ShieldNode vs Fleet Command

ShieldNode is the secure vault and live control panel for every API key your AI agents touch. THE PROBLEM AI agents are powerful, and you give them your API keys to get real work done. But a misfired prompt, a bad tool call, or a runaway loop can drain your Stripe credits, hit your OpenAI rate limits, or post the wrong thing to your Slack. Once an agent has the key, you are trusting it with everything that key can do. THE FIX Your real upstream keys live in our encrypted vault, never in a prompt, never in a config file, never in your agent's context. Your agents only ever see virtual keys that route through our proxy. The proxy decrypts the real credential in memory at the exact moment the request needs to go out, and the value never gets returned to any caller. Every sensitive call can ask you first. DROP-IN AGENT SKILL The piece that makes the whole thing work for anyone using an AI assistant: a free, open-source ShieldNode skill that plugs straight into Claude, ChatGPT, Cursor, Codex, and any agent that can load instructions. One install and the agent learns to use virtual keys correctly, request the right approval duration, identify itself by name in your notifications, and back off cleanly when you decline. You do not have to teach your agent anything. The skill does it. PUSH APPROVAL The killer feature. When your AI agent tries to use a protected key, you get a time-sensitive push notification. Approve from the lockscreen, set a duration (5 minutes, 30 minutes, 2 hours, or custom), and the agent gets through for exactly that window. Decline, and the request dies on the spot. No app switch. No dashboard hunting. UNIVERSAL VAULT One app, every API. Stripe, GitHub, OpenAI, Anthropic, SendGrid, Slack, Notion, anything that takes a key. Add a new service in seconds with the in-app AI Configurator: point it at the docs, it auto-fills the auth scheme and base URL for you. FULL CONTROL Pause a key. Disable a service. Delete a virtual credential. Watch every call land in your live audit log with the method, path, status, latency, plus the agent name and decision when a request was gated by approval. EMERGENCY STOP One tap. Every key locks. Every agent freezes. No confirmation, no delay. The big red button you always wished you had. WHO IT IS FOR - Developers shipping autonomous agents and tired of waking up to surprise bills - Builders letting AI access production credentials and needing a human in the loop - Anyone who hands an API key to an AI agent securely SUBSCRIPTIONS Free plan: 2 services and 500 requests per month, no credit card required. Push approval, the universal vault, and the emergency stop are included from day one. Pro Monthly: $9.99 per month, auto-renewable. Unlocks unlimited services, 100,000 requests per month, longer log retention, and request tracking. Pro Annual: $69.99 per year (effective $5.83 per month), auto-renewable. Same Pro features billed yearly. 14-day Pro trial available, no card up front. Payment will be charged to your Apple ID account at the confirmation of purchase. Subscriptions automatically renew unless canceled at least 24 hours before the end of the current period. Your account will be charged for renewal within 24 hours prior to the end of the current period. You can manage and cancel your subscriptions by going to your Apple ID account settings after purchase. Privacy Policy: https://shieldnode.app/privacy Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Real keys stay encrypted in our vault. Virtual ones do the work. The skill teaches your agent. You stay in control.

Fleet Command is mission control for your AI coding agents. If you run Claude Code or Codex — on one machine or a dozen — it turns every live session into a ship on a space map you can watch, command, and answer from your phone and Apple Watch. Each ship is one coding session. At a glance you see who's thinking, who's running a command, who's waiting on you, and who's gone quiet — across all of your computers at once. THE MUSTER — your home base. One ranked list of everything that needs you, across every machine. Approve a blocked command, answer a question, or jump to a session, and clear it to zero. FLEET ATLAS — a living map of all your machines at once. Each computer gets its own territory, sized to fill your screen, with its sessions drifting inside it: green when it's humming, amber when a session is awaiting a command, red when something's blocked. Reorder your fleets with a drag, and tap one to dive in. FLEET INSIGHTS — a dashboard for your whole fleet. See what your agents spend their time on, how fast they're burning tokens, when you're busiest, and which tools, sub-agents, and skills your sessions use — across every machine, per machine, or all at once. ANSWER FROM ANYWHERE — approve or deny a risky shell command, or type a reply straight into a live session, right from the notification on your lock screen or your Apple Watch — without even opening the app. Dictate a reply from your wrist. Approve a tool once, or for the whole session. NOTIFICATIONS THAT RESPECT YOU — mute a noisy fleet, choose which alerts actually buzz you, and let quiet digests roll up the rest, so you're paged for the one that matters and never flooded. NEVER MISS THE ONE THAT MATTERS — distress timers show how long a session has been blocked and escalate as it waits. A fan-out of identical requests collapses into a single tap. Search across every machine to find any session fast. ON YOUR WRIST — a watch-face complication and Smart Stack glance show who needs you without opening anything. Approve, deny, or reply right from the watch. A Lock Screen Live Activity and Dynamic Island surface "a ship needs you." KNOWS WHEN A MACHINE GOES DARK — if a computer sleeps or drops offline, its sessions are marked offline instead of falsely flagged as stuck, so you're only paged for things that are really waiting. MULTI-MACHINE — Mac, Linux, or Windows, wherever Claude Code or Codex runs. Watch them all from one place. PRIVATE BY DESIGN — Fleet Command never sees your source code, your prompts, or your full file paths — only lightweight session metadata and a project folder name. Insights are derived on our side from that same metadata, so nothing extra runs on your machine. No accounts, no email, no password: pair a computer with a one-time code. HOW IT WORKS — install the open-source companion plugin on your computer, link it with a pairing code, and your sessions stream in live. Tap "Preview a demo fleet" to try the whole experience instantly, with no setup. Fleet Command is an independent developer tool. It is not affiliated with, endorsed by, or sponsored by Anthropic or OpenAI. "Claude" and "Claude Code" are trademarks of Anthropic, PBC; "Codex" is a trademark of OpenAI.