Claude (Subscription)

What It Is

Claude (Subscription) is an AI provider that runs your AI nodes through Claude Code — Anthropic's command-line app and the officially supported Agent SDK path for building on Claude. Instead of pasting an API key, you sign in to Claude Code once with your Claude account, and Watchflows uses that session.

Everything an AI node can do works here: plain prompts, structured JSON output with schema validation, and the AI Agent node's full tool-using loop. To Watchflows it's just another provider in the picker — the difference is who bills the usage (your Claude plan) and how the call travels (through the local claude binary rather than an HTTP API).

Setup

1. 1 Install Claude Code from claude.com/claude-code if it isn't on your Mac already.
2. 2 Sign in — run claude in Terminal and log in with your Claude account.
3. 3 Add the provider — Settings → AI Providers → Add Provider → Claude (Subscription).

There are no API key or URL fields. In their place the provider sheet shows a live status card with three checks:

• Claude Code installed — green shows the installed version; red offers an Install Claude Code link.
• Signed in — red shows the copyable claude Terminal command that starts the sign-in flow.
• Ready — both checks pass and the provider can run.

Just installed or just signed in? Hit Recheck — it re-runs the checks immediately instead of waiting for the next automatic probe.

Billing & Limits

Calls consume your Claude plan's usage limits — the same pool as your other Claude Code use. When your plan's limits are hit, runs pause until the limits reset: the AI node fails with a clear plan limit reached message rather than looping or retrying on its own.

If extra usage is enabled on your Claude account, calls may continue past the plan limits at API rates billed by Anthropic — Watchflows cannot see that spend.

Models

The model list is a set of aliases, not pinned versions. Each alias resolves to Anthropic's current model of that family, so you stay on the latest generation without updating Watchflows.

Limitations

• Text only — no image input. An AI node that receives an image on this provider fails with a clear message; pick a vision-capable provider for that node instead. If you want a subscription-based option that does handle images, ChatGPT (Subscription) accepts vision input.
• Temperature and max-tokens are ignored — Claude Code manages its own generation settings.
• Requires the CLI installed and signed in — the provider is unavailable in the picker until both checks pass.
• Latency is seconds, not milliseconds — expect roughly 2–3 seconds per call. Fine for automations; noticeable if a flow chains many AI nodes.
• AI Agent runs are metered per turn — every turn of an AI Agent's loop (each tool decision or reply) is its own ~2–3 second Claude Code call, and each turn draws on your plan's usage. A long agent run spends many turns of plan usage where a single Prompt node spends one.
• Concurrent runs are queued — a couple of calls run at once; the rest wait their turn instead of stampeding your plan.

Troubleshooting

These are the exact messages the app shows, and what to do about each.

Privacy

Prompts and payload data go to Anthropic under your account, governed by your Claude account's terms and data settings. Nothing routes through Watchflows servers — the app talks only to the Claude Code CLI on your Mac, which talks directly to Anthropic.

Unlike Ollama, LM Studio, or the Apple on-device model, this is not a local provider: your data does leave the machine. For fully offline or privacy-sensitive flows, use a local provider instead.