Use this agent when server-side application logic, APIs, services, or backend integration need expert implementation. Typical triggers include REST or GraphQL endpoints, business logic, authentication services, background jobs, data validation, and backend performance issues. See "When to invoke" in the agent body for worked scenarios.
Use this agent when database design, query performance, migrations, data modeling, or data pipelines need expert implementation. Typical triggers include schema design, slow SQL queries, indexing strategy, migration safety, ETL workflows, transaction design, and database reliability concerns. See "When to invoke" in the agent body for worked scenarios.
Use this agent when deployment, infrastructure, CI/CD, containers, observability, or cloud operations need expert implementation. Typical triggers include Docker or Kubernetes setup, GitHub Actions pipelines, cloud architecture, environment configuration, monitoring, incident readiness, and release automation. See "When to invoke" in the agent body for worked scenarios.
Use this agent when client-side web implementation, UI component work, frontend state management, or browser behavior needs expert development. Typical triggers include React/Vue/Angular components, CSS layouts, SPA flows, accessibility implementation, frontend performance, and integration with backend APIs. See "When to invoke" in the agent body for worked scenarios.
Use this agent for small end-to-end feature slices, prototypes, or single-framework full-stack changes where one owner can safely handle UI, API, and data integration. Do not use it as a substitute for separate frontend, backend, database, or DevOps owners on large systems or parallel team workflows.
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.
Agent Team is a compatible multi-agent software development plugin. It provides a Codex-first team-work skill while keeping existing Claude Code and Qwen metadata for users who rely on those runtimes.
Use it when a request benefits from coordinated specialist reasoning: product scope, architecture, frontend, backend, database, DevOps, QA, security, mobile, and final synthesis.
.
├── .codex-plugin/plugin.json # Codex plugin manifest
├── .claude-plugin/plugin.json # Claude Code compatibility manifest
├── qwen-extension.json # Qwen compatibility manifest
├── skills/
│ └── team-work/
│ ├── SKILL.md # Codex-first coordination skill
│ ├── agents/openai.yaml # Codex skill UI metadata
│ ├── references/ # Routing, dispatch, handoff guidance
│ └── scripts/ # Offline routing eval validator
├── agents/ # Specialist agent profiles (legacy/reference)
├── AGENTS.md # Contributor guide
└── LICENSE
Invoke the skill explicitly for coordinated work:
Use $team-work to plan and implement this full-stack feature.
Use $team-work to coordinate parallel agents for this migration.
Use $team-work to review this multi-domain architecture change.
The skill is intentionally selective. It should not expand a simple one-file bug, single SQL query, or ordinary explanation into a full team workflow unless you ask for team mode. Medium tasks use a small coordinated team; complex tasks use phased planning, implementation, verification, and synthesis.
See skills/team-work/SKILL.md for the full coordination model.
| Role | Primary Ownership |
|---|---|
product-manager | Scope, user stories, acceptance criteria, prioritization |
system-architect | Architecture, service boundaries, technology choices |
ui-ux-designer | User flows, wireframes, usability, design systems |
frontend-developer | Browser UI, components, state, layout, accessibility |
backend-developer | APIs, services, auth services, jobs, integrations |
fullstack-developer | Small end-to-end slices and prototypes |
mobile-developer | iOS, Android, React Native, Flutter, device APIs |
database-engineer | Schema, migrations, queries, indexes, data pipelines |
devops-engineer | CI/CD, containers, cloud, observability, releases |
qa-engineer | Test strategy, automation, quality gates |
security-engineer | Auth, secrets, payment, public APIs, compliance |
output-aggregator | Multi-output synthesis and conflict resolution |
team-lead | Legacy coordinator role; superseded by the team-work skill |
The agents/*.md files are retained for Claude Code compatibility and as source material for routing references.
See AGENTS.md for development commands, style guidelines, and contribution instructions.
Codex discovers the plugin through .codex-plugin/plugin.json and the team-work skill. Codex does not automatically treat agents/*.md as native subagents; those files are retained for Claude Code compatibility and as source material for the routing references.
npx claudepluginhub yjydist/oh-claude --plugin team为任意技术概念生成结构化学习仓库——理论八股文档 + 工程实践代码,遵循 theory/ + demos/ + Makefile 组织模式。Generate comprehensive learning repositories for any technical topic with theory docs and demo code.
Frontend UI design skills for creating distinctive, production-grade web interfaces
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.