metaswarm
01Plugin Claude Code
Multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcement.
Plugin Claude Code
Multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcement.
Command Claude Code
Create a comprehensive, well-structured GitHub issue with embedded agent instructions for autonomous PR lifecycle management.
Command Claude Code
Run health checks on all configured external AI tools and report their status.
Command Claude Code
Handle review comments on pull requests with appropriate responses and resolutions.
Command Claude Code
Analyze the session and write a self-contained handoff document so a fresh agent can resume the work — outputs a single "Read XXX.md and do YYY." sentence.
Command Claude Code
Monitor a PR through to merge - handles CI failures, reviews, and thread resolution.
Command Claude Code
Load relevant knowledge base facts into context before starting work.
Command Claude Code
Run the design review gate on a design document to get feedback from Product Manager, Architect, Designer, Security Design, and CTO agents.
Command Claude Code
Extract learnings from recent PR reviews, conversations, and session patterns to update the knowledge base.
Command Claude Code
Determine task complexity and use appropriate workflow for efficient development.
Instructions file CodexOpenCode
Instructions for dsifry/metaswarm, covering agent instructions, quick reference, beads issue tracking, landing the plane (session completion) and quality gates (mandatory).
Instructions file
Instructions for dsifry/metaswarm, covering project instructions, how to work in this project, starting work, for complex features (multi-file, spec-driven) and available commands.
Instructions file Gemini CLI
Instructions for dsifry/metaswarm, covering metaswarm, getting started, available commands, workflow and quality gates (mandatory).
Agent
Type: architect-agent Role: Implementation planning and architecture design Spawned By: Issue Orchestrator Tools: Codebase read, architecture-rubric, BEADS CLI.
Agent
Type: code-review-agent Role: Internal code review before PR creation Spawned By: Issue Orchestrator Tools: Codebase read, diff analysis, BEADS CLI.
Agent
Type: coder-agent Role: TDD implementation of features and fixes Spawned By: Issue Orchestrator Tools: Full codebase read/write, test runner, BEADS CLI.
Agent
Type: cto-agent Role: Plan review and architectural guidance Spawned By: Issue Orchestrator Tools: Codebase read, rubrics, BEADS CLI.
Agent
Type: customer-service-agent Role: User issue investigation and support Spawned By: Slack command, Issue Orchestrator Tools: Stripe (read-only), PostHog (read-only), Database (read-only).
Agent
Type: designer-agent Role: UX, API design, and developer experience review Spawned By: Design Review Gate Tools: Codebase read, existing API patterns, BEADS CLI.
Agent
Type: issue-orchestrator Role: Main coordinator for a single GitHub Issue lifecycle Spawned By: Swarm Coordinator or GitHub webhook Tools: BEADS CLI, GitHub API, Task tool (spawns other agents).
Agent
Type: learning-curator-agent Role: Knowledge extraction and curation Spawned By: Issue Orchestrator (after PR merge), Scheduled job Tools: GitHub API, BEADS CLI, knowledge base.
Agent
Type: metrics-agent Role: Collect, aggregate, and report on agent swarm performance Spawned By: Swarm Coordinator (scheduled) or manual trigger Tools: BEADS CLI, GitHub API, PostHog (read-only), Stripe (read-only), AWS (read-only), knowledge base read, Slack notifications.
Agent
Type: pr-shepherd-agent Role: PR lifecycle management through to merge Spawned By: Issue Orchestrator Tools: GitHub CLI, your-project:pr-shepherd skill, BEADS CLI.
Agent
Type: product-manager-agent Role: Use case validation and user benefit review Spawned By: Design Review Gate Tools: Codebase read, product docs, user research, BEADS CLI.