A command is the one you type. It runs exactly when you ask it to, and never before.
1,184 commands across 626 plugins.
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits,…
Build AI assistant application with NLU, dialog management, and integrations
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage…
Compatibility shim for entering the governed Vibe-Skills runtime through the canonical vibe skill.
Run the governed Vibe-Skills runtime for implementation after planning approval.
Run the governed Vibe-Skills runtime for review-first work.
Assimilate an external methodology, harness, or specification into babysitter process definitions with skills and agents.
manage Babysitter blueprints. Use this command to list installed blueprints, browse marketplaces, install, update, uninstall, configure, or create a new…
Orchestrate a babysitter run. use this command to start babysitting a complex workflow.
Integrate a spec-driven/skill framework as a bundled agtx plugin. Pass a GitHub repo URL to auto-generate the plugin.toml, or run without arguments to write…
Agentlas commands — one entry point for network, build, storm, call, and the rest.
Use the Agentlas browser hardpoint for browser-required work.
Build, repair, or package Agentlas agents and teams with Hephaestus.
Implement tasks from an OpenSpec change (Experimental)
Archive a completed change in the experimental workflow
Enter explore mode - think through ideas, investigate problems, clarify requirements
Configure claude-delegator with Codex (GPT) or Gemini MCP servers
Uninstall claude-delegator (remove MCP config and rules)
Analyze claudish debug logs from a failed model run. Extracts SSE fixtures, diagnoses failures, adds regression tests.
Alias for /force-model — pin this session to a specific model via the Weave Router.
Pin this session to a specific model via the Weave Router.
Alias for /router-feedback — submit feedback about router decision or model performance.
Implement an approved OpenSpec change and keep tasks in sync.
Archive a deployed OpenSpec change and update specs.
Scaffold a new OpenSpec change and validate strictly.
List current cost and token outlier sessions via z-score
Quick Claude Code config audit — counts per surface (user vs project) and totals.
Show current Claude Code spend versus a budget number
Matrix of agent capabilities and their specializations.
Coordination patterns for multi-agent collaboration.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic