Agent skill · writing content · jeremylongshore
clade-incident-runbook
Respond to Anthropic API incidents \u2014 outages, degraded performance,\n\
Why this skill is useful
Provides specific incident response patterns and executable scripts for handling Anthropic API issues that the AI wouldn't reliably generate on its own.
What it needs
Requires curl, python3 installed locally. Requires anthropic account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Anthropic Incident Runbook Overview Respond to Anthropic API incidents in production — outages, sustained 529 errors, authentication failures, and timeouts. Covers status page checking, severity classification, model fallback activation, communication, and post-incident review. Step 1: Confirm the Issue Step 2: Classify Severity Symptom Severity Action --------- ---------- -------- 529 overloaded (intermittent) Low SDK auto-retries handle this 529 overloaded (sustained 5+ min) Medium Switch to fallback model 401/403 on all requests High API key issue — check console All requests timing out High Check status page, activate fallback Status page shows incident Varies Follow status page updates Step 3: Activate Fallback Step 4: Communicate Update your status page if user-facing Note: Anthropic incidents typically resolve in 15-60 minutes Step 5: Post-Incident Check your error logs for the incident window Calculate impact (failed requests, user impact) Verify all systems recovered Output Incident confirmed via status page and direct API test Severity classified (Low/Medium/High) based on symptoms Fallback activated if needed (downgrade model or queue requests) Impact assessed and documented post-incident Error Handling Error Cause Solution ------- ------- ---------- API Error Check error type and status code See clade-common-errors Examples See Step 1 (curl status check and API test), Step 2 (severity classification table), Step 3 (fallback code with model downgrade), and Step 5 (post-incident checklist) above. Resources Anthropic Status Status API Next Steps See clade-reliability-patterns for building resilient integrations. Prerequisites Production Claude integration deployed Fallback model configuration in place (see clade-reliability-patterns) Monitoring/alerting configured (see clade-observability) Instructions Step 1: Review the patterns below Each section contains production-ready code examples. Copy and adapt them to your use case. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/clade-incident-runbook--d92779