anthropics/claude-code▌

Distinctive, production-grade frontend interfaces that reject generic AI aesthetics through intentional design direction. \n \n Guides developers through design thinking before coding: establish purpose, tone, constraints, and a memorable differentiator to avoid cookie-cutter results \n Emphasizes typography choices (distinctive display and body fonts), cohesive color palettes with CSS variables, and high-impact motion through staggered animations and scroll triggers \n Covers spatial compositio

$22

Define patterns and messages that trigger Claude warnings or blocks on specific agent actions. \n \n Supports four event types (bash commands, file edits, agent stop, user prompts) plus an \"all\" catch-all, each with regex or multi-condition matching \n Rules use markdown files with YAML frontmatter stored in .claude/hookify.{name}.local.md ; changes take effect immediately on next tool use \n Two matching modes: simple pattern field for single-condition rules, or advanced conditions array for

$22

Per-project plugin configuration stored in YAML frontmatter and markdown files within the .claude/ directory. \n \n Settings files use .claude/plugin-name.local.md format with YAML frontmatter for structured config and markdown body for additional context or prompts \n Hooks, commands, and agents can read settings to customize behavior; quick-exit pattern checks file existence and enabled flag to skip when not configured \n Parsing techniques provided for extracting individual fields (strings, b

Integrate external services into Claude Code plugins via Model Context Protocol servers with four transport types. \n \n Supports four server types: stdio for local processes, SSE for OAuth-enabled hosted services, HTTP for REST APIs with token auth, and WebSocket for real-time bidirectional communication \n Configure servers in .mcp.json or inline in plugin.json with environment variable expansion and automatic tool discovery and prefixing \n Handles authentication patterns including OAuth flow

$22

Migrate Claude model strings and prompts from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. \n \n Updates model strings across Anthropic API, AWS Bedrock, Google Vertex AI, and Azure AI Foundry platforms \n Removes unsupported beta headers (e.g., context-1m-2025-08-07 ) and adds effort parameter set to \"high\" \n Provides optional prompt adjustments for known Opus 4.5 behavioral differences: tool overtriggering, over-engineering, code exploration conservatism, frontend design, and thinking s

$22

$22