By tobyilee
Orchestrate multi-agent AI teams (Claude, Codex, Gemini) for parallel coding tasks and second opinions, generate interactive Spring Boot projects with dependencies, run agentic Red-Green-Refactor TDD cycles across JS/Python/Java/Go/Rust, create structured PRDs from repo context, control macOS cmux terminal panes/windows, save conversation logs, and guard destructive bash executions.
npx claudepluginhub tobyilee/toby-plugins --plugin toby-essentialsUse this skill to delegate tasks to OpenAI Codex CLI running in the background. Trigger on "delegate to codex", "send to codex", "ask codex to", "run with codex", "have codex do", "codex에게", "codex로", "코덱스에게", "코덱스로", "use codex for", "let codex handle", "codex한테 시켜", "codex로 돌려봐". Also trigger when the user wants a second opinion from another AI specifically mentioning Codex or OpenAI, wants to compare Claude's approach with Codex, or asks to run a task with an external OpenAI agent in parallel. Do NOT trigger for general "delegate" or "외부 AI" requests without mentioning Codex/OpenAI — those may be better handled by gemini-delegate or other tools.
Use this skill to delegate tasks to Google Gemini CLI running in the background. Trigger on "delegate to gemini", "send to gemini", "ask gemini to", "run with gemini", "have gemini do", "gemini에게", "gemini로", "제미나이에게", "제미나이로", "use gemini for", "let gemini handle", "gemini한테 시켜", "gemini로 돌려봐". Also trigger when the user wants a second opinion from another AI specifically mentioning Gemini or Google, wants to compare Claude's approach with Gemini, or asks to run a task with an external Google agent in parallel. Do NOT trigger for general "delegate" or "외부 AI" requests without mentioning Gemini/Google — those may be better handled by codex-delegate or other tools.
This skill should be used when the user asks about "omc", "oh-my-claudecode", "omc 사용법", "omc 활용", "omc guide", "omc tips", "omc cheatsheet", "omc reference", "omc 모드", "omc 에이전트", "omc 스킬", "which omc mode", "how to use omc", "omc keyword", "omc 매직 키워드", "omc commands", "omc modes comparison", "autopilot vs ralph", "autopilot vs team", "ralph vs ultrawork", "team mode", "omc agent", "omc tool", "omc 설정", "omc setup", "omc doctor", "omc pipeline", "omc architecture", or needs guidance on choosing OMC execution modes, agents, skills, or strategies. Provides a comprehensive quick-reference for oh-my-claudecode v4.10+ plugin.
This skill should be used when the user asks to 'create a prd', 'write prd for', 'plan this feature', 'write requirements', 'spec out a feature', 'product requirements document', 'feature spec', 'define user stories', or needs guidance on structured feature planning and requirements documentation.
Use this skill to save a summary of the current conversation to a markdown file. Trigger on "save conv", "save conversation", "대화 저장", "대화내용 저장", "대화 저장해줘", "대화내용 저장해줘", "conversation 저장", "로그 저장", "대화 기록 남겨", "save chat", "save log", "대화 정리해서 저장", "지금까지 대화 저장", "conv 저장". Also trigger when the user asks to log, archive, or record the current conversation, or wants a summary of what was discussed saved to a file. Do NOT trigger for memory saving (use memory system) or for git commit messages.
Spring Boot 프로젝트를 Spring Initializr를 이용해 생성하는 스킬. 사용자가 Spring Boot 프로젝트 생성, 스프링 부트 새 프로젝트, Spring Initializr, 새 스프링 앱 만들기, create spring boot app, 스프링 부트 시작 등을 요청할 때 반드시 이 스킬을 사용한다. 간단한 Spring Boot 시작 요청이라도 이 스킬을 사용해야 한다.
Use this skill to control the cmux terminal app from Claude Code. Trigger on "cmux", "open browser pane", "split pane", "browser split", "open in browser", "cmux browser", "cmux notify", "cmux split", "새 pane 열어", "브라우저 열어", "알림 보내", "사이드바", "workspace 만들어", "pane 분할", "browser automation", "cmux에서", "cmux로", "cmux 사용해서". Also trigger when the user wants to open a URL alongside their terminal, send notifications when a task completes, manage terminal panes programmatically, automate browser interactions from the CLI, or set sidebar status/progress for build scripts. Do NOT trigger for general tmux commands — cmux is a different app. If cmux is not detected (no socket, no CLI), inform the user and skip.
Guide for developing with Spring Boot 4 and Spring Framework 7. Use this skill whenever the user is working on a Spring Boot 4 project, asking about Spring Boot 4 or Spring Framework 7 changes, migrating from Boot 3 to 4, or encountering issues related to Boot 4 breaking changes. Trigger on "Spring Boot 4", "Spring 7", "Boot 4 migration", "Spring Boot 4 변경사항", "Boot 4로 업그레이드", "Spring Boot 4 프로젝트", "spring-boot 4.x", "Spring Framework 7 변경", "Boot 4 에러", "Jackson 3 마이그레이션". Also trigger when the user creates a new Spring Boot project and the version is 4.x, or when build errors suggest Boot 4 compatibility issues (e.g., missing starters, Jakarta EE 11 issues, Jackson 3 package errors, HttpHeaders API changes). Do NOT trigger for Spring Boot 3.x or earlier questions that don't involve upgrading.
Use this skill when the user wants to develop features using Test-Driven Development with an agentic Red-Green-Refactor cycle. Trigger on "start TDD", "do TDD", "TDD로 개발해줘", "TDD 시작", "TDD 팀 만들어", "테스트 주도 개발", "red green refactor", "test-driven development", "테스트 먼저 작성하고 싶어", "write tests first then implement", "테스트부터 짜줘", "TDD 방식으로 구현해줘". Also trigger when a user describes a feature and says they want it built incrementally with tests, e.g. "이 기능 테스트 먼저 만들고 하나씩 구현하자", "build this with failing tests first", or "한 단계씩 테스트 작성하면서 개발하고 싶어". Do NOT trigger for simply writing unit tests after implementation, running existing tests, or debugging test failures — those are not TDD workflows.
Use this skill to send a task to Codex running in a cmux pane and get the result back as a file. Trigger on "toby codex", "toby codex에게", "toby codex한테", "toby codex로", "toby codex에게 해줘", "toby codex한테 시켜", "toby codex로 보내", "toby codex에게 물어봐". Only trigger when the user explicitly says "toby codex" — the "toby" prefix is required to distinguish from codex-delegate. Do NOT trigger on bare "codex" mentions without the "toby" prefix. This skill communicates with a persistent Codex pane in cmux (started by toby-team-starter) and collects the result via a file. Do NOT trigger for codex-delegate (which launches a new codex process in the background).
Use this skill to send a task to Gemini running in a cmux pane and get the result back as a file. Trigger on "toby gemini", "toby gemini에게", "toby gemini한테", "toby gemini로", "toby gemini에게 해줘", "toby gemini한테 시켜", "toby gemini로 보내", "toby gemini에게 물어봐". Only trigger when the user explicitly says "toby gemini" — the "toby" prefix is required to distinguish from gemini-delegate. Do NOT trigger on bare "gemini" mentions without the "toby" prefix. This skill communicates with a persistent Gemini pane in cmux (started by toby-team-starter) and collects the result via a file. Do NOT trigger for gemini-delegate (which launches a new gemini process in the background).
Use this skill to spawn a multi-agent workspace with Codex and Gemini running alongside Claude in cmux. Trigger on "toby team", "toby team 시작", "toby team 준비", "toby team 시작해", "toby team 준비해", "toby 팀 시작", "toby 팀 준비", "agent team", "에이전트 팀", "codex랑 gemini 같이", "start agent team", "팀 시작", "멀티 에이전트 시작", "codex gemini 같이 띄워", "에이전트 팀 만들어", "spawn agents", "launch agents", "에이전트 pane 열어", "agent pane", "start multi-agent", "codex gemini pane". Also trigger when the user wants Codex and Gemini running side-by-side in terminal panes for parallel work, or asks to set up a multi-agent development environment. Do NOT trigger when the user just wants to delegate a single task to codex or gemini — use codex-delegate or gemini-delegate for that. This skill is specifically for spawning persistent agent panes in cmux.
This skill should be used when the user asks to "use harness", "하네스 사용", "harness use case", "하네스 유즈케이스", "run harness template", "하네스 템플릿", "harness 실행", "하네스 예제 실행", "pick a harness", "하네스 골라줘", "harness menu", "하네스 메뉴", "select harness use case", "하네스 선택", "quick harness", "하네스 빨리", "start harness", "하네스 시작해줘". Presents a menu of pre-built harness use cases and launches the selected one via the harness:harness skill. Do NOT trigger when the user wants to build a custom harness from scratch — use harness:harness directly for that.
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Toby's personal Claude Code plugin marketplace.
v1.27.0Toby's personal toolkit: code analysis, TDD, Spring Boot init, Spring Boot 4 guide, PRD generation, AI delegation, cmux terminal control, multi-agent team (toby-codex, toby-gemini), and security hooks.
| Command | Description |
|---|---|
/code-quality | Evaluate code quality with 4 parallel agents, score 9 dimensions (readability, maintainability, testability, performance, security, etc.), generate markdown report |
/code-explore | Deep codebase analysis with 5 parallel agents (structure, style, architecture, complexity, testing), generate comprehensive report |
/merge-permissions | Merge local project .claude/settings.local.json permissions into global ~/.claude/settings.json |
| Skill | Version | Description |
|---|---|---|
prd | 1.0.0 | Generate structured Product Requirements Documents — gather context, ask clarifying questions, produce actionable specs with user stories |
tdd-team | 0.3.0 | 3-agent TDD team (Red/Green/Refactor) with task decomposition, progress tracking ([x]/[>]/[ ]), and user checkpoints between cycles |
spring-boot-init | — | Spring Initializr API를 활용한 Spring Boot 프로젝트 생성 — Gradle Kotlin DSL 기반, 인터랙티브 버전/의존성 선택 |
spring-boot4-guide | 0.1.0 | Spring Boot 4 / Spring Framework 7 개발 가이드 — migration, breaking changes, Jackson 3, Jakarta EE 11, modularization |
codex-delegate | 0.3.0 | Delegate tasks to OpenAI Codex CLI — background execution, context gathering, parallel delegation support |
gemini-delegate | 0.3.0 | Delegate tasks to Google Gemini CLI — background execution, context gathering, parallel delegation support |
cmux | 0.2.0 | Control the cmux terminal app — window/workspace/pane/surface management, read-screen, send input, browser automation (DOM, network interception, viewport emulation), SSH, markdown viewer, wait-for synchronization, notifications, sidebar metadata, hooks integration |
toby-team-starter | 0.1.0 | Spawn Codex (--full-auto) and Gemini (--yolo) in cmux panes alongside Claude — duplicate detection via pane title labeling |
toby-codex | 0.1.0 | Send a task to the Codex cmux pane and collect the result as a file in tobyteam/ — requires "toby codex" prefix |
toby-gemini | 0.1.0 | Send a task to the Gemini cmux pane and collect the result as a file in tobyteam/ — requires "toby gemini" prefix |
save-conversation | — | Save a summary of the current conversation to a markdown file, with Korean→English prompt rewrites logged to monthly prompt-{yyyymm}.md — trigger with "save conv", "대화 저장", etc. |
omc-tips | 0.2.0 | oh-my-claudecode (OMC) comprehensive quick-reference — mode selection, magic keywords, 19 agents (3-tier), 37 skills, hooks, MCP tools, and practical examples |
use-harness | 0.1.0 | Quick-start menu for pre-built harness use cases — 8 templates across 4 categories (Research, Content, Media, Engineering), category→use case two-step selection, launches via harness:harness |
| Hook | Event | Description |
|---|---|---|
block-dangerous.sh | PreToolUse (Bash) | Block rm -rf outside project dir (direct and indirect via bash -c, eval), path normalization for symlink bypass prevention |
save-conv-before-commit.sh | PreToolUse (Bash) | Ensure conversation log is saved before git commit — blocks commit if no recent conversation log exists or is not staged |
Add this marketplace in Claude Code:
/install-marketplace https://github.com/tobyilee/toby-plugins
Then install individual plugins from it.
MIT
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Development practices: TDD workflow with red-green-refactor
External tools integration skills for CLI utilities, APIs, and third-party services
PLAN/ACT/EVAL workflow with auto-detection, specialist agents, and reusable skills for systematic TDD development
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use