# Claude Code

Anthropic's agentic coding tool for the terminal, IDE, desktop app and browser

**Verdict: conditional.** Claude Code is the most architecturally complete agentic coding tool we track: dynamic workflows, maker-checker sub-agents, cloud routines and a separate verifier model all ship in one engine across terminal, IDE, desktop and web. The condition is cost. Anthropic's own docs put the average at about $13 per developer per active day, or $150-250 per month, and agent teams use roughly 7x the tokens in plan mode. Right for teams that meter and cap spend. Last verified 2026-09-30.

Claude Code is Anthropic's agentic coding tool, led by Boris Cherny. Its official docs describe one engine that reads a codebase, edits files, runs commands and integrates with development tools, available in the terminal, IDE extensions for VS Code and JetBrains, a desktop app, and the web. Announced on February 24, 2025 as a limited research preview and continuously updated since, it is the execution environment for Anthropic's vision of "loop engineering" — autonomous multi-agent coding workflows that run on timers, schedule, or goal-conditioned execution. The tool supports sub-agents with a maker-checker split (separate models write and verify code), isolated git worktrees for parallel agents, persistent project memory via CLAUDE.md and Skills (SKILL.md), and MCP server connections to external tools (GitHub, Slack, Linear). Dynamic Workflows (May 28, 2026) enable orchestrating up to 1,000 agents with 16 concurrent, with JavaScript orchestration scripts that keep orchestration logic out of the model's context window. Cloud Routines (research preview) run scheduled automations on Anthropic's servers. The /goal command uses a separate evaluator model to check completion conditions after each agent turn. As of June 15, 2026, automated workloads bill against a separate monthly credit pool ($20 Pro, up to $200 Max) rather than the interactive subscription pool. Ecosystem includes Cursor and Windsurf routing, MCP servers, and a growing library of community Skills and sub-agent definitions.

## Strengths

- Teams running autonomous coding loops with maker-checker verification, scheduled agentic tasks, and multi-agent orchestration across large codebases.
- Developers on a tight token budget — Anthropic's docs put the average enterprise cost at about $13 per developer per active day ($150-250 per developer per month), and agent teams use roughly 7x the tokens of a standard session in plan mode.

## Pricing

- Model: freemium
- Pro: $20/mo, or $17/mo billed annually
- Max: From $100/mo
- Team (Standard seat): $25/seat/mo, or $20 billed annually
- Team (Premium seat): $125/seat/mo, or $100 billed annually
- Enterprise: $20/seat + usage at API rates

Website: https://claude.com/product/claude-code

## Sources

- [Anthropic Claude pricing page](https://claude.com/pricing)
- [Anthropic — Claude 3.7 Sonnet and Claude Code announcement (Feb 24, 2025)](https://www.anthropic.com/news/claude-3-7-sonnet)
- [Claude Code docs: manage costs effectively](https://code.claude.com/docs/en/costs)
- [Claude Code docs: overview](https://code.claude.com/docs/en/overview)
- [Loop Engineering crash course (Agent Factory)](https://agentfactory.panaversity.org/docs/loop-engineering-crash-course)
- [Tech Times — Claude Code Loop Engineering deep dive](https://www.techtimes.com/articles/318828/20260622/claude-code-loop-engineering-stop-prompting-start-designing-autonomous-agent-workflows.htm)
- [TechCrunch — The AI world is getting loopy](https://techcrunch.com/2026/06/22/the-ai-world-is-getting-loopy/)

Canonical: https://neomanex.com/directory/claude-code