs structure.
Semantic (facts), episodic (experiences), procedural (rules) -- route them to different backends so they persist appropriately.
5/ The takeaway: the best agent architectures are about information flow, not raw capability.
What patterns are you using? Reply with your favorite agent architecture trick.
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 · 71 lines · 36 tokens per session scan A 97ba81db6c54
twitter-post is a skill published in the GitHub repository langchain-ai/langgraph-101 (695 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 518 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.