Deep Agents TypeScript quickstart

Follow the live docs — do not invent an alternate API from memory:

https://docs.langchain.com/oss/javascript/deepagents/quickstart

Fetch that page (Docs MCP or HTTP) and implement the research-agent shape it shows (createDeepAgent, research system prompt, invoke with a research question like “What is LangGraph?”). Requires Node 22+.

Local setup constraints

Apply these on top of the quickstart (they keep setup minimal and model-agnostic):

Ask which provider/model to use. Showcase that Deep Agents are model-agnostic. Suggested prompt:

Which model should this agent use? Pass a provider:model string — e.g. openai:gpt-5.5, anthropic:claude-sonnet-5, google-genai:gemini-3.5-flash. Default if you're unsure: anthropic:claude-sonnet-5.
We'll use that provider's built-in web search (no separate search API key).
Create a new directory (e.g. deep-agent/) and do all work there — do not pollute the open project.
Do not use Tavily (or @langchain/tavily). Replace the quickstart's search tool with the chosen provider's built-in web search. Look up the current export/tool shape on that provider's LangChain docs (examples as of writing — re-check if needed):

Provider Built-in search tool

Anthropic @langchain/anthropic tools.webSearch_*() (or equivalent dict)

OpenAI { type: "web_search" }

Google { google_search: {} }

Prefer Anthropic / OpenAI / Google so provider search is available. Only secret: that provider's API key in .env (gitignored). Skip LangSmith tracing unless they ask.
Install packages from the quickstart minus Tavily; add the provider package for their model.
Run the research example, show output, then stop. Point to deep-agents-core / customization / Managed Deep Agents for next steps.

Provider	Built-in search tool
Anthropic	`@langchain/anthropic` `tools.webSearch_*()` (or equivalent dict)
OpenAI	`{ type: "web_search" }`
Google	`{ google_search: {} }`

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

78

Quality

68

Clarity

78

Completeness

62

Summary

This skill scaffolds a minimal local Deep Agent in TypeScript by following LangChain's official quickstart docs. It guides users to create a new project directory, select a language model provider (OpenAI, Anthropic, or Google), replace the Tavily search integration with the provider's built-in web search, and run a research agent example locally.

Static Analysis Findings

1 finding

Patterns detected by deterministic static analysis before AI scoring. Hover over any finding code for detailed information and remediation guidance.

Credential Exposure

SEC-020Direct .env File Access

Direct .env file access

SKILL.md.env

85% confidenceCWE-538: Sensitive Info in Externally-Accessible File

Detected Capabilities

fetch remote documentationcreate local project directoryinstall npm packagesread environment variablesinvoke language model APIs via provider SDKexecute TypeScript/Node.js codeweb search via provider APIs

Trigger Keywords

Phrases that agents use to match this skill to user intent.

deep agents quickstartlangchain typescript scaffoldlocal research agentdeep agent setupprovider web search

Risk Signals

WARNING

SEC-020: Direct .env file access — mentions creating .env file to store provider API keys

SKILL.md line 34

Referenced Domains

External domains referenced in skill content, detected by static analysis.

docs.langchain.com

Use Cases

Quick local Deep Agent prototyping without external dependencies
Evaluate Deep Agents with different model providers
Learn Deep Agents API and structure through hands-on scaffolding
Set up a minimal research agent for testing LangGraph concepts
Bootstrap a project for custom Deep Agent extensions

Quality Notes

Positive: Clear scope boundary — skill is limited to a new local directory, does not pollute existing projects
Positive: Explicit model-agnostic design with three well-documented provider options
Positive: References official LangChain documentation as authoritative source, reducing outdated instruction risk
Positive: Clear constraint list that makes prerequisites and dependencies explicit
Negative: No error handling guidance — what if user lacks Node 22+, or provider API fails?
Negative: Does not document how to manage or rotate API keys after setup
Negative: Assumes user knows how to create/format .env files and add gitignore rules — could benefit from examples
Negative: No validation steps — skill does not guide verification that the agent runs correctly
Negative: Missing troubleshooting section — unclear what to do if provider search tool shape differs from docs or if installation fails

Model: claude-haiku-4-5-20251001Analyzed: Oct 12, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

deepagents-typescript-quickstart