Glossary
What is Claude Code?
Claude Code is Anthropic's agentic coding tool. It runs in the terminal, IDEs, a desktop app and on the web, reads and edits code, runs commands, and can use tools and connected services to complete tasks. Developers also use it for non-coding work like research, data tasks and browser automation.
What it does
- Understands a codebase by reading and searching files.
- Makes multi-file changes, runs tests and fixes failures.
- Runs shell commands with permission.
- Connects to tools and services through MCP and plugins.
- Follows instructions in project files such as CLAUDE.md and skills.
Beyond coding
With browser tools, Claude Code can navigate sites, read pages and fill forms. That makes it useful for repetitive web work around a product: checking listings, submitting to directories, testing sign-up flows. Permission prompts and stopping points keep the user in control of accounts and payments.
For launches
AgentLaunch is designed to be opened in Claude Code (or Codex or Cursor): the repository holds the directory catalog, the recorded submit path for each directory and a launch tracker, and the agent works through them in your own browser.
Example
A founder types "launch my product to the directories that fit" in Claude Code inside the launch kit. It reads the playbook, matches directories to her product, writes copy per directory and submits, pausing when a site needs a CAPTCHA or payment.
FAQ
Is Claude Code free?
It's included with some Claude plans and available with API usage; check Anthropic's current pricing.
Does Claude Code only work in the terminal?
No. It also runs in IDEs, a desktop app and on the web.
Can Claude Code use a browser?
Yes, with browser tools or integrations enabled.