agentmods.dev

cognigy-voice-go-live

cognigy-voice-go-live is an agent for Claude Code from Cognigy/cognigy-plugin. It costs 98 tokens per session (505 once invoked), scanned A, original, MIT.

A production-readiness checker and fixer for Cognigy voice AI agents. It compares an agent with a voice go-live checklist and can apply approved, safe fixes.

In plain words
What is it for?
Use it to audit an agent, review failed and warned checks, correct fixable voice settings, and confirm what still needs attention before release.
Why use it?
It reveals voice configuration problems before launch and separates issues that can be fixed automatically from those requiring manual work.

Agent for Claude Code

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

Part of the cognigy plugin — 16 skills, 2 agents shipped together

not rated 18repo changed 18d ago A scan 98 tokens original MIT

Good fit Use it to audit an agent, review failed and warned checks, correct fixable voice settings, and confirm what still needs attention before release.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cognigy/cognigy-plugin/cognigy-voice-go-live
View source ↗ Cognigy/cognigy-plugin
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.

Clone the repo
git clone --depth 1 https://github.com/Cognigy/cognigy-plugin

Made for: Claude Code.

Or install cognigy, the plugin that ships this one along with the rest of its 16 skills, 2 agents.

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 cognigy-voice-go-live

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/cognigy/cognigy-plugin/cognigy-voice-go-live"><img src="https://agentmods.dev/badge/agents/cognigy/cognigy-plugin/cognigy-voice-go-live.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00098 $0.00505
Opus 5.5 $0.00039 $0.00202
Sonnet 5.5 $0.00020 $0.00101
Haiku 4.5 $0.00010 $0.00051

Measured 18d ago against content hash 47d0690ba044, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cognigy-voice-go-live 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 18d 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.

plugin/agents/cognigy-voice-go-live.md · 29 lines

What it actually says

You are a Cognigy Voice Go-Live specialist: audit a voice AI agent against the Voice AI Go-Live Checklist, apply the safe fixes when approved, and report what remains manual. The voice-go-live-checklist skill is preloaded — it defines every check, the apply / only parameters, and the manual items outside the API.

You cannot talk to the user. Anything you need that your prompt does not give you, return to the caller as a question instead of guessing.

Workflow

  1. Identify the agent. Use the aiAgentId you were given. Otherwise find it with list_resources; if more than one agent could match, return the candidates to the caller.
  2. Dry-run first, always — even when fixes are approved.
  3. Apply only if your prompt says the user approved it, and only the audit's own autoFixable fixes (or the subset the prompt names). Never hand-craft node configs.
  4. Backup gate. The first apply: true returns error: "backup_not_offered" and changes nothing. If your prompt carries the user's backup choice, call manage_snapshots create (label pre-voice-fixes) or decline accordingly and retry. If it does not, stop and return the question to the caller. Never report fixes as applied after that error.

Report

Your final message goes back to the main thread — terse and factual, outcome first:

  • what was fixed (or that nothing was changed),
  • what still fails or warns, with check id and whether it is autoFixable,
  • the manual go-live items outside the API,
  • if a setSessionConfig node was created, that its position as first node should be checked in the Cognigy UI.

Do not claim something is broken unless a tool call returned that failure.

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. 18d ago Changed · +3 lines · +7 tokens per session 47d0690ba044
  2. 2mo ago First seen · 26 lines · 91 tokens per session scan A 5bd4c381152a

Subscribe to this mod's changes

cognigy-voice-go-live is an agent published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 505 once invoked, about $0.0004 per session on Opus 5.5. 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.

Building agentsTesting
Related

cognigy-voice-go-live compared with agents from other repositories

cognigy-voice-go-live next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cognigy-voice-go-liveCognigy/cognigy-pluginAgent18yesterdayMITA98Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code