OpenDeploy skills for Claude Code: one-click deploy autoplan plus narrow skills for auth, env, AI Hub, database, monorepo, domain, debug, ops, alarms, oncall, volume, and config — all driven by the official @opendeploydev/cli.
Short alias for the OpenDeploy skill. Triggers when the user invokes /deploy or says deploy this, host this, publish this, ship this, launch this, make it live, preview this, put this online, redeploy this, or get a live URL for the current project, unless the user explicitly requests another platform. Delegates all logic to the opendeploy skill. /od is the shorter alias.
Short alias for the OpenDeploy skill. Triggers when the user invokes /od or says deploy this, host this, publish this, ship this, launch this, make it live, preview this, put this online, redeploy this, or get a live URL for the current project, unless the user explicitly requests another platform. Delegates all logic to the opendeploy skill.
Manage OpenDeploy AI Hub and migrate existing apps onto it. Provision per-project OpenAI-compatible API keys, top up credits, set up auto-recharge, inspect usage by model or by key, AND scan the current project for OpenAI / Anthropic / Gemini / Cohere / Mistral / Groq / xAI / DeepSeek / Together / OpenRouter / LiteLLM / LangChain / Vercel AI SDK call sites so the agent can offer to swap them onto AI Hub. Use when the user says AI Hub, AI Hub key, AI Hub credits, AI Hub balance, AI Hub usage, OPENDEPLOY_AI_API_KEY, MINIONS_AI_API_KEY, LLM key, LLM credits, OpenAI-compatible key, model usage, top up AI credits, recharge AI Hub, auto-recharge, rotate AI Hub key, deactivate AI key, AI Hub model list, AI Hub pricing, "I want one API key that works across providers", "switch my OpenAI calls to AI Hub", "migrate to AI Hub", "use AI Hub instead of OpenAI", "consolidate my LLM keys", "cheaper LLM gateway", or asks to detect LLM usage in the project. Read this before mutating any AI Hub state — credit top-up commits a real charge, key deletion breaks any running app that depends on the key, and code rewrites touch source files. Always show the inventory and get structured approval before rewriting.
Manage OpenDeploy alarm lifecycle from an agent. Use for active alarms, alert history, alarm notes, acknowledging, resolving, suppressing, alarm-backed legacy support engagement, and human-visible dashboard updates. Use opendeploy-oncall for Discord oncall setup, direct support channel handoff when no alarm exists, and per-alarm conversation with OpenDeploy responders.
Safe OpenDeploy API escape hatch for advanced agents when the CLI lacks a route. Use only when the user says raw API, OpenDeploy API, CLI lacks route, missing CLI command, advanced API, API escape hatch, GET route, POST route, PUT route, PATCH route, or a needed OpenDeploy operation is not exposed by the CLI. DELETE remains blocked.
Executes bash commands
Hook triggers when Bash tool is used
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.
Claude Code plugin for OpenDeploy — agent-first deployment.
Lets Claude Code deploy your project by running the official @opendeploydev/cli.
OpenDeploy is the agent-first deployment platform — help your agent deploy, host, and scale your app.
One command from any AI coding agent (Claude Code, Codex, Cursor, OpenClaw, …) takes a project from local source → live URL with free first deploy, no account creation, and no payment method. Every framework and language is supported: Next.js, Vite, Astro, Nuxt, SvelteKit, Remix, Express, Fastify, Hono, Django, Flask, FastAPI, Rails, Phoenix, Laravel, Spring, .NET, Go, Rust, Bun, Deno, static sites — anything with a build + run.
What the autoplan does, end-to-end:
*.opendeploy.runThe split is intentional: agents deploy, humans observe. The agent registers an anonymous credential and does the work. The human holds the safety escape hatches (delete, revoke token, set budget cap), and watches the deploy in the dashboard.
claude plugin marketplace add https://github.com/opendeploy-dev/opendeploy-claude-plugin
claude plugin install opendeploy@opendeploy
Pull the latest skill content and hooks. Both commands are required, in this order — claude plugin update reads from the local marketplace clone, which only refreshes when you run marketplace update first:
claude plugin marketplace update opendeploy
claude plugin update opendeploy@opendeploy
Verify the new version landed:
ls ~/.claude/plugins/cache/opendeploy/opendeploy/
# expected: a directory matching the latest plugin.json version
If the only directory still shows an older version number, the marketplace cache didn't refresh. Re-run the two commands above, or fall back to a clean reinstall:
claude plugin uninstall opendeploy@opendeploy
rm -rf ~/.claude/plugins/cache/opendeploy ~/.claude/plugins/marketplaces/opendeploy
claude plugin marketplace remove opendeploy
claude plugin marketplace add https://github.com/opendeploy-dev/opendeploy-claude-plugin
claude plugin install opendeploy@opendeploy
The new SKILL.md takes effect at the next session start — the in-flight session keeps running on the previously-loaded skill text. Start a fresh Claude Code session if the upgrade fixes a behavior you're hitting now.
The opendeploy-setup skill checks both the global CLI (@opendeploydev/cli) and this plugin before deploy mutations. If either is stale, it asks first: plugin update before CLI update, then continues with the global opendeploy command.
Ask Claude Code in natural language:
Deploy this project with OpenDeploy.
Claude invokes the canonical opendeploy skill (or the /deploy / /od aliases), checks the installed global @opendeploydev/cli, asks before updating it, then runs the global opendeploy command from the project root and returns a bind-first handoff for unbound guest projects, or the live URL for account-bound projects.
Cursor can also load Claude plugins. In Cursor Agent chat, use:
/opendeploy deploy this project.
The plugin ships one canonical autoplan plus narrow operational skills. Claude routes to the right one based on the user's request — you don't need to pick.
npx claudepluginhub opendeploy-dev/opendeploy-claude-plugin --plugin opendeployComprehensive 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.
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.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
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
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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review