A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
Are you the author? Sign in to claim
Redefining development through cognitive automation and collaborative agent systems.
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment. Expert agents write code, hooks enforce quality in real-time, skills inject framework-specific knowledge, and intelligent cartography auto-maps plugins and projects — so Claude never guesses, never duplicates, and always follows your architecture.

Without plugins: Claude Code writes code based on its training data. It can hallucinate APIs, duplicate existing code, ignore your project structure, and produce inconsistent quality.
With Fusengine plugins:
# Add marketplace
/plugin marketplace add fusengine/agents
# Install all plugins
/plugin install fuse-ai-pilot fuse-commit-pro fuse-laravel fuse-nextjs fuse-react fuse-astro fuse-swift-apple-expert fuse-solid fuse-tailwindcss fuse-design fuse-prompt-engineer fuse-shadcn-ui fuse-security fuse-changelog
# Setup (hooks + API keys + MCP servers)
~/.claude/plugins/marketplaces/fusengine-plugins/setup.sh # macOS / Linux
~\.claude\plugins\marketplaces\fusengine-plugins\setup.ps1 # Windows
Statusline (optional):
bun --cwd ~/.claude/plugins/marketplaces/fusengine-plugins/plugins/core-guards/statusline run config
User prompt → Hook detects project type → Expert agent activated
→ Hook loads SOLID references → Agent reads docs via MCP
→ Hook blocks if DRY violation → Agent writes code
→ Hook checks file size → Sniper validates quality
→ Hook blocks secrets → Commit with version bump
Every step is intercepted. Claude cannot skip research, cannot duplicate code, cannot exceed file size limits, and cannot commit without security validation.
Each plugin provides an expert agent that auto-activates when it detects the framework in your project. The agent has access to official documentation via MCP servers and follows SOLID principles enforced by hooks.
| Plugin | Detects | What the agent does |
|---|---|---|
| fuse-nextjs | next.config.* | App Router, RSC, Prisma 7, Better Auth, proxy.ts patterns |
| fuse-laravel | composer.json + artisan | Eloquent, Livewire, Blade, queues, Sanctum, Stripe Connect |
| fuse-react | package.json + React | React 19 hooks, TanStack Router/Form, Zustand stores |
| fuse-astro | astro.config.* | Islands, Content Layer, Actions, SEO, Starlight, i18n |
| fuse-swift-apple-expert | Package.swift | SwiftUI, concurrency, all Apple platforms (iOS → visionOS) |
| fuse-tailwindcss | tailwind.config.* | v4.1 CSS-first config, @theme, @utility, OKLCH colors |
| fuse-design | Any UI task | Gemini Design MCP + shadcn/ui + WCAG 2.2 accessibility |
| fuse-shadcn-ui | components.json | Radix/Base UI detection, registry, theming, migration |
| Plugin | What it enforces |
|---|---|
| fuse-ai-pilot | APEX workflow orchestration, 7-phase sniper validation, DRY detection via jscpd, 4-level cache (60-75% token savings) |
| fuse-security | OWASP Top 10 scanning, CVE research via NVD/OSV.dev, dependency audit, secrets detection, auth patterns audit |
| fuse-solid | Files < 100 lines, interface separation, JSDoc mandatory — auto-detected for TypeScript, PHP, Swift, Go, Java, Ruby, Rust |
| Plugin | What it automates |
|---|---|
| fuse-commit-pro | Conventional commits with security check, auto version bump, CHANGELOG, git tag — blocks secrets from commits |
| fuse-prompt-engineer | Prompt creation with CoT/Few-Shot/Meta-Prompting, A/B testing, 50+ template library, agent design |
| fuse-cartographer | Intelligent cartography: auto-generates navigable maps of plugins and projects at SessionStart with merge-preserving enrichment — agents navigate via linked index trees, /map --enrich completes descriptions from source frontmatter |
| fuse-changelog | Monitors Claude Code updates, detects breaking changes in plugins, gathers community feedback via Exa |
| Plugin | What it guards |
|---|---|
| core-guards | Blocks git push --force, rm -rf, npm install without lock, enforces SOLID file limits, tracks session state, DRY duplication blocking — also bundles token-optimization hooks (MCP verbosity caps, MCP + WebFetch disk cache, SessionStart cleanup) |
| claude-rules | Injects APEX/SOLID/DRY rules into every prompt so Claude never forgets the methodology |
| Feature | How it prevents mistakes |
|---|---|
| APEX Workflow | Forces Analyze before coding — no more "let me just write this real quick" |
| Agent Teams | Parallel agents with exclusive file ownership — no merge conflicts |
| DRY Detection | Blocks Write/Edit if function/class name already exists — forces import or shared extraction |
| SOLID Hooks | Denies file save if >100 lines or missing SOLID reference read |
| Sniper Validation | 7-phase post-edit check: explore → research → grep → lint → fix → zero errors |
| 4-Level Cache | Caches exploration, docs, lessons, tests — 60-75% token savings |
| Token-efficient by default | Caps MCP verbosity (Context7/Exa numResults≤3, tokens≤2000), disk cache for MCP results + WebFetch with TTL (48h / 24h) and ripgrep lookup, auto-cleanup at SessionStart — typically saves ~150-200 KB per research-heavy session |
| 28 MCP Servers | Context7, Exa, Astro docs, Gemini Design, shadcn, Playwright, and more |
| Smart Commits | Security scan before commit, auto version bump, CHANGELOG, shields.io badge sync |
| Section | Content |
|---|---|
| Getting Started | Installation, configuration, first steps |
| Workflow | APEX methodology, agents, skills, commands |
| Plugins | Per-plugin documentation and skills |
| Reference | Architecture, hooks, MCP servers, cache system |
MIT
Open-source AI code assistant for VS Code and JetBrains — autocomplete, chat, and agents
Garry Tan's Claude Code setup with 23 tools serving as CEO, Designer, Eng Manager, and QA
Kanban-based orchestration for 10+ coding agents with isolated git worktrees per agent
Battle-tested Claude Code workflows — self-correcting memory, parallel worktrees, 8 hook types, 5 agents