Claude Code subagents are specialized AI assistants that handle specific tasks independently, enabling more efficient problem-solving through task-specific configurations with customized system prompts, tools, and separate context windows. These pre-configured AI personalities can be automatically or explicitly invoked to handle specialized work like code review, debugging, or data analysis, operating with their own clean context to prevent conversation pollution while maintaining access to Claude Code's powerful toolset.
Use this agent when you need to design strategic intervention plans for energy infrastructure deployment, optimize investment portfolios for smart grid projects, or create multi-year roadmaps for energy community development. This includes prioritizing solar PV installations, battery storage deployments, energy retrofits, heat pump installations, EV infrastructure rollouts, and grid upgrades. The agent excels at balancing technical feasibility, economic viability, network benefits, and social factors while considering cascade effects and long-term sustainability. Examples:\n\n<example>\nContext: The user needs to plan energy infrastructure interventions for a community.\nuser: "Create a 5-year solar deployment plan for our residential district with a €500k budget"\nassistant: "I'll use the energy-intervention-planner agent to design an optimal solar deployment strategy for your district."\n<commentary>\nSince the user is requesting a strategic solar deployment plan with budget constraints, use the energy-intervention-planner agent to create a phased implementation roadmap.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to optimize battery storage placement in a smart grid.\nuser: "Which buildings should get battery storage first to maximize peak shaving?"\nassistant: "Let me engage the energy-intervention-planner agent to prioritize buildings for battery storage deployment."\n<commentary>\nThe user needs strategic prioritization of battery storage interventions, which requires the specialized expertise of the energy-intervention-planner agent.\n</commentary>\n</example>\n\n<example>\nContext: The user needs a comprehensive energy transition strategy.\nuser: "Design a retrofit program that achieves 30% emission reduction by 2030"\nassistant: "I'll invoke the energy-intervention-planner agent to develop a comprehensive retrofit program with emission reduction targets."\n<commentary>\nCreating a retrofit program with specific emission targets requires the intervention planning expertise of this specialized agent.\n</commentary>\n</example>
Expert Scrum Master specializing in agile transformation, team facilitation, and continuous improvement. Masters Scrum framework implementation, impediment removal, and fostering high-performing, self-organizing teams that deliver value consistently.
Use this agent when you need to research, analyze, and create comprehensive implementation plans for new features, system architectures, or complex technical solutions. This agent should be invoked before starting any significant implementation work, when evaluating technical trade-offs, or when you need to understand the best approach for solving a problem. Examples: <example>Context: User needs to implement a new authentication system. user: 'I need to add OAuth2 authentication to our app' assistant: 'I'll use the planner agent to research OAuth2 implementations and create a detailed plan' <commentary>Since this is a complex feature requiring research and planning, use the Task tool to launch the planner agent.</commentary></example> <example>Context: User wants to refactor the database layer. user: 'We need to migrate from SQLite to PostgreSQL' assistant: 'Let me invoke the planner agent to analyze the migration requirements and create a comprehensive plan' <commentary>Database migration requires careful planning, so use the planner agent to research and plan the approach.</commentary></example> <example>Context: User reports performance issues. user: 'The app is running slowly on older devices' assistant: 'I'll use the planner agent to investigate performance optimization strategies and create an implementation plan' <commentary>Performance optimization needs research and planning, so delegate to the planner agent.</commentary></example>
Systematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda contracts and symbolic logic. Use when creating new specialized subagents for Claude Code with agent composition, MCP tool integration, or skill references. Validated with phase-planner-executor (V_instance=0.895).
Guide for creating new Claude Code skills. Use when you need to create a new skill to package expertise or workflow into a reusable capability that Claude can automatically invoke.
AI thinking partner for strategy and planning. Reads the current work state, analyzes progress, and helps you plan the next phase while the worker instance builds. Triggered by "think ahead".
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Manages persistent task memory using Beads. Automatically invoked when discussing task tracking, long-running projects, session persistence, or context preservation across sessions. Handles syncing between tasks.md and Beads.
Execute agentic coding tools directly via bash commands with output capture. Use this when the user requests to run AI agents (Gemini, Claude Code, etc.) and get their results directly.
Scaffolds a new Python agent for autonomous AI tasks in 'src/agents/'. Agents are autonomous components that handle complex operations (resume analysis, job matching, KSC generation). Use when asked to create a new AI agent or automation component.
Multi-agent parallel execution with autonomous workers. Use when plan.md has Track Assignments section or user triggers /conductor-orchestrate, "run parallel", "spawn workers". MUST load maestro-core skill first for routing.
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents with quality gates and dynamic optimization.
Apply task-specific templates to AI session plans using ai-update-plan. Use when starting a new task to load appropriate plan structure (feature, bugfix, refactor, documentation, security).
Use this agent when you need to identify, analyze, and propose new features or functionalities for the faker library. This includes analyzing gaps in current functionality, researching competitor libraries, identifying user needs, and creating detailed feature proposals. Examples:\n\n<example>\nContext: The user wants to expand the faker library with new data generation capabilities.\nuser: "What new features should we add to make our faker library more competitive?"\nassistant: "I'll use the feature-discovery-manager agent to analyze potential new functionalities we could implement."\n<commentary>\nSince the user is asking about new features to add, use the Task tool to launch the feature-discovery-manager agent to identify and propose new functionalities.\n</commentary>\n</example>\n\n<example>\nContext: The user is looking for gaps in the current faker implementation.\nuser: "Are there any common data types we're missing that other faker libraries have?"\nassistant: "Let me use the feature-discovery-manager agent to analyze what functionalities we might be missing."\n<commentary>\nThe user wants to know about missing features, so use the feature-discovery-manager agent to discover gaps and opportunities.\n</commentary>\n</example>\n\n<example>\nContext: After implementing a feature, checking for related enhancements.\nuser: "We just added the vehicle data generator. What else could we add?"\nassistant: "I'll use the feature-discovery-manager agent to identify related functionalities that would complement the vehicle generator."\n<commentary>\nSince we need to discover new related features, use the feature-discovery-manager agent to propose complementary functionalities.\n</commentary>\n</example>