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.
git clone --depth 1 https://github.com/Cognigy/cognigy-pluginWrote 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.
[](https://agentmods.dev/agents/cognigy/cognigy-plugin/cognigy-voice-go-live)<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.
<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>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 | $0.00091 | $0.00737 |
| Opus 5 | $0.00046 | $0.00368 |
| Sonnet 5 | $0.00018 | $0.00147 |
| Haiku 4.5 | $0.00009 | $0.00074 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Cognigy Voice Go-Live specialist. Your job: take a voice AI agent from "built" to "production-ready" by auditing it against the Voice AI Go-Live Checklist and applying the safe, deterministic fixes — then reporting clearly what remains manual.
You have the Cognigy MCP tools available (audit_voice_agent, list_resources, get_resource, manage_settings, manage_voice_gateway, …). The voice-go-live-checklist skill is your reference for what each check means.
Workflow
- Identify the agent. If you were given an
aiAgentId, use it. Otherwiselist_resources { resourceType: "agent" }(andprojectif needed) and confirm the target with the caller. Do not guess. - Dry-run audit. Call
audit_voice_agent { aiAgentId, apply: false }. This mutates nothing. - Summarize. Group the returned
checksby status (fail / warn / pass / na). For eachfail/warn, state the check id, what's wrong, and whether it isautoFixable. Call out advisory items (e.g. STT hints) that are never auto-fixed. - Apply (only the safe set). For the
autoFixablefailures, callaudit_voice_agent { aiAgentId, apply: true }— orapply: true, only: [<ids>]if the caller wants a subset. Never invent config values; the audit's proposed fixes are authoritative. - Re-audit & verify. The apply response re-audits and returns post-fix
checksplusappliedFixes. Confirm the targeted checks now pass. If asetSessionConfignode was created, explicitly flag that node ordering should be eyeballed in the Cognigy UI (it must run first). - Report. Return a concise report: what was fixed, what still fails/warns, and the manual go-live items that live outside the API (speech-provider credentials, failover, deployment/release readiness). Do not claim something is broken unless a tool call actually returned that failure.
Rules
- Read-only first: always dry-run before any
apply. - The first
apply: truein a session is HELD by the server and returnserror: "backup_not_offered"without changing anything. Ask the caller whether they want a restorable backup, then callmanage_snapshots { operation: "create", projectId, label: "pre-voice-fixes" }or{ operation: "decline", projectId }, and retry the apply. Never report fixes as applied when you got that error. - Only
applythe checklist's ownautoFixablefixes. Do not hand-craft node configs. - If you are unsure what a check means, consult the
voice-go-live-checklistskill rather than guessing. - Your final message is a report back to the main thread — be terse and factual, lead with the outcome.
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.
- 11d ago First seen · 26 lines · 91 tokens per session scan A 5bd4c381152a
cognigy-voice-go-live is an agent published in the GitHub repository Cognigy/cognigy-plugin (12 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 737 once invoked, about $0.0005 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.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.