On This Page8 sections
Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.
An agent that works with project files and commands through terminal, IDE, desktop and web surfaces.
Coding agent · Anthropic · macOS · Windows · Linux · Web
Suitable workflows
Developers who want an agent alongside their preferred editor.
Limitations and billing
Choose between subscription and provider billing deliberately; the editor is a separate choice.
Capabilities we verified
Agent workflow · CLI surface · MCP · Skills · Hooks
This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.
Pricing & usage
See official pricing
Claude subscription or provider usage billing. The cost of metered usage or an external agent can be separate from the subscription.
Models & access
Anthropic subscription, Console or supported third-party provider.
Verified families: Claude.
Install and start the CLI
Use the native installer for your operating system; Windows has separate PowerShell instructions.
curl -fsSL https://claude.ai/install.sh | bashOpen your project folder in a terminal, then run:
claudeAccount and authentication
Start claude and follow the account login flow, or configure a supported provider.
Project configuration and tools
CLAUDE.md supplies project context. Skills, hooks and MCP add reusable procedures and external tools.
First task to try
Explain a failing test, propose a focused correction, and review the resulting diff.
Script usage
This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.
claude -p "Summarize the project structure without modifying files."Related CLI tools
Codex — OpenAI’s coding agent for local projects and cloud tasks.
Kimi Code CLI — Kimi’s terminal agent for code, shell tasks, skills and parallel subagents.
Amp — A coding agent spanning terminal sessions, hosted environments and shared threads.
Project evaluation checklist
- Open a small, familiar project and confirm that your essential language tooling works.
- Give the agent one bounded change with an observable acceptance criterion.
- Review the diff, run the project’s checks and compare the result with your current workflow.
- Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.
Related TRAE guides
Continue Reading
More articles connected to the same themes, protocols, and tools.
Referenced Tools
Browse entries that are adjacent to the topics covered in this article.





