Claude Code
Anthropic Terminal agentsAnthropic’s terminal coding agent. Included with Claude Pro/Max subscriptions; shares one usage pool with claude.ai.
Capabilities
| Read local project | Supported Runs in your project directory. |
|---|---|
| Edit files | Supported Edits files directly. |
| Run commands | Supported Runs shell commands and builds/tests. |
| Image input | Supported Paste screenshots into the session. |
| Long autonomous tasks | Conditional Multi-step agent work, but limited by plan usage caps — long tasks need a healthy quota. |
Working experience
Editorial assessment based on official documentation and publicly known behavior — not a field-test score. Sources and check date on this page.
🧪 ResetDog field notes
No completed field test for this tool yet. The capability descriptions on this page come from official documentation.
🎯 Good for
Change pages / UI · Fix a bug · · Let an agent run · Continue from a screenshot · Hand off my project
🧭 How you use it
In the terminal · Inside your IDE
Works on: macOS / Windows / Linux
💰 Cost & quota
Subscription · Included with subscription
🆓 Free / trial access
No free tier for Claude Code itself; it is included with paid Claude plans (Pro and up).
🏷️ Pricing notes
Pro $20/mo (or $17/mo billed annually) includes Claude Code; Max $100/mo (5x Pro usage) and $200/mo (20x). Usage resets on a rolling 5-hour window with additional weekly caps; one shared pool across claude.ai and Claude Code. API pay-as-you-go via Anthropic Console is an alternative.
🚀 Setup
Node.js 18+, then `npm install -g @anthropic-ai/claude-code`, run `claude` in your project, sign in with a Claude account or API key.
⚠️ Main limitations
- Subscription plans have session and weekly usage caps — very long agent runs can hit them.
- You need a paid Claude plan (or API billing) before you can start.
🔒 Privacy & data
Governed by Anthropic’s commercial terms and privacy policy; check data-use settings for your plan. Official privacy policy ↗
🧾 What is official vs ours
Facts like pricing, plans, and capability limits come from the official pages linked below, checked on the date shown. Summaries and task-fit notes are written by ResetDog. Anything marked “conditional” or “unknown” was not fully confirmed — treat it as unverified.