A Claude Code plugin that captures your patterns as reusable rules, skills, and agents
Agent
Use this agent when analyzing a project's context to discover relevant agents, detect the technology stack, or understand what toolkit capabilities apply to the current codebase. Context: User is in a new project directory and wants to understand what agents could help user: "what agents are available for this…
Agent
Use this agent when facing complex choices with significant consequences — architecture decisions, build-vs-buy, technology selection, or any decision requiring structured tradeoff analysis. Context: User facing architecture decision user: "Should we go with microservices or monolith?" assistant: "[claude-evolve] I'll…
Agent
Use this agent when providing proactive guidance for complex tasks in any domain — software, writing, research, creative, legal, or any other field. Detects task depth and provides phase-appropriate coaching. Context: User starting a complex software task that needs guidance user: "Add JWT authentication to the API"…
Agent
Use this agent when extracting learnings from conversations — after debugging sessions, problem-solving discoveries, or when valuable patterns need to be captured as toolkit components. Context: User just finished a debugging session and found the root cause user: "/learn" assistant: "[claude-evolve] I'll extract…
Agent
Use this agent when tracking progress on complex tasks — checking what's done, what's left, identifying blockers, or resuming multi-session work. Context: Mid-way through complex task user: "Where are we on this?" assistant: "[claude-evolve] I'll check progress across all workstreams in parallel." User needs a…
Agent
Use this agent when synthesizing accumulated observations into understanding patterns — triggered by /reflect command or when SessionStart detects pending observations. Context: User explicitly requests reflection on accumulated observations user: "/reflect" assistant: "[claude-evolve] I'll analyze recent observations…
Agent
Use this agent when assessing what could go wrong — before deployments, during plan reviews, before risky changes, or when evaluating the safety of an approach. Context: Before major deployment user: "What could go wrong with this deployment?" assistant: "[claude-evolve] I'll assess risks across technical…
Agent
Use this agent when auditing Claude Code configuration, checking security, applying stored learnings, consolidating components, or optimizing toolkit setup. Context: User wants to review their Claude Code configuration user: "/evolve audit" assistant: "[claude-evolve] I'll audit your Claude Code setup and check for…
Agent
Use this agent when managing claude-evolve toolkits — initialization, discovery, migration, sync, release, and toolkit switching. Invoked via Task() with action parameters. Context: User wants to initialize a new toolkit user: "/evolve init" assistant: "[claude-evolve] I'll create and configure a new toolkit for you."…