Claude Profile picture
Aug 19 5 tweets 2 min read Read on X
How (and why) agents in Claude Code help you write better code, faster:

Agents allow you to deploy specialized experts for every task. It's like managing a team rather than collaborating 1-on-1. Image
To get started, launch Claude Code, run /agents and select "Create new agent."

Define it by describing what the agent should do and when it should be used. Be specific but not overly prescriptive.
The next step is to integrate your tools.

Agents can interact with external APIs, databases, or services via tools and MCP servers. Image
An agent can be almost anything:

- Security auditor
- Test analyzer
- Code optimizer
- Refactor engineer
- UI designer
- Code organizer Image
See everything you can do with agents: docs.anthropic.com/en/docs/claude…

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Claude

Claude Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @claudeai

Aug 14
Today we're launching new ways to learn in Claude Code and the Claude app.

First up: Claude Code now lets you customize communication styles with /output-style
We're introducing two output styles to help students and developers build skills:

- Explanatory: Claude explains its reasoning step-by-step
- Learning: You take turns coding with Claude
Use 'Explanatory' for Claude to go deeper on what it's doing and why—it shares the reasoning behind architectural decisions, explains tradeoffs, and teaches you best practices as it codes.
Read 5 tweets
Aug 6
We just shipped automated security reviews in Claude Code. Catch vulnerabilities before they ship with two new features:

- /security-review slash command for ad-hoc security reviews
- GitHub Actions integration for automatic reviews on every PR
The /security-review command runs security analysis directly from your terminal.

Claude checks for vulnerabilities like:
- SQL injection risks
- XSS vulnerabilities
- Insecure data handling

Found a vulnerability? Simply ask Claude to fix it.
Our new GitHub action is a friendly security reviewer for all your PRs.

When configured, the integration checks every new PR for vulnerabilities, posting inline comments with explanations and recommended fixes. Image
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(