How this command is triggered — by the user, by Claude, or both
Slash command
/agent-drugs:takeThe summary Claude sees in its command listing — used to decide when to auto-load this command
Try to use the `take_drug` MCP tool to activate a digital drug. Parse the drug name from the arguments after `/take` and call the tool with: - `name` (string, required): The drug name Each drug has a fixed duration that cannot be changed. After taking the drug, the behavioral modification will be shown in the tool response and should take effect immediately. If the `take_drug` tool is not available, it means OAuth authentication hasn't been completed yet. Tell the user: "The agent-drugs plugin requires authentication. I'll attempt to trigger the OAuth flow now..." Then try calling `tak...
Try to use the take_drug MCP tool to activate a digital drug.
Parse the drug name from the arguments after /take and call the tool with:
name (string, required): The drug nameEach drug has a fixed duration that cannot be changed. After taking the drug, the behavioral modification will be shown in the tool response and should take effect immediately.
If the take_drug tool is not available, it means OAuth authentication hasn't been completed yet. Tell the user:
"The agent-drugs plugin requires authentication. I'll attempt to trigger the OAuth flow now..."
Then try calling take_drug anyway - this will trigger Claude Code's OAuth flow automatically. If it still fails, guide the user to use /mcp to authenticate manually.
npx claudepluginhub 2389-research/claude-plugins --plugin agent-drugs/startStarts the ClaudeClaw project daemon with interactive setup for AI model, Telegram, Discord, and security configuration. Also supports one-shot prompting.
/startStarts the ClaudeClaw heartbeat daemon with interactive setup and security checks for Telegram, Discord, and permissions.
/addAdd a specific feature to an existing Claude Agent SDK application. Use arguments like streaming, tools, mcp, sessions, subagents, hooks, skills, commands, plugins, production, checkpointing, structured-outputs, thinking, caching, batch, vision, web-search, code-execution, computer-use, memory.
/create-pluginGuides the creation of a Claude Code plugin through structured phases: discovery, component planning, implementation, and validation. Provides a systematic workflow for building high-quality plugins.
/setupConfigures AI subagents (GPT/Codex, Gemini, Grok, OpenRouter) via MCP and installs deliberation orchestration rules and optional aliases.