What is voicelink-debug?

A troubleshooting command for VoiceLink phone calls connected to Dograh. It checks the provider registration, public secure WebSocket connection, reverse-proxy setup, phone-number format, credentials, and inbound routing.

Use it to diagnose registration errors, unreachable WSS URLs, failed outbound calls, expired credentials, WebSocket upgrade problems, and inbound call-routing issues.

It narrows a call failure to the first broken connection or configuration layer instead of relying on guesswork.

voicelink-debug — Command for Claude Code by Harddiikk

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Harddiikk/dograh-voicelink-plugin

Claude Code

/plugin install dograh-voicelink-plugin

Made for: Claude Code.

Or install dograh-voicelink-plugin, the plugin that ships this one along with the rest of its 1 skill, 4 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/harddiikk/dograh-voicelink-plugin/voicelink-debug/github.svg)](https://agentmods.dev/commands/harddiikk/dograh-voicelink-plugin/voicelink-debug)

Your own site

<a href="https://agentmods.dev/commands/harddiikk/dograh-voicelink-plugin/voicelink-debug"><img src="https://agentmods.dev/badge/commands/harddiikk/dograh-voicelink-plugin/voicelink-debug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/harddiikk/dograh-voicelink-plugin/voicelink-debug"><img src="https://agentmods.dev/badge/commands/harddiikk/dograh-voicelink-plugin/voicelink-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 912 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.00912
Opus 5	$0.00019	$0.00456
Sonnet 5	$0.00008	$0.00182
Haiku 4.5	$0.00004	$0.00091

Measured 4d ago against content hash 588c911e4b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

voicelink-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/voicelink-debug.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voicelink-debug

Systematically diagnose VoiceLink calling on Dograh. Be evidence-driven: run a check, read the actual output, then decide. Full detail in references/debugging.md.

Triage order (stop at the first failing layer)

Is the provider registered? bash "${CLAUDE_PLUGIN_ROOT}/scripts/verify.sh" <base-url> → expect health 200 and a 101 on /api/v1/telephony/ws. 404 = overlay not applied / api not restarted.
Is the WSS URL real and reachable? BACKEND_API_ENDPOINT must be a public https:// origin → derived wss://. A ws:// (localhost) URL means VoiceLink can't connect. Confirm the reverse proxy (Caddy/nginx) passes the WebSocket upgrade on /api/v1/telephony/ws.
Outbound fails immediately? Read the api logs for the add_lead payload. customer_number must be bare 10-digit (carrier rejects 91-prefixed customer numbers, Q.850 cause 38). The did_number comes from the per-call from_number and is required by VoiceLink's add_lead — if initiate_call raises ValueError about a missing from_number, bind a DID / phone number to the campaign. Check credentials validate (bearer_token OR username+password). A 401 with bearer-only config means the token expired and there's no username/password to re-login.
Inbound not routing? Read the logged raw start frame (VoiceLink INBOUND start frame (raw): …). Confirm a telephony_phone_numbers row exists for the normalized called DID, is_active=true, with an inbound_workflow_id. Inbound start-frame field names are "unconfirmed upstream" — if the DID isn't being picked up, compare the logged frame to what the handler reads and adjust providers/voicelink/routes.py (pick(...)), then add a regression test.
Audio is silent / one-way / robotic? Codec is G.711 A-law @ 8 kHz (not mu-law). For quiet inbound audio (common on Indian carriers starving VAD/ASR), raise VOICELINK_INBOUND_GAIN (live-tunable, no rebuild). Check the serializer RMS log (~1/sec).

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago Changed · +4 lines 588c911e4b12
9d ago First seen · 56 lines · 39 tokens per session scan A 90468a9a8139

Subscribe to this mod's changes

voicelink-debug is a command published in the GitHub repository Harddiikk/dograh-voicelink-plugin (9 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 912 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Debugging

voicelink-debug

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/voicelink-debug

Triage order (stop at the first failing layer)

What this file has done since we first saw it

Other commands, from other repositories

cloudflare-durable-objects:debug

cloudflare-durable-objects:optimize

doctor

api

optimize-code

errors