Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By tbdng
Compound engineering with Agent Teams + Ralph Loops. Spawn coordinated teams that iterate until tests pass, then capture learnings for the next cycle. Includes 6 commands and 2 skills.
npx claudepluginhub tbdng/compound-teams-plugin --plugin compound-teamsExecute an implementation plan using Agent Teams. Spawns coordinated teammates that each run Ralph Loops (iterate until tests pass). Use after /ct:plan.
Extract learnings from the most recent build/review cycle and update CLAUDE.md. This is what makes the workflow compound — each cycle improves the next.
Research the codebase and web, then create a detailed implementation plan with parallelizable tasks. Run this before /ct:build.
Fast build for small tasks (bug fixes, refactors, config changes) that don't need a full plan. Spawns 1 builder + 1 verifier with Ralph Loop.
Spawn a review team that examines recent code changes from security, architecture, and correctness perspectives. Run after /ct:build.
Knowledge management for compound engineering. Use when adding learnings to CLAUDE.md, reviewing past patterns, or deciding how to structure project memory. Covers entry format, section organization, and maintenance.
The Ralph Loop pattern for Agent Team teammates. Use when spawning builder teammates that need to iterate until all tests, lint, and type checks pass. Provides the standard retry logic, max attempts, and escalation rules.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Intelligently compose and deploy Claude Code Agent Teams. Auto-selects optimal team composition from 24+ agents and 83+ skills across 5 scopes, generates task dependency graphs, and orchestrates multi-agent workflows with a single command.
Agent Teams スキルを設計・構築するためのベストプラクティスガイド。サブエージェント定義、SendMessage 通信プロトコル、タスク依存管理、PostToolUse Hook ログ、MCP ツール統合、コンテキストファイル設計を網羅。7つの実績あるチームスキルから抽出したパターン集
Skill for deciding when and how to create agent teams - single agent vs parallel subagents vs coordinated teams, with model selection and communication patterns
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
The team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation). Claude Code용 팀 아키텍처 팩토리: 도메인 한 문장을 에이전트 팀과 스킬 세트로 변환하는 메타 스킬.
A Claude Code plugin marketplace distributing the compound-teams plugin.
/plugin marketplace add https://github.com/tbdng/compound-teams-plugin
/plugin install compound-teams
Then in any project:
/ct:setup
See plugins/compound-teams/README.md for full documentation.
MIT