anth-incident-runbook
Execute incident response procedures for Claude API outages and degradation. Use when Claude API is returning errors, experiencing high latency, or showing degraded performance in production. Trigger with phrases like "anthropic incident", "claude api down", "anthropic outage", "claude degraded", "anthropic runbook".
Best use case
anth-incident-runbook is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Execute incident response procedures for Claude API outages and degradation. Use when Claude API is returning errors, experiencing high latency, or showing degraded performance in production. Trigger with phrases like "anthropic incident", "claude api down", "anthropic outage", "claude degraded", "anthropic runbook".
Teams using anth-incident-runbook should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/anth-incident-runbook/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How anth-incident-runbook Compares
| Feature / Agent | anth-incident-runbook | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Execute incident response procedures for Claude API outages and degradation. Use when Claude API is returning errors, experiencing high latency, or showing degraded performance in production. Trigger with phrases like "anthropic incident", "claude api down", "anthropic outage", "claude degraded", "anthropic runbook".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Anthropic Incident Runbook
## Severity Classification
| Severity | Condition | Response Time |
|----------|-----------|---------------|
| P1 | API returning 500/529 for all requests | Immediate |
| P2 | Rate limiting (429) or high latency (>10s p99) | 15 minutes |
| P3 | Intermittent errors (<5% error rate) | 1 hour |
| P4 | Degraded quality (not errors) | Next business day |
## Immediate Triage (First 5 Minutes)
```bash
# 1. Check Anthropic status page
curl -s https://status.anthropic.com/api/v2/status.json | python3 -c \
"import sys,json; d=json.load(sys.stdin); print(d['status']['indicator'], '-', d['status']['description'])"
# 2. Test API connectivity
curl -s -w "\nHTTP %{http_code} | Time: %{time_total}s\n" \
https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model":"claude-haiku-4-20250514","max_tokens":8,"messages":[{"role":"user","content":"1"}]}'
# 3. Check rate limit headers
curl -s -D - https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model":"claude-haiku-4-20250514","max_tokens":8,"messages":[{"role":"user","content":"1"}]}' \
2>/dev/null | grep -i "ratelimit\|retry-after\|request-id"
```
## Decision Tree
```
API returning errors?
├── 401/403 → Key issue → Check ANTHROPIC_API_KEY is set and valid
├── 429 → Rate limited → Check headers, reduce traffic, wait for retry-after
├── 500 → Server error → Check status.anthropic.com, retry with backoff
├── 529 → Overloaded → Temporary, retry after 30-60s
└── Timeouts → Network or long generation → Increase timeout, check max_tokens
```
## Mitigation Actions
### Rate Limiting (429)
```python
# Immediate: reduce traffic
# 1. Enable circuit breaker
# 2. Queue non-critical requests
# 3. Switch to Message Batches for bulk work
# 4. Reduce max_tokens to shorten generation time
```
### API Outage (500/529)
```python
# Graceful degradation
def get_response_with_fallback(prompt: str) -> str:
try:
msg = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}]
)
return msg.content[0].text
except (anthropic.InternalServerError, anthropic.APIStatusError):
return "Our AI assistant is temporarily unavailable. Please try again shortly."
```
### Key Compromise
```bash
# 1. Immediately revoke key at console.anthropic.com
# 2. Generate new key
# 3. Deploy new key to all environments
# 4. Audit recent usage for unauthorized calls
# 5. File incident report
```
## Postmortem Template
```markdown
## Incident: [Title]
- **Duration:** [start] to [end]
- **Severity:** P[1-4]
- **Impact:** [what users experienced]
- **Root Cause:** [what went wrong]
- **Detection:** [how we found out]
- **Mitigation:** [what we did to fix it]
- **Request IDs:** [from debug logs]
- **Action Items:**
- [ ] [preventive measure 1]
- [ ] [preventive measure 2]
```
## Error Handling
| Symptom | Likely Cause | Quick Fix |
|---------|-------------|-----------|
| All requests fail 401 | Key rotated/expired | Check Console for active keys |
| Sudden 429 spike | Traffic burst or tier change | Check rate limit headers |
| Slow responses (>10s) | Large max_tokens or complex prompt | Reduce max_tokens, use Haiku |
| Intermittent 500s | Upstream API issue | Check status.anthropic.com |
## Resources
- [API Status](https://status.anthropic.com)
- [Error Reference](https://docs.anthropic.com/en/api/errors)
- [Rate Limits](https://docs.anthropic.com/en/api/rate-limits)
## Next Steps
For data compliance, see `anth-data-handling`.Related Skills
responding-to-security-incidents
Analyze and guide security incident response, investigation, and remediation processes. Use when you need to handle security breaches, classify incidents, develop response playbooks, gather forensic evidence, or coordinate remediation efforts. Trigger with phrases like "security incident response", "ransomware attack response", "data breach investigation", "incident playbook", or "security forensics".
windsurf-incident-runbook
Execute Windsurf incident response when AI features fail or cause production issues. Use when Cascade breaks code, Windsurf service is down, AI-generated code causes production incidents, or team needs emergency Windsurf troubleshooting. Trigger with phrases like "windsurf incident", "windsurf outage", "windsurf broke production", "cascade caused bug", "windsurf emergency".
webflow-incident-runbook
Execute Webflow incident response — triage by HTTP status (401/403/429/500), circuit breaker activation, cached fallback, Webflow status page checks, communication templates, and postmortem process. Trigger with phrases like "webflow incident", "webflow outage", "webflow down", "webflow on-call", "webflow emergency", "webflow broken".
vercel-incident-runbook
Vercel incident response procedures with triage, instant rollback, and postmortem. Use when responding to Vercel-related outages, investigating production errors, or running post-incident reviews for deployment failures. Trigger with phrases like "vercel incident", "vercel outage", "vercel down", "vercel on-call", "vercel emergency", "vercel broken".
veeva-incident-runbook
Veeva Vault incident runbook for enterprise operations. Use when implementing advanced Veeva Vault patterns. Trigger: "veeva incident runbook".
vastai-incident-runbook
Execute Vast.ai incident response for GPU instance failures and outages. Use when responding to instance failures, investigating training crashes, or handling spot preemption emergencies. Trigger with phrases like "vastai incident", "vastai outage", "vastai down", "vastai emergency", "vastai instance failed".
twinmind-incident-runbook
Incident response for TwinMind failures: transcription not starting, audio not captured, sync failures, and calendar disconnect. Use when implementing incident runbook, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind incident runbook", "twinmind incident runbook".
supabase-incident-runbook
Execute Supabase incident response: dashboard health checks, connection pool status, pg_stat_activity queries, RLS debugging, Edge Function logs, storage health, and escalation. Use when responding to Supabase outages, investigating production errors, debugging connection issues, or preparing evidence for Supabase support escalation. Trigger: "supabase incident", "supabase outage", "supabase down", "supabase on-call", "supabase emergency", "supabase broken", "supabase connection issues".
speak-incident-runbook
Incident response for Speak API outages: triage, fallback to offline mode, and recovery procedures. Use when implementing incident runbook, or managing Speak language learning platform operations. Trigger with phrases like "speak incident runbook", "speak incident runbook".
snowflake-incident-runbook
Execute Snowflake incident response with triage, rollback, and postmortem using real SQL diagnostics. Use when responding to Snowflake outages, investigating query failures, or running post-incident reviews for pipeline failures. Trigger with phrases like "snowflake incident", "snowflake outage", "snowflake down", "snowflake on-call", "snowflake emergency".
shopify-incident-runbook
Execute Shopify incident response with triage using Shopify status page, API health checks, and rate limit diagnosis. Trigger with phrases like "shopify incident", "shopify outage", "shopify down", "shopify on-call", "shopify emergency", "shopify not responding".
sentry-incident-runbook
Execute incident response procedures using Sentry error monitoring. Use when investigating production outages, triaging error spikes, classifying incident severity, or building postmortem reports from Sentry data. Trigger with phrases like "sentry incident", "sentry triage", "investigate sentry error", "sentry runbook", "production incident sentry".