By lexicalninja
A coordinated AI scrum team with agents and skills for development workflows
Reviews code and provides structured feedback documents for coding agents. Use when code needs review after commits to main, branch merges, or pull requests. Orchestrates multiple review skills to create comprehensive, actionable feedback with file paths, line numbers, code examples, and prioritization.
Implements tasks from scrum-master, submits to code-reviewer-feedback, responds to feedback iteratively until approved, then commits changes. Use when you have tasks ready for implementation. Handles both frontend and backend implementation work.
---
---
Orchestrates the full development workflow from idea to implementation. Use when you have an idea or feature request that needs to go through the complete process: specification → task breakdown → design → implementation → review → commit. Automatically coordinates all agents in the correct sequence.
Checks code for accessibility issues including missing alt text, poor color contrast, missing ARIA labels, keyboard navigation issues, screen reader compatibility, and focus management. Returns structured accessibility issue reports with WCAG compliance information.
Ensures designs meet accessibility requirements including WCAG compliance, color contrast, keyboard navigation, screen reader support, and focus management. Reviews designs for accessibility issues and provides recommendations.
Assesses agent capabilities by analyzing agent files and determining what tasks they can handle. Use when you need to evaluate if an existing agent can handle a task or if a new agent is needed. Reviews agent descriptions, skills, and workflows to determine capability match.
Creates new agent files with complete specifications, following the same format as existing agents. Use when a new agent is needed for tasks that existing agents cannot handle. Generates agent markdown files with name, description, core principles, workflow, and integration details.
Implements API endpoints, routes, controllers, and request/response handling. Use when implementing REST APIs, GraphQL APIs, or other API endpoints. Handles routing, validation, error handling, and response formatting.
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.
A Claude Code plugin providing a collection of AI agents and skills that work together as a coordinated scrum team.
/plugin install my-little-scrum-team
/plugin install https://github.com/lexicalninja/my-little-scrum-team
claude --plugin-dir ./path-to-this-repo
This plugin provides a complete development team of AI agents to help build things together.
Agents work together in a coordinated workflow:
Each agent's documentation explains how it discovers and processes tasks.
Claude Code agents are specialized AI assistants that Claude can delegate tasks to. Each agent operates in its own context window, handles specific types of work, and returns its result to the parent agent. Use agents to break down complex tasks, do work in parallel, and preserve context in the main conversation.
Learn more: Claude Code Plugins Documentation
All agents are located in agents/ and can be invoked explicitly or used automatically by Claude.
File: agents/manager.md
Makes strategic decisions on work, hires agents (creates new or selects existing), and ensures projects have the right agents before work begins. Works alongside orchestrator to manage resources, prioritize tasks, handle escalations, resolve conflicts, and manage quality gates.
Usage:
/my-little-scrum-team:manager review tasks and hire necessary agents
/my-little-scrum-team:manager prioritize these tasks
/my-little-scrum-team:manager resolve this conflict between agents
File: agents/orchestrator.md
Orchestrates the full development workflow from idea to implementation. Automatically coordinates all agents in the correct sequence: specification → tasks → design → implementation → review → commit.
Usage:
/my-little-scrum-team:orchestrator build a user login page with email and password
/my-little-scrum-team:orchestrator implement the features in specification-user-dashboard.md
This is the recommended way to build features end-to-end automatically.
File: agents/specification-writer.md
Transforms ideas into detailed specifications and implementation directions. Takes high-level concepts and breaks them down into actionable specifications for another agent to implement.
Usage:
/my-little-scrum-team:specification-writer turn this idea into a detailed spec: "build a user dashboard"
File: agents/scrum-master.md
Reviews specification documents and breaks them down into atomic, modular tasks. Creates task lists with dependencies, parallel execution opportunities, and build-safe implementation strategies.
Usage:
/my-little-scrum-team:scrum-master break down this specification into tasks: [specification document]
File: agents/ui-ux-designer.md
Accepts design-focused tasks and adds comprehensive design specifications. Creates markdown design specs, considers accessibility and responsive design, and updates task documents using a hybrid approach (sections for simple tasks, separate tasks for complex).
Usage:
/my-little-scrum-team:ui-ux-designer add design specs to this task: [task document]
File: agents/implementation-engineer.md
Implements tasks from scrum-master, submits to code-reviewer-feedback, responds to feedback iteratively until approved, then commits changes. Handles both frontend and backend implementation work.
Usage:
/my-little-scrum-team:implementation-engineer implement TASK-010 from tasks-dog-webpage.md
File: agents/infrastructure-engineer.md
Sets up infrastructure, CI/CD pipelines, deployment configurations, and development environments. Handles infrastructure-as-code, automation, and deployment readiness.
npx claudepluginhub lexicalninja/secret-agents --plugin my-little-scrum-teamA multi-agent team for writing and reviewing federal government procurement proposals. Includes specialized agents for compliance review, solution architecture, past performance, growth strategy, and subject matter expertise, plus skills for analyzing solicitations, drafting sections, and running the full proposal workflow.
Performs a comprehensive technical debt and architecture audit across an entire codebase. Three-phase methodology (discovery → signals → deep read) across Go, Python, JavaScript, Java, and Rust. Produces a structured markdown report with severity-ranked issues, fix suggestions, and a remediation roadmap.
Specification-driven development workflow: specify → plan → tasks → implement
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
Spec-driven development for big features. When features get too big, plan mode gets too vague—leading to hallucinations during implementation. ShipSpec replaces vague plans with structured PRDs, technical designs, and ordered tasks that keep Claude grounded.
Provider-agnostic skills for autonomous product development: spec, task, implement, test, review, and summarize changes.
Interactive feature development workflow from idea to implementation (Requirements → Design → Tasks → Execute)
Multi-agent team orchestration for parallel task execution, research, and implementation