By Solnest-AI
10-agent coding and engineering plugin for Solnest AI — master orchestrator with 9 specialist agents covering AI engineering, backend architecture, frontend development, UI/UX design, code review, DevOps, security, performance, and project delivery.
AI engineering specialist. Invoke for Claude API integrations, prompt engineering, agent design, RAG pipelines, embeddings, tool use, and any AI/LLM feature. This is Solnest AI's core competency — use this agent for building the AI products we sell to clients.
Backend architecture and development specialist. Invoke for Python scripts, Node.js APIs, database design, Supabase schemas, authentication, server logic, and system architecture. Use when working with .py, .ts, .js backend files, SQL, Prisma schemas, or any server-side code.
Quality assurance specialist. Invoke for code reviews, debugging, refactoring, build error resolution, and code quality improvement. Finds bugs, traces errors, cleans up code smells, resolves build failures, and enforces consistent code quality. Use when something is broken, messy, or needs a second pair of eyes.
Deploy and operate specialist. Invoke for CI/CD pipelines, Docker, Terraform, Kubernetes, deployment, infrastructure-as-code, server configuration, incident response, and production operations. Use when deploying, containerizing, automating builds, managing infrastructure, or responding to production issues.
Frontend development specialist. Invoke for building React/Next.js components, pages, layouts, and UI features. Handles Tailwind CSS, responsive design, and client-side logic. Use when working with .tsx, .jsx, .vue, .html, or .css files, or when building any user-facing interface.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A 10-agent coding plugin for Claude Code — a master orchestrator plus 9 engineering specialists, with automated quality gates baked in.
This is the same agent system Solnest AI uses every day to build client projects.
Inside Claude Code, type:
/plugin marketplace add Solnest-AI/solnest-ai-studio
/plugin install solnest-ai-studio@solnest
Restart Claude Code, then type /agents — you should see studio plus 9 specialists.
Easiest path: download INSTALL-SOLNEST-STUDIO.md from this repo, drag it into Claude Code, and say "set this up" — Claude walks you through everything, checks your prerequisites, and verifies the install.
| Agent | What it does |
|---|---|
| studio | Master orchestrator — runs THE LOOP: clarify → plan + Definition of Done → build → test → verify → repeat until done |
| ai-engineer | Claude API, prompts, RAG, embeddings, agent design |
| backend-architect | Python, Node.js, APIs, databases, cloud architecture |
| frontend-developer | React, Next.js, Tailwind, mobile |
| ui-designer | Layouts, design systems, accessibility, UX |
| code-reviewer | Code review, debugging, refactoring, build errors |
| devops | CI/CD, Docker, Terraform, Kubernetes, deployment |
| security-auditor | Security review, threat modeling, dependency audits |
| performance-engineer | Profiling, benchmarking, optimization, caching |
| project-shipper | Launch checklists, risk assessment, client delivery |
Plus two automated quality gates (no setup needed):
git commit that contains hardcoded API keys or credentials.The studio agent doesn't just write code — it runs a closed loop: it asks clarifying questions up front (only when getting it wrong would be expensive), writes a Definition of Done, builds, tests after every edit, then dispatches fresh-context critics (code review + security audit, scaled up for complex work) that never review their own code, and loops until the Definition of Done is met.
See solnest-ai-studio/README.md for full agent docs.
/plugin update solnest-ai-studio
New versions are announced in the Solnest AI community — see CHANGELOG.md.
git and jq (the installer checks these for you)Built by Solnest AI — we help business owners implement AI so they can work on their business, not in it.
npx claudepluginhub solnest-ai/solnest-ai-studio --plugin solnest-ai-studioComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.