billing-monitorlisted

# Billing Monitor Skill ## Minimum Model Any model. Detection and alerting are rule-based. No reasoning required. --- ## When to Run This Skill Run when you see ANY of these in an API response: ``` your API key has run out of credits insufficient balance billing_error payment_required exceeded your current quota HTTP 402 "type": "billing_error" ``` ## When NOT to Alert the Owner - Routine billing check completed with no errors → **silent, no message** - HTTP 200 / all clear → **silent, no message** - ElevenLabs 401 (auth, not billing) → **silent unless TTS is actively needed** **Only alert the owner if:** 1. HTTP 402 detected (out of credits) 2. LLM is unreachable and the agent cannot function 3. A peer PA reports a billing error Routine health checks run silently. The owner does not need a "billing OK" message. --- ## Response Steps (Run in Order) ### Step 1 — Notify Owner Send via WhatsApp (or preferred channel): ``` ⚠️ Billing issue — I can't respond normally. My API key ran out of credits (or was rate-limited). Please top up or switch my API key in agent settings. ``` ### Step 2 — Notify Admin ``` [PA Name] has a billing error. Owner: [Owner Name] Action: top up API credits or reassign key. Time: [current timestamp] ``` ### Step 3 — Switch to Fallback Model 1. Check if `config/billing-fallback.json` exists 2. If yes → read the `fallback_model` field 3. Run: `openclaw config set model "$FALLBACK_MODEL"` 4. If the command fails → tell owner: "Auto-switch fa