Deterministic shell hooks in Claude Code. Run commands on edit, stop, and permission events, plus optional prompt-based and HTTP hooks.

Versioned Claude Code bundles of skills, agents, hooks, and MCP. Install from the official marketplace with /plugin or enabledPlugins.

Claude Code skills are SKILL.md packages that extend the agent on demand. Custom slash commands merged into skills; follows the Agent Skills standard.

Specialized Claude Code workers with their own context, tools, and permissions. Use them so research and logs do not flood the main session.

Anthropic's Mythos-class flagship made safe for general use, with 1M-token context, frontier coding and vision, days-long agentic autonomy, and $10/$50 per 1.

Anthropic's previous Opus snapshot: 200k context, $5/$25 per 1M tokens. Later billed lines include Opus 4.6 and Opus 5.

Anthropic's previous Sonnet snapshot: 200k context, $3/$15 per 1M tokens. Docs now sell newer Claude 4.6 and Claude 5 lines.

Claude Haiku 4.5: a previous low-cost Claude row at $1/$5 per 1M tokens and 200k context.

Anthropic's frontier Opus model with 1M-token context and effort-controlled reasoning, near-Fable-5 intelligence at Opus-4.8 pricing for agents and coding.

Claude Sonnet 5: live mid-tier Claude row at $2/$10 per 1M tokens and 1M context. Not leftover Sonnet 4.5.

Anthropic agent library. Python 7,910 stars, MIT.

OpenAI-compatible AI API gateway: one base URL and key for 60+ models from GPT, Claude, Gemini, DeepSeek, Sora, and VEO, with routing, failover, and unified.

Previous Claude 3.5 Sonnet snapshot. Not the 2026 default.

Previous Claude 3 Haiku snapshot. Not the 2026 fast default.

Previous Claude 3 Opus snapshot. Not the 2026 flagship.

Previous Claude 3 Sonnet snapshot. Not the 2026 default.

Previous Claude v1 snapshot. Not a 2026 text default.

Anthropic's official learning platform. 300+ free courses and tutorials across Claude.ai, Cowork, Claude Code, Tag, and the Platform API, plus an AI Fluency.

TypeScript kit for MCP servers. Software $0. Not a 5-minute Claude Desktop-only tutorial.

Your AI coding companion that lives on your desktop - a charming desktop pet powered by Claude AI

Anthropic's enterprise code security scanning, now powered by Claude Mythos 5 in public beta, tracing data across files to report CWE categories, severity, and suggested fixes.

Anthropic's generally available Fable-class model for coding and knowledge work. $10/$50 per 1M tokens, cache reads $0.25, API id claude-fable-5-1.