Claude Code
Anthropic's official terminal agent for Claude. Ships as a CLI installable from npm, with first-class support for MCP servers, custom hooks, slash commands, subagent orchestration, and a project-level CLAUDE.md memory file. The harness benefits from being co-designed with Claude's agentic post-training, which is the main reason it tops most agentic-coding leaderboards when paired with Opus 4.7 or Sonnet 4.6.
Leaderboard Placements
| Benchmark | Best base model | Score | Rank |
|---|---|---|---|
| SWE-bench Verified | Claude Opus 4.7 | 74.5 | #1 / 15 |
| Terminal-Bench | Claude Opus 4.7 | 52.3 | #1 / 13 |
| Aider Polyglot | Claude Opus 4.7 | 84.2 | #1 / 7 |
| SWE-Lancer | Claude Opus 4.7 | 41.8 | #1 / 5 |
Distribution
CLI installable via npm. Also available as a VS Code and JetBrains extension, plus a desktop app.
Model Story
Anthropic models only. Routes Opus 4.7 by default, with Sonnet 4.6 and Haiku 4.5 selectable. No bring-your-own-key for non-Anthropic models.
Pricing
Subscription tied to Anthropic API credits or a flat-rate Pro/Max plan. No per-tool fees.
Who It's For
Engineers running long, autonomous coding sessions in a terminal where MCP integrations and project-aware memory pay off.
Notable Features
- Native MCP server orchestration (single config, hot reload)
- CLAUDE.md per-project and ~/.claude/CLAUDE.md global memory
- Hooks: pre-tool, post-tool, on-stop
- Subagent delegation with isolated worktrees
- Plan mode with approval gating