Gather context for a beads issue by exploring the codebase, reading referenced docs, and summarizing findings. Use when starting work on a story, feature, or task and you need to understand the relevant code, architecture, and acceptance criteria before planning.
Fix a bug by coordinating a debugger, coder, and tester through investigation, root cause analysis, regression TDD, code review, and PR creation. Use when the user wants to fix a bug from beads or GitHub issues.
Implement a user story or feature by coordinating a coder and tester through design, implementation with TDD, multi-area code review, and PR creation. Use when the user wants to implement a story, feature, or task from beads.
Investigate a bug by reproducing it, performing root cause analysis, and recording findings in beads and GitHub. Uses the debugger agent to systematically diagnose issues. Use when you need to reproduce a bug, investigate its root cause, and produce an RCA.
Implement a task by coordinating an agent team with parallel prototypes, multi-area code review, fix cycles, PR creation, and comparative evaluation. Use when the user wants to explore multiple implementation approaches for a spike, prototype, or feature.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub galexy/metapowers --plugin metapowersMeta-prompting and self-improvement - skill writer, hook writer
Multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcement
Automatically detects and loads AGENTS.md files to provide agent-specific instructions alongside CLAUDE.md. Enables specialized agent behaviors without manual intervention.
Dynamic orchestrator plugin — 200+ agents, 200+ skills, hooks, and MCP servers. Upstream sources linked via git submodules (agency-agents, everything-claude-code, oh-my-claudecode, gstack, superpowers)
Agent coordination and meta-programming - multi-agent orchestration, workflow automation. Works best with other voltagent plugins installed.
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows