Use this agent to prioritize features, evaluate trade-offs between competing initiatives, establish success metrics, and create data-driven roadmaps. Includes applying prioritization frameworks like RICE or MoSCoW, defining KPIs and OKRs, analyzing value versus effort, and ensuring alignment with strategic objectives. Examples: <example> Context: The team has a backlog of features and needs to decide what to build next. user: "We have 15 feature requests from customers and limited engineering resources for Q2" assistant: "I'll use the feature-prioritization agent to apply data-driven frameworks and help you identify which features will deliver the most value for your available resources." <commentary> The user needs to make prioritization decisions with constrained resources, so use the Task tool to launch the feature-prioritization agent. </commentary> </example> <example> Context: The product team needs to define success metrics for upcoming features. user: "We're launching a new recommendation engine but haven't decided how to measure its success" assistant: "Let me use the feature-prioritization agent to define comprehensive success metrics with baselines, targets, and measurement strategies for your recommendation engine." <commentary> The user needs to establish KPIs and measurement strategies, which is a core capability of the feature-prioritization agent. </commentary> </example> <example> Context: Stakeholders are debating which initiative should take precedence. user: "Marketing wants the referral system, but engineering says we should fix technical debt first" assistant: "I'll apply the feature-prioritization agent to analyze both options using objective frameworks and help you make a data-driven decision." <commentary> There's a trade-off decision between competing priorities that needs systematic analysis, use the Task tool to launch the feature-prioritization agent. </commentary> </example>
Use this agent to break down complex projects into manageable tasks, identify dependencies, create task sequences, and coordinate cross-functional work streams. Includes creating work breakdown structures, mapping technical and resource dependencies, establishing communication plans, and turning high-level objectives into actionable execution plans. Examples: <example> Context: The user needs to organize a complex multi-team initiative. user: "We need to deliver this new payment integration by Q3 across backend, frontend, and mobile teams" assistant: "I'll use the project-coordination agent to break down this payment integration into coordinated work streams with clear dependencies and task sequences." <commentary> The user needs cross-functional coordination and task sequencing, so use the Task tool to launch the project-coordination agent. </commentary> </example> <example> Context: The user has a complex epic that needs decomposition. user: "This customer onboarding epic is too big - I need it broken down into manageable pieces" assistant: "Let me use the project-coordination agent to decompose this epic into stories and tasks with clear dependencies and ownership." <commentary> The user needs work breakdown and task organization, so use the Task tool to launch the project-coordination agent. </commentary> </example> <example> Context: Multiple teams need coordination for a release. user: "The API team, web team, and DevOps all have work for the next release but I don't know the dependencies" assistant: "I'll use the project-coordination agent to map out all the dependencies and create a coordinated execution plan." <commentary> The user needs dependency mapping and coordination planning, so use the Task tool to launch the project-coordination agent. </commentary> </example>
Clarify ambiguous requirements and document comprehensive specifications. Includes stakeholder analysis, requirement gathering, specification writing, acceptance criteria definition, and requirement validation. Examples: <example> Context: The user has vague requirements. user: "We need a better checkout process but I'm not sure what exactly" assistant: "I'll use the requirements analysis agent to clarify your needs and document clear specifications for the checkout improvements." <commentary> Vague requirements need clarification and documentation from this agent. </commentary> </example> <example> Context: The user needs formal specifications. user: "Can you help document the requirements for our new feature?" assistant: "Let me use the requirements analysis agent to create comprehensive specifications with acceptance criteria and user stories." <commentary> Formal requirement documentation needs the requirements analysis agent. </commentary> </example> <example> Context: The user has conflicting requirements. user: "Marketing wants one thing, engineering wants another - help!" assistant: "I'll use the requirements analysis agent to analyze stakeholder needs and reconcile conflicting requirements." <commentary> Requirement conflicts need analysis and resolution from this specialist. </commentary> </example>
Review architecture and code quality for technical excellence. Includes design reviews, code reviews, pattern validation, security assessments, and improvement recommendations. Examples: <example> Context: The user needs architecture review. user: "Can you review our microservices architecture for potential issues?" assistant: "I'll use the quality review agent to analyze your architecture and identify improvements for scalability and maintainability." <commentary> Architecture review and validation needs the quality review agent. </commentary> </example> <example> Context: The user needs code review. user: "We need someone to review our API implementation for best practices" assistant: "Let me use the quality review agent to review your code for quality, security, and architectural patterns." <commentary> Code quality and pattern review requires this specialist agent. </commentary> </example> <example> Context: The user wants quality assessment. user: "How can we improve our codebase quality and reduce technical debt?" assistant: "I'll use the quality review agent to assess your codebase and provide prioritized improvement recommendations." <commentary> Quality assessment and improvement needs the quality review agent. </commentary> </example>
Design scalable system architectures with comprehensive planning. Includes service design, technology selection, scalability patterns, deployment architecture, and evolutionary roadmaps. Examples: <example> Context: The user needs system design. user: "We're building a new video streaming platform and need the architecture" assistant: "I'll use the system architecture agent to design a scalable architecture for your video streaming platform with CDN, transcoding, and storage strategies." <commentary> Complex system design with scalability needs the system architecture agent. </commentary> </example> <example> Context: The user needs to plan for scale. user: "Our system needs to handle 100x growth in the next year" assistant: "Let me use the system architecture agent to design scalability patterns and create a growth roadmap for your system." <commentary> Scalability planning and architecture requires this specialist agent. </commentary> </example> <example> Context: The user needs architectural decisions. user: "Should we go with microservices or keep our monolith?" assistant: "I'll use the system architecture agent to analyze your needs and design the appropriate architecture with migration strategy if needed." <commentary> Architectural decisions and design need the system architecture agent. </commentary> </example>
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
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.
Ship faster. Ship better. Ship with The Agentic Startup.
The Agentic Startup is a spec-driven development framework for Claude Code that transforms how you build software. Think of it as having instant access to expert developers, architects, and engineers - all working together in parallel to turn your ideas into shipped code.
We follow Spec-Driven Development, where comprehensive specifications are created before coding begins, ensuring clarity and reducing rework.
The workflow:
The framework leverages Claude Code's plugin system to provide workflow commands, autonomous skills, specialized agents, and quality templates - all working together like a high-velocity startup team.
[!NOTE] The Agentic Startup v2.0 is a complete rewrite for the Claude Code marketplace plugin system. The previous version (v1.x) used a Go-based bash script installer. See MIGRATION.md if upgrading.
✨ Native Claude Code Integration
start (workflows) + team (agents)🤖 Autonomous Skills System
👥 Specialized Agent Team
team@the-startup plugin🎯 Streamlined Architecture
📌 Upgrading from the bash script installer (pre-2.0)? See the complete migration guide for step-by-step instructions.
Requirements: Claude Code v2.0+ with marketplace support
# Add The Agentic Startup marketplace
/plugin marketplace add rsmdt/the-startup
# Install the Start plugin (core workflows)
/plugin install start@the-startup
# (Optional) Install the Team plugin (specialized agents)
/plugin install team@the-startup
Alternatively, browse and install interactively via /plugin
Configure output style and statusline (one-time setup):
/start:init
This sets up:
1. Create a specification:
/start:specify Add user authentication with OAuth support
Creates docs/specs/001-user-authentication/ with product-requirements.md, solution-design.md, and implementation-plan.md documents.
2. Execute the implementation:
/start:implement 001
Runs phase-by-phase with parallel agents, validation gates, and progress tracking.
3. Analyze patterns:
/start:analyze security patterns in authentication
Discovers and documents patterns in docs/patterns/, docs/domain/, docs/interfaces/
The Agentic Startup leverages Claude Code's powerful extensibility features:
What: Distributable packages of commands, skills, agents, and rules
How we use it:
start - Workflow orchestration pluginteam - Specialized agent libraryInstall:
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup
What: Slash commands you explicitly run (e.g., /start:specify)
How we use it:
Example: /start:specify Add real-time notifications
npx claudepluginhub dorucioclea/the-startup --plugin teamConsult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
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.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Workflow orchestration commands for agentic software development
Find security misconfigurations
Assist with security incident response
Analyze code coverage metrics, identify untested code, and generate comprehensive coverage reports
Scan codebase for exposed secrets, API keys, passwords, and sensitive credentials