Deepgram Incident RunbookSAFE
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Overview
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
4f83675ca38aOBSERVED · 2026-10-08Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: deepgram-incident-runbook description: 'Execute Deepgram incident response procedures for production issues. Use when handling Deepgram outages, debugging production failures, or responding to service degradation. Trigger: "deepgram incident", "deepgram outage", "deepgram production issue", "deepgram down", "deepgram emergency", "deepgram 500 errors". ' allowed-tools: Read, Write, Edit, Bash(curl:*), Bash(kubectl:*) version: 1.13.0 license: MIT author: Jeremy Longshore <[email protected]> tags: - saas - deepgram - debugging - incident-response compatibility: Designed for Claude Code --- # Deepgram Incident Runbook ## Prerequisites - An incident ID, commander, affected service/environment, escalation route, and authorized redacted diagnostic access. - A data/consent owner and documented safe mitigation or rollback action. ## Examples For elevated transcription errors, declare scope, capture aggregate health and redacted correlation IDs, stabilize with the documented circuit-breaker/rollback, and verify recovery against the SLO. Escalate provider or data-impact incidents through the approved path; do not attach customer audio, transcripts, or credentials to the incident channel. ## Overview Standardized incident response for Deepgram-related production issues. Includes automated triage script, severity classification (SEV1-SEV4), immediate mitigation actions, fallback activation, and post-incident review template. ## Quick Reference | Resource | URL | |----------|-----| | Deepgram Status | https://status.deepgram.com | | Deepgram Console | https://console.deepgram.com | | Support Email | [email protected] | | Community | https://github.com/orgs/deepgram/discussions | ## Severity Classification | Level | Definition | Response Time | Example | |-------|------------|---------------|---------| | SEV1 | Complete outage, all transcriptions failing | Immediate | 100% 5xx errors | | SEV2 | Major degradation, >50% error rate | < 15 min | Specific model failing | | SEV3 | Minor degradation, elevated latency | < 1 hour | P95 > 30s | | SEV4 | Single feature affected, cosmetic | < 24 hours | Diarization inaccurate | ## Instructions ### Step 1: Automated Triage (First 5 Minutes) ```bash #!/bin/bash set -euo pipefail echo "=== Deepgram Incident Triage ===" echo "Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ)" echo "" # 1. Check Deepgram status page echo "--- Status Page ---" STATUS=$(curl -s -o /dev/null -w "%{http_code}" https://status.deepgram.com) echo "Status page: HTTP $STATUS" # 2. Test API connectivity echo "" echo "--- API Connectivity ---" curl -s -w "\nHTTP: %{http_code} | Latency: %{time_total}s\n" \ 'https://api.deepgram.com/v1/projects' \ -H "Authorization: Token $DEEPGRAM_API_KEY" | head -5 # 3. Test transcription echo "" echo "--- Transcription Test ---" RESULT=$(curl -s -w "\n%{http_code}" \ -X POST 'https://api.deepgram.com/v1/listen?model=nova-3&smart_format=true' \ -H "Authorization: Token $DEEPGRAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav"}') HTTP_CODE=$(echo "$RESULT" | tail -1) echo "Transcription: HTTP $HTTP_CODE" # 4. Test multiple models echo "" echo "--- Model Tests ---" for MODEL in nova-3 nova-2 base; do CODE=$(curl -s -o /dev/null -w "%{http_code}" \ -X POST "https://api.deepgram.com/v1/listen?model=$MODEL" \ -H "Authorization: Token $DEEPGRAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav"}') echo "$MODEL: HTTP $CODE" done # 5. Query internal metrics (if available) echo "" echo "--- Internal Metrics ---" curl -s localhost:3000/health 2>/dev/null || echo "Health endpoint unavailable" ``` ### Step 2: SEV1 Response (Complete Outage) ```typescript import { createClient } from '@deepgram/sdk'; class DeepgramFallbackService { private primaryClient: ReturnType<typeof createClient>; private isInFallbackMode = false; private failedRequests: Array<{ url: string; options: any; timestamp: Date }> = []; constructor(apiKey: string) { this.primaryClient = createClient(apiKey); } async transcribe(url: string, options: any) { if (this.isInFallbackMode) { return this.handleFallback(url, options); } try { const { result, error } = await this.primaryClient.listen.prerecorded.transcribeUrl( { url }, options ); if (error) throw error; return { source: 'deepgram', result }; } catch (err) { console.error('Deepgram failed, entering fallback mode'); this.isInFallbackMode = true; return this.handleFallback(url, options); } } private handleFallback(url: string, options: any) { // Queue for later replay this.failedRequests.push({ url, options, timestamp: new Date() }); console.warn(`Queued for replay: ${url} (${this.failedRequests.length} in queue)`); return { source: 'fallback', message: 'Transcription queued — Deepgram is currently unavailable', queuePosition: this.failedRequests.length, }; } // Call when Deepgram recovers async replayQueue() { console.log(`Replaying ${this.failedRequests.length} queued requests...`); const queue = [...this.failedRequests]; this.failedRequests = []; this.isInFallbackMode = false; for (const req of queue) { try { await this.transcribe(req.url, req.options); console.log(`Replayed: ${req.url}`); } catch (err: any) { console.error(`Replay failed: ${req.url} — ${err.message}`); this.failedRequests.push(req); } } } } ``` ### Step 3: SEV2 Response (Partial Degradation) ```typescript async function mitigateSev2() { const client = createClient(process.env.DEEPGRAM_API_KEY!); const testUrl = 'https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav'; console.log('=== SEV2 Mitigation =
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__deepgram-incident-runbook.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 4f83675ca38a | SAFE | B | 89 | first audit |
Questions
What does the Deepgram Incident Runbook skill do?
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Is Deepgram Incident Runbook safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Deepgram Incident Runbook access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Deepgram Incident Runbook work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.