Atlas / Skills / jeremylongshore / Deepgram Incident Runbook

Deepgram Incident RunbookSAFE

skills/jeremylongshore/deepgram-incident-runbook

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.13.0
Hosts
1 documented
License
MIT
Stars
2,823
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
03

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 =
04

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.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (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.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__deepgram-incident-runbook.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aSAFEB89first audit
06

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.

Advertisement