skills-benchmarks is a test suite that measures how the design of skill documentation affects Claude Code's adherence to recommended coding patterns. It is used to compare documentation approaches across LangChain-related tasks and other agent workflows. Its catalogue entries represent skills, hooks, instructions, and a plugin used in the benchmark project.
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/skills-benchmarks --skill langchain-dependenciesgit clone --depth 1 https://github.com/langchain-ai/skills-benchmarksWrote 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/skills-benchmarks/langchain-dependencies)<a href="https://agentmods.dev/skills/langchain-ai/skills-benchmarks/langchain-dependencies"><img src="https://agentmods.dev/badge/skills/langchain-ai/skills-benchmarks/langchain-dependencies/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/skills-benchmarks/langchain-dependencies"><img src="https://agentmods.dev/badge/skills/langchain-ai/skills-benchmarks/langchain-dependencies.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 | $0.00068 | $0.03652 |
| Opus 5 | $0.00034 | $0.01826 |
| Sonnet 5 | $0.00014 | $0.00730 |
| Haiku 4.5 | $0.00007 | $0.00365 |
Grade A, and why
langchain-dependencies 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 11d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- langchain-dependencies — 95% identical, 18 lines differ
- langchain-dependencies — 95% identical, 18 lines differ
How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Key principles:
- LangChain 1.0 is the current LTS release. Always start new projects on 1.0+. LangChain 0.3 is legacy maintenance-only — do not use it for new work.
- langchain-core is the shared foundation: always install it explicitly alongside any other package.
- langchain-community (Python only) does NOT follow semantic versioning; pin it conservatively.
- LangGraph vs Deep Agents: choose one orchestration approach based on your use case — they are alternatives, not a required stack (see Framework Choice below).
- Provider integrations (model, vector store, tools) are installed separately so you only pull in what you use.
Environment Requirements
| Requirement | Python | TypeScript / Node |
|---|---|---|
| Runtime minimum | Python 3.10+ | Node.js 20+ |
| LangChain | 1.0+ (LTS) | 1.0+ (LTS) |
| LangSmith SDK | >= 0.3.0 | >= 0.3.0 |
Core Packages
Python — always required
| Package | Role | Min version |
|---|---|---|
langchain |
Agents, chains, retrieval | 1.0 |
langchain-core |
Base types & interfaces (peer dep) | 1.0 |
langsmith |
Tracing, evaluation, datasets | 0.3.0 |
Python — orchestration (pick one)
| Package | Use when | Min version |
|---|---|---|
langgraph |
Building custom graphs directly | 1.0 |
deepagents |
Using the Deep Agents framework | latest |
Python — model providers (pick the one(s) you use)
| Package | Provider |
|---|---|
langchain-openai |
OpenAI (GPT-4o, o3, …) |
langchain-anthropic |
Anthropic (Claude) |
langchain-google-genai |
Google (Gemini) |
langchain-mistralai |
Mistral |
langchain-groq |
Groq (fast inference) |
langchain-cohere |
Cohere |
langchain-fireworks |
Fireworks AI |
langchain-together |
Together AI |
langchain-huggingface |
Hugging Face Hub |
langchain-ollama |
Ollama (local models) |
langchain-aws |
AWS Bedrock |
langchain-azure-ai |
Azure AI Foundry |
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.
- 11d ago First seen · 406 lines · 68 tokens per session scan A f121127617fb
langchain-dependencies is a skill published in the GitHub repository langchain-ai/skills-benchmarks (116 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 3,652 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 2026-08-30.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…