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.
npx skills add Cognigy/cognigy-plugin --skill voice-go-live-checklistgit 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/skills/cognigy/cognigy-plugin/voice-go-live-checklist)<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/voice-go-live-checklist"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/voice-go-live-checklist/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/skills/cognigy/cognigy-plugin/voice-go-live-checklist"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/voice-go-live-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 37 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 50 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 68 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00051 | $0.01486 |
| Opus 5.5 | $0.00020 | $0.00594 |
| Sonnet 5.5 | $0.00010 | $0.00297 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
voice-go-live-checklist 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 2mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Go-Live Checklist Guide
audit_voice_agent checks a voice AI agent against the deterministic subset of the Voice AI guidebook Go-Live Checklist (section 3) and can apply safe fixes. It reads the flow chart (and optionally the endpoint and LLM) over the Cognigy REST API, so it only covers what the API can both read and change. Speech-provider status, failover behaviour, and release-readiness items live in the external Voice Gateway app or are runtime/operational — those are manual and out of scope.
Quick start
1. Dry-run report (no changes):
audit_voice_agent { aiAgentId }
audit_voice_agent { aiAgentId, endpointId, projectId } // also checks Output Transformer + fallback LLM
2. Apply all safe fixes:
audit_voice_agent { aiAgentId, apply: true }
3. Apply a subset:
audit_voice_agent { aiAgentId, apply: true, only: ["vg.barge-in-off", "agent.stream-output"] }
- Provide
aiAgentId(the flow is resolved for you) orflowIddirectly. endpointIdenables the Output Transformer check.projectIdenables the fallback-LLM check.- Dry-run is the default. Nothing changes unless you pass
apply: true.
How it resolves things
- Flow: from
aiAgentId(same resolution as the other agent tools) or theflowIdyou pass. - Set Session Config node: the first chart node of type
setSessionConfig. - AI Agent node: the chart node of type
aiAgentJob. - Endpoint / LLM: only fetched when
endpointId/projectIdare supplied.
Statuses
| Status | Meaning |
|---|---|
pass |
Meets the recommended setting. |
fail |
Deviates from the recommended default. Usually auto-fixable. |
warn |
Advisory — needs human judgement (e.g. hint content), not auto-fixed. |
na |
Not applicable / not enough data (e.g. no Set Session Config node yet, or no endpointId). |
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.
- 2mo ago First seen · 86 lines · 51 tokens per session scan A 4786542d158b
voice-go-live-checklist is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,486 once invoked, about $0.0002 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.
voice-go-live-checklist compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| voice-go-live-checklistCognigy/cognigy-plugin | Skill | 18 | yesterday | MIT | A | 51 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |