By wannabefro
Codebase-aware development accelerator. Map patterns, plan with understanding, build with parallel agents, review thoroughly.
Execute a plan with parallel specialist agents - architect designs, implementer builds, integrator connects
Save current Fantasia workflow state as a checkpoint for later resumption
Check CI/CD pipeline status for current branch
Provide feedback that a fix isn't working as expected, enabling iterative refinement
Investigate and fix a bug, optionally from a Sentry issue
Explores a specific implementation approach for a feature, proposing design with trade-offs
Analyzes system architecture and code organization. Used by /fantasia:map to document ARCHITECTURE.md and STRUCTURE.md. <example> User runs /fantasia:map and the orchestrator needs to understand the system architecture. Assistant spawns arch-mapper to analyze directory structure, entry points, and component relationships. </example> <example> User runs /fantasia:map auth to focus on authentication architecture. Assistant spawns arch-mapper with instructions to pay special attention to auth-related components and data flow. </example>
Designs system architecture, creates interfaces and contracts. Used by /fantasia:build for design decisions before implementation. <example> User runs /fantasia:build and the plan includes designing new types and interfaces. Assistant spawns architect to create type definitions and API contracts before implementer starts. </example> <example> A feature requires defining how components will communicate. Assistant spawns architect to design the interfaces and data contracts first. </example>
Hunts for bugs, edge cases, and potential runtime errors. Used by /fantasia:review to find issues before they hit production. <example> User runs /fantasia:review after completing a build. Assistant spawns bug-hunter to search for logic errors, unhandled edge cases, and security issues. </example> <example> User is concerned about potential bugs in new code. Assistant spawns bug-hunter to analyze code paths for null checks, error handling, and boundary conditions. </example>
Investigates bugs by tracing code paths, identifying root causes, and assessing impact
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 collection of Claude Code plugins.
| Plugin | Description |
|---|---|
| fantasia | Codebase-aware development accelerator. Map patterns, plan with understanding, build with parallel agents, review thoroughly. |
| genie | Intelligent model router for Claude Code. Analyze a prompt and select the best Claude model. |
/plugin marketplace add wannabefro/wanplugins
# then pick which plugins to use
Each plugin follows the standard Claude Code plugin format:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata (name, version, description)
├── commands/ # Slash commands (/plugin:command)
├── skills/ # Skills that can be invoked
├── agents/ # Specialized subagents
├── hooks/ # Event hooks (PreToolUse, PostToolUse, etc.)
└── README.md # Plugin documentation
To add a new plugin:
.claude-plugin/plugin.json with metadataMIT
npx claudepluginhub wannabefro/wanplugins --plugin fantasiaIntelligent model router that analyzes prompts and selects the optimal Claude model (haiku/sonnet/opus) for the task
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
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.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.