troubleshoot-voice-agents

troubleshoot-voice-agents is a skill for Claude Code from voicelogica/voice-logica-plugin. It costs 59 tokens per session (1,090 once invoked), scanned A, original, MIT.

A troubleshooting guide for Voice Logica phone calls and voice agents, using call records, live prompts, and tool logs to find what went wrong.

In plain words
What is it for?
Use it to investigate failed calls, missing tool actions, broken settings, expired subscriptions, phone connections, and oversized agent prompts.
Why use it?
It helps separate prompt, subscription, phone, permission, and tool problems from issues wrongly blamed on the language or speech-recognition model.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the voice-logica plugin — 17 skills, 1 MCP server shipped together

Good fit Use it to investigate failed calls, missing tool actions, broken settings, expired subscriptions, phone connections, and oversized agent prompts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add voicelogica/voice-logica-plugin --skill troubleshoot-voice-agents
Clone the repo
git clone --depth 1 https://github.com/voicelogica/voice-logica-plugin

Made for: Claude Code.

Or install voice-logica, the plugin that ships this one along with the rest of its 17 skills, 1 MCP server.

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.

agentmods badge for troubleshoot-voice-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents/github.svg)](https://agentmods.dev/skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents)
Your own site
<a href="https://agentmods.dev/skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents"><img src="https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents/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.

agentmods 80×15 button for troubleshoot-voice-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents"><img src="https://agentmods.dev/badge/skills/voicelogica/voice-logica-plugin/troubleshoot-voice-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,090 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01090
Opus 5 $0.00030 $0.00545
Sonnet 5 $0.00012 $0.00218
Haiku 4.5 $0.00006 $0.00109

Measured 12d ago against content hash be7389fc5ec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

troubleshoot-voice-agents 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 12d 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.

skills/troubleshoot-voice-agents/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Troubleshoot Voice Logica agents

Use MCP tools. Do not guess. Do not invent Call IDs, tool results, or plan features.

Do not start with the model

Call dumps may show model, temperature, or reasoningEffort. Those are usually platform defaults, not the customer's knobs. Only treat the model as relevant if the plan can select a model (can-select-model) or the company uses its own API keys.

Look at the prompt, tool prompts, whether the expected tool fired (toolCalls), plan features, and view/role gates first.

Expired / zero-second subscriptions look like random product bugs. get_subscription and the call endCallReason before debugging SIP or the prompt.

"Stopped working" first checks

  1. get_subscription — active? seconds remaining? Plan feature for the missing tab?
  2. Any Call IDs in the window? Zero → traffic never reached Voice Logica (manage-phones).
  3. Phone still registered? (get_voip_phones)
  4. Prompt size (get_agent_prompt) — approaching / above ~20k characters → extract facts to knowledge, do not add more rules (edit-voice-agents).
  5. Last change (prompt, transfer settings, integration, hours).

Prompt vs bug

Read the live prompt for that exact situation before agreeing it is a defect.

  • Agent broke an explicit rule: fix the mechanism. Check the rule is not already there (a violated rule is not a missing rule). Restating it eats system-prompt budget.
  • Agent followed an explicit rule: this is an SOP change, not a bug. Say so, then edit the rule if the user wants that.
  • Prompt is silent: agree the desired behavior, then write it.

A truncated agent line in a transcript does not prove the agent interrupted. Get the recording or call logs if interruption is the complaint.

If the agent speaks JSON / tool names / brackets, collect Call ID + timestamp and file a ticket. Do not prompt-paper over leaked system content.

Tools and tests

Scenario or judge fields like toolCalls[].succeeded are a model reading the transcript. The transcript often does not include tool responses. A tool can return HTTP 200 and still look failed there.

Read the full file on GitHub · 74 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.

  1. 12d ago First seen · 74 lines · 59 tokens per session scan A be7389fc5ec0

Subscribe to this mod's changes

troubleshoot-voice-agents is a skill published in the GitHub repository voicelogica/voice-logica-plugin (0 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 1,090 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

tauri-mcp-cli

Use the Tauri MCP CLI to start and recover driver sessions, automate Tauri webviews, capture UI state, debug IPC, and work with mobile or remote devices. Use whenever an agent needs to operate a Tauri v2 app from terminal commands.

hypothesi/mcp-server-tauri · 57 tokens

logic-review

Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…

hyhmrright/logic-lens · 161 tokens

logic-fix-all

Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic…

hyhmrright/logic-lens · 211 tokens

logic-health

Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…

hyhmrright/logic-lens · 180 tokens

build-until-pass

Use when a build, typecheck, lint, or test command is failing and you want the agent to drive it to green on its own — run the check, read the errors, apply the smallest fix, re-run, repeat until exit code 0. Stops the human from being the while-loop (run → read error → fix one line → run again) and stops the agent…

LichAmnesia/lich-skills · 93 tokens

debug-hypothesis

Use when debugging any non-trivial bug — wrong output, crash, flaky test, performance regression, or "it works locally but not in CI." Forces a scientific-method loop (Observe → Hypothesize → Experiment → Conclude) so the agent stops guessing and starts reasoning. Prevents the.

LichAmnesia/lich-skills · 64 tokens