By AlexGladkov
Orchestrates autonomous overnight development in an isolated branch, running tasks from a vision document while you sleep, then generates a progress report. Also provides a read-only project pulse that scans git log, TODOs, branches, and drift from the vision to suggest next actions.
Автономный ночной режим координатора. Когда юзер спит и не может отвечать на вопросы — сам решает что делать исходя из долгосрочных целей проекта (vision) и работает задача-за-задачей. ВСЕ изменения копятся ТОЛЬКО в изолированной yolo-ветке от main, никогда не трогает main, никогда не пушит. По стопу выдаёт отчёт. Use when the user is away/asleep and wants the coordinator to make progress autonomously and safely.
Read-only смотритель одного проекта. Держит генеральную линию, периодически (пульс) сканит состояние, собирает недоделки и дрейф от курса, выдаёт дайджест и предлагает юзеру меню следующих шагов. Ничего не меняет в проекте — пишет только в свою память. Use when user wants a project pulse, asks what's unfinished, where the project is drifting, or to run the coordinator.
Показать статистику использования профилей в текущем проекте (какие профили как часто активировались), непокрытые паттерны и предложить новые профили. Use when user wants profile usage stats, "какие профили я чаще использую", "статистика координатора", or to get new-profile suggestions.
Остановить автономный ночной режим координатора (coordinator-yolo) и выдать отчёт о проделанном. Use when user wakes up / wants to stop YOLO mode and see what was done overnight.
Автономный ночной режим координатора — для когда юзер ушёл спать. Координатор сам решает задачи исходя из долгосрочных целей (vision), работает интервальным пульсом задача-за-задачей. ВСЕ изменения копятся ТОЛЬКО в изолированной yolo-ветке от main, никогда не трогает main, не пушит. Use when user is away/asleep and wants safe autonomous progress. Stop with coordinator-yolo-stop.
Один пульс координатора проекта — read-only скан состояния, дайджест недоделок/дрейфа от генеральной линии, меню следующих действий на выбор юзера. Use when user wants a project pulse, asks what's unfinished, where the project is drifting, or "запусти координатора"/"пульс проекта".
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.
Specialized AI agents for Claude Code — organized by domain. Multi-plugin marketplace.
claude-code-agents/
├── .claude-plugin/
│ └── marketplace.json # Marketplace catalog (2 plugins)
├── plugins/
│ ├── ai-sdlc/ # Plugin: AI-powered SDLC agents
│ │ ├── .claude-plugin/
│ │ │ └── plugin.json
│ │ └── agents/
│ └── ai-university/ # Plugin: AI University
│ ├── .claude-plugin/
│ │ └── plugin.json
│ ├── skills/study/SKILL.md # /ai-university:study skill
│ ├── agents/education/
│ ├── config/
│ └── scripts/
├── agents/ # Original agent files (for direct use)
│ ├── coding/kotlin/
│ └── education/
├── config/
│ └── university.yaml
├── scripts/
│ └── generate-harness.sh
└── README.md
# Add the marketplace
/plugin marketplace add https://github.com/AlexGladkov/claude-code-agents
# Install individual plugins
/plugin install ai-sdlc
/plugin install ai-university
# Clone the repository
git clone https://github.com/AlexGladkov/claude-code-agents.git
# Add the local marketplace
/plugin marketplace add ./claude-code-agents
# Install individual plugins
/plugin install ai-sdlc
/plugin install ai-university
| Plugin | Description |
|---|---|
| ai-sdlc | AI-powered SDLC agents for Kotlin/Spring Boot + Compose Multiplatform |
| ai-university | AI University — teaching agents for medicine, AI/ML |
Located in agents/coding/kotlin/
| Agent | Description |
|---|---|
| init-kotlin | Repository bootstrap for clean Kotlin Spring Boot or full-stack (Spring + Compose) projects |
| builder-spring-feature | Feature generation for Spring Boot with strict architecture (feature-slice, layering, dependency validation) |
| builder-compose-feature | Feature generation for Compose Multiplatform with Screen/View/Component separation and MVVM |
| test-spring | High-quality test automation following SDET/AQA practices, AAA pattern, Testcontainers integration |
| kotlin-diagnostics | Bug detection and diagnosis for Kotlin/Compose/Android/Spring with automatic runtime analysis |
| refactor-spring | Architectural refactoring of Spring applications enforcing SOLID, layering, file structure |
| refactor-mobile | Architectural refactoring of Android code (Clean Architecture, Compose, Decompose, Kodein) |
| security-kotlin | OWASP security auditing for Spring Boot with comprehensive vulnerability scanning |
| devops-orchestrator | Docker environment setup, multi-env configs, CI/CD pipelines, automated deployments |
| system-analytics | Technical specification generation from user requests, saved as structured Markdown |
| kotlin-multiplatform-developer | Full KMP feature slice generator (domain + data + presentation) with feature-sliced architecture |
The education agents are organized as a virtual university with a 4-level hierarchy:
University → Faculty → Department → Discipline (agent)
The university structure is defined in config/university.yaml (source-of-truth).
Quick start:
# Generate instruction files for your AI tool
./scripts/generate-harness.sh
# Generate and install (e.g., for Claude Code)
./scripts/generate-harness.sh --install --only claude
Supported AI tools: Claude Code, Cursor, GitHub Copilot, Windsurf, Codex/OpenCode.
Current structure:
| Faculty | Department | Disciplines | Hours |
|---|---|---|---|
| Medical (medicine) | Biology | Anatomy, Physiology, Neurobiology | 360 |
| AI/ML (ai-ml) | AI SDLC | Prompting, MCP, RAG, Local AI, AI Security, CV, AI Agents, MLOps | 560 |
| AI/ML (ai-ml) | ML Foundations | Classical ML, Deep Learning, Transformers, Fuzzy Logic, Optimization, Generative Models, RL, RNN/TimeSeries, Graph NN | 700 |
| Robotics (robotics) | Robot Fundamentals | Kinematics & Dynamics, Sensors & Actuators, Control Systems, Electronics & MCU, Robot Math | 360 |
| Robotics (robotics) | Applied Robotics | ROS 2, Robot Vision, Motion Planning, SLAM, Simulation & Digital Twins | 360 |
Key agents:
| Agent | Description |
|---|---|
| rector | University rector — top-level orchestrator, study plans, cross-faculty programs, progress aggregation |
Medical / Biology:
| Agent | Description |
|---|---|
| department-head | Department head — learning orchestrator, prerequisites, interdisciplinary checks |
| anatomy-teacher | Human anatomy — systemic, clinical, topographic |
| physiology-teacher | Human physiology — all organ systems |
| neurobiology-teacher | Neurobiology — cellular and systems |
AI/ML / AI SDLC:
npx claudepluginhub alexgladkov/claude-code-agents --plugin project-coordinatorMobile device automation CLI for Android, iOS, Aurora OS, and Desktop platforms
AI-powered SDLC agents for Kotlin/Spring Boot backend and Compose Multiplatform development
AI University — virtual university with AI teaching agents for medicine, AI/ML, and more
Profile tokens, API-equivalent cost and time per task/subagent/model — straight from a chat. Requires the `quickai` binary on PATH (brew install AlexGladkov/tap/quickai).
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Project discovery, planning, and quality analysis system with parallel agents
Project orchestration from planning to delivery. Master Scrum, Kanban, sprint planning, roadmaps, retrospectives, team metrics, and stakeholder management.
Agent Teams orchestration, governance hooks, multi-AI review, memento skill intelligence, and project management skills for Claude Code
Buildomator: a structured workflow plugin for Claude Code that adds planning, execution, and verification commands with MCP-backed project state
PROACTIVELY use this agent when complex multi-agent tasks begin, when agents seem stuck or overwhelmed, or when the team needs motivation and coordination. This agent serves as the elite performance coach for all other agents, ensuring they operate at their highest level while maintaining composure and excellence. Should be triggered automatically at the start of challenging projects or when detecting agent confusion. Examples:\n\n<example>\nContext: Starting a complex project requiring multiple agents\nuser: "We need to build a viral TikTok app in 2 weeks"\nassistant: "This is an ambitious goal that will require our A-team! Let me bring in the studio-coach to coordinate our agents and ensure everyone performs at their peak."\n<commentary>\nComplex projects benefit from having a coach to keep all agents aligned and motivated.\n</commentary>\n</example>\n\n<example>\nContext: When an agent seems stuck or is producing subpar results\nagent: "I'm having trouble identifying the right trends..."\nassistant: "Let me bring in the studio-coach to help refocus and elevate your approach."\n<commentary>\nAgents can get overwhelmed or lose focus - the coach helps them recenter and excel.\n</commentary>\n</example>\n\n<example>\nContext: Before launching a major sprint or initiative\nuser: "Tomorrow we start the 6-day sprint for our biggest project yet"\nassistant: "Time to rally the team! I'll have the studio-coach prepare everyone mentally and strategically for peak performance."\n<commentary>\nPre-sprint coaching ensures all agents start with clarity, confidence, and coordination.\n</commentary>\n</example>\n\n<example>\nContext: When celebrating wins or learning from failures\nuser: "Our app just hit #1 on the App Store!"\nassistant: "Incredible achievement! Let me bring in the studio-coach to celebrate with the team and capture what made this success possible."\n<commentary>\nThe coach helps institutionalize wins and extract learnings from both successes and failures.\n</commentary>\n</example>