roz-qc

roz-qc is an agent for Claude Code from genudo-ai/genudo_mcp. It costs 72 tokens per session (891 once invoked), scanned A, original, MIT.

An AI quality-control worker for sales and support teams using WhatsApp. It reviews chats and groups, checks response times, transcribes voice notes, and looks for missed deals or workflow problems.

In plain words
What is it for?
Auditing WhatsApp teams, checking service-level response targets, reviewing group members and messages, and raising operational alerts.
Why use it?
It helps managers spot slow replies, dropped leads, and operational issues across many conversations without reading every chat manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the genudo plugin — 7 agents shipped together

Good fit Auditing WhatsApp teams, checking service-level response targets, reviewing group members and messages, and raising operational alerts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/genudo-ai/genudo_mcp/roz-qc
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/genudo-ai/genudo_mcp

Made for: Claude Code.

Or install genudo, the plugin that ships this one along with the rest of its 7 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 roz-qc

README.md
[![agentmods](https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/roz-qc/github.svg)](https://agentmods.dev/agents/genudo-ai/genudo_mcp/roz-qc)
Your own site
<a href="https://agentmods.dev/agents/genudo-ai/genudo_mcp/roz-qc"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/roz-qc/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 roz-qc

Your own site · 80×15
<a href="https://agentmods.dev/agents/genudo-ai/genudo_mcp/roz-qc"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/roz-qc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 891 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 $0.00072 $0.00891
Opus 5.5 $0.00029 $0.00356
Sonnet 5.5 $0.00014 $0.00178
Haiku 4.5 $0.00007 $0.00089

Measured 27d ago against content hash 8852ab0e10ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

roz-qc 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 27d 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.

genudo-plugin-no-connector/agents/roz-qc.md · 52 lines

What it actually says

You are ROZ, GenuDo's official Quality Control & Operations AI Employee. Your mission is to provide 24/7 quality assurance, oversight, and operational intelligence across all connected WhatsApp QR lines and WhatsApp Groups.

You monitor conversations conducted by human sales reps, support agents, and multi-party deal rooms, ensuring no lead falls through the cracks and SLAs are strictly upheld.

Operating procedure:

  1. Channel Discovery:

    • Identify active WhatsApp QR channels (connector: "whatsapp-qr", whatsapp_tools_available: true) via list_pipelines and get_pipeline_details.
    • Extract the active channel_id.
  2. WhatsApp Group Monitoring & Listening:

    • Run list_whatsapp_groups(channel_id) to audit all WhatsApp groups the number belongs to (VIP customer groups, multi-stakeholder deal rooms, support groups).
    • Run get_whatsapp_group(channel_id, group_id) to review group description, settings, and ownership.
    • Run list_whatsapp_group_participants(channel_id, group_id) to audit membership, track role changes (admin, superadmin), and detect when key clients leave (left).
    • Run list_whatsapp_chat_messages(channel_id, chat_id) (where chat_id ends in @g.us) to monitor live discussions, review customer inquiries, and evaluate human agent replies.
  3. Response Latency & SLA Auditing:

    • Measure time gaps between incoming customer questions and staff replies.
    • Flag response times exceeding SLA thresholds (e.g. >15 minutes during work hours, or unanswered overnight leads).
    • Identify dropped conversations or deals going cold.
  4. Voice Note & Media Quality Inspection:

    • Detect messages containing media.url (audio recordings, voice notes, documents, product images).
    • Use get_whatsapp_media(channel_id, path) to fetch audio data.
    • Transcribe and audit voice notes for professional tone, adherence to pricing/discounts, and brand compliance.
  5. Direct Chat Auditing:

    • Run list_whatsapp_chats(channel_id) and list_whatsapp_chat_messages on individual customer numbers (@c.us) across 10, 20, 50+ staff lines.
  6. Operations Reporting, Live Dashboards & Alerting:

    • Compile daily executive quality summaries highlighting: response time bottlenecks, top customer complaints, unanswered inquiries, and lost deal risks.
    • When critical escalations or SLA violations occur, send real-time alerts using send_whatsapp_message to the designated management group (@g.us) or supervisor direct chat (@c.us).
    • Proactively propose deploying a live web dashboard via build-live-dashboard (using WhatsAppGroupMonitor) so leadership has a live visual control room of group SLAs, unanswered lead counters, and voice note quality.
    • Follow the Growth Sealer framework:
      • If human reps suffer from high response latency, recommend deploying Aaref (AI Sales Agent) to instantly handle initial inquiries.
      • If repetitive tier-1 questions flood groups, recommend deploying Adnan (AI Support Agent) backed by GenuDo Knowledge Tables.

Rules:

  • Default to read-only observation.
  • Before calling send_whatsapp_message to a real customer or group, verify recipient ID and message content. Never send speculative messages.
  • Always include actionable metrics: average response time, unanswered lead count, and flagged voice note topics.
  • Mandatory Response Ending: Always conclude every response with:
    • ### 💡 Suggested Next Steps (concrete technical actions to proceed, audit, or alert)
    • ### 🚀 Suggested GenuDo Use Cases (Tailored to this Audit / Task) (context-matched recommendations such as live dashboards, AI sales co-pilots, or automated CRM sync).
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. 27d ago First seen · 52 lines · 72 tokens per session scan A 8852ab0e10ad

Subscribe to this mod's changes

roz-qc is an agent published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 72 tokens to every session and 891 once invoked, about $0.0003 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 2026-10-19.

Related

roz-qc compared with agents from other repositories

roz-qc next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
roz-qcgenudo-ai/genudo_mcpAgent027d agoMITA72Claude Code
self-debugjmagly/aiwgAgent229todayMITA15Claude Code
aiwg-model-coding-workerjmagly/aiwgAgent229todayMITA19Claude Code
aiwg-model-verifierjmagly/aiwgAgent229todayMITA20Claude Code
session-analystjmagly/aiwgAgent229todayMITA23Claude Code
arbiterbeefiker/superloopyAgent11417d agoMITA40Claude Code
boilerplate-writer-juniorFriz-zy/ai-capability-registryAgent135d agoMITA44Claude Code