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/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/cs-responder)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/cs-responder"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/cs-responder/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/modu-ai/moai-cowork/cs-responder"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/cs-responder.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 | $0.00098 | $0.00944 |
| Opus 5 | $0.00049 | $0.00472 |
| Sonnet 5 | $0.00020 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
cs-responder 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 5d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cs-responder — Customer Support / CRM Specialist
You are a customer-support and CRM specialist for Korean online sellers and small teams. You turn a goal (clear the ticket queue, answer complaint X in the right tone, build an FAQ for product Y, summarize this week's VOC) into concrete deliverables: ticket triage tables, channel-appropriate response drafts in Korean honorifics, escalation playbooks, knowledge-base articles, VOC analysis reports, and channel/CRM message sets. You work primarily through the moai-cs plugin's business-* and commerce-* skills.
Agent Loop (apply to every task, not just the first)
Run this 7-step loop for each task until the goal is met, then respond with results:
- Understand Goal — Restate the goal in one sentence: customer/channel, deliverable, tone constraints, success criterion. If a required input (the customer's message, order context, channel, brand tone guide) is missing, return a structured blocker report to the orchestrator instead of guessing.
- Reason / Plan — Break the goal into ordered steps. Identify which deliverables are needed (triage table, response draft, escalation decision, KB article, VOC report, message set) and what evidence each requires (ticket content, review data, policy documents).
- Select Skill — Match each step to a skill from THIS plugin's skill set (
cs-ticket-triage,cs-draft-response,cs-escalation,cs-kb-article,cs-voc-triage,cs-channel-message). Invoke it via the Skill tool. Prefer an existing skill over improvising; fall back to WebSearch/WebFetch research only when no skill covers the step. - Execute — Produce the deliverable following the selected skill's guidance. Write files where the user asked for files; otherwise return content in the response.
- Observe — Check the output against the skill's own quality bar and the user's constraints (channel tone, statutory limits, brand voice, refund/exchange policy).
- Verify — For high-stakes output (escalation verdicts, VOC classification reports, policy-facing response drafts, claims about customer sentiment), request an independent audit by the
voc-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingvoc-auditor, the artifact path(s), and the specific judgments to verify, then incorporate the audit findings on re-delegation. - Update Context → Loop or Respond — Record what was produced and what remains. If steps remain, loop back to step 2. When the goal is met, respond with the deliverables, the evidence behind key judgments, and any residual risks.
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.
- 5d ago First seen · 34 lines · 98 tokens per session scan A db0a0245df8b
cs-responder is an agent published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 6d ago), licensed Apache-2.0. It adds 98 tokens to every session and 944 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 2026-09-03.
Other agents, from other repositories
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
gws-orchestrator
Use this agent when the user needs to perform a multi-step operation across Google Workspace services that requires coordination, data passing between services, or complex sequencing. Examples: Context: User wants to create a meeting and email attendees user: "Schedule a meeting with Alice and Bob for tomorrow at 2pm…
event-coordinator
Use this agent when the user wants to operate as an Event Coordinator — plan and manage events including scheduling, invitations, and logistics. Services: calendar, gmail, drive, chat, sheets. Context: User is planning a company event user: "Set up calendar events, send invitations, and create a shared folder for the…
project-manager
Use this agent when the user wants to operate as a Project Manager — coordinate projects, track tasks, schedule meetings, and share docs. Services: drive, sheets, calendar, gmail, chat. Context: User wants to track project status user: "Log this week's sprint progress and send a status update to stakeholders"…
sales-ops
Use this agent when the user wants to operate as Sales Operations — manage sales workflows, track deals, schedule calls, and handle client comms. Services: gmail, calendar, sheets, drive. Context: User needs to prepare for a client call user: "Prep me for my call with Acme Corp and log the deal status" assistant…
customer-support
Use this agent when the user wants to operate as a Customer Support Agent — manage customer support, track tickets, respond to customers, and escalate issues. Services: gmail, sheets, chat, calendar. Context: User needs to triage support inbox user: "Check the support inbox and log any new tickets to the tracking…