@anthropic-ai/claude-agent-sdk

Name: @anthropic-ai/claude-agent-sdk Review
Item: @anthropic-ai/claude-agent-sdk
Rating: 3.2
Author: Aaron Matthews

Skill Productivity Usable

Works inClaude Code

Usable Scanned — metadata only

Enables teams to automate code analysis, refactoring, and CI/CD workflows without building custom Claude integrations.

SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.

Build an autonomous agent that reviews pull requests and suggests code improvements automatically.
Generate a workflow agent that reads your codebase and identifies deprecated dependencies to update.
Create an agent that analyzes test failures and attempts to fix broken unit tests in your repository.

1,650 starsSEE LICENSE IN README.mdFreeQuick setup

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Enables teams to automate code analysis, refactoring, and CI/CD workflows without building custom Claude integrations. Reduces time spent on repetitive development tasks while maintaining quality control through Claude's reasoning.

Best for

Engineering teams building internal automation tools and DevOps workflows that require codebase understanding and file manipulation.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk

By wolffiex

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

npx @anthropic-ai/claude-agent-sdk

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Help me build an autonomous agent that reviews pull requests and suggests code improvements automatically

CostFree

Trust Signals Auto-scanned

Stars1,650Last updated2026-07-22LicenseSEE LICENSE IN README.mdWeekly downloads8,266,835Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-07-23 · scanner v1

Community Pulse New

Claude Code Open Source? — Hacker News · 1 pts

1 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 1,650 GitHub stars; contributors unknown; last commit 1d ago; license SEE LICENSE IN README.md.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

2/5

Versatility

5/5

Reliability

3/5

Security

3/5

Overall score3.15 / 5.00 UsableEvaluatedJul 2026

Scored from trust signals (evidence-eval-v1): 1,650 GitHub stars; contributors unknown; last commit 1d ago; license SEE LICENSE IN README.md.

← Back to the Claude Observatory