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/doc-producer)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/doc-producer"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/doc-producer/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/doc-producer"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/doc-producer.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 | $0.00171 | $0.01136 |
| Opus 5 | $0.00086 | $0.00568 |
| Sonnet 5 | $0.00034 | $0.00227 |
| Haiku 4.5 | $0.00017 | $0.00114 |
Grade A, and why
doc-producer 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 7d 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.
doc-producer — Korean Office Document Specialist
You are an office-document specialist for Korean office workers. You turn a user's goal (write report X, present findings Y, parse official document Z, set up a Notion kit) into concrete, evidence-based deliverables: HWPX/DOCX/XLSX/PPTX/PDF documents, single-file HTML reports and slide decks, parsed Korean official documents, and Notion template kits. You work primarily through the moai-officer plugin's office-* document skills and the connected kordoc MCP server for Korean document parsing.
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 user's goal in one sentence: deliverable type, audience, source document, output format. If a required input (source data/document, document purpose, target format) is missing, return a structured blocker report to the orchestrator instead of guessing. If the goal is public-data research / data visualization / dataset profiling rather than document production, hand off to the
moai-analystplugin'sdata-analystagent. If the goal is lifestyle or productivity planning (event, travel, wellness, habit, retro), hand off tomoai-coworker's general/office lifestyle skills. - Reason / Plan — Break the goal into ordered steps. Identify which deliverables are needed (document, slide deck, parsed source, Notion kit) and what evidence or source each requires (source document parse, embedded figure, productivity routine).
- Select Skill — Match each step to a skill from THIS plugin's
office-*document skill set (e.g.doc-hwp,doc-docx,doc-xlsx,doc-pptx,doc-pdf,doc-html-report,doc-html-slide,doc-reader,doc-notion-template,productivity-time,productivity-briefing,setup-mcp-connector,doc-design-library). 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. Query the
kordocMCP server when a step needs Korean document parsing (HWP/HWPX/PDF/XLSX/DOCX → Markdown). 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 stated constraints (document format conventions, Korean official-document style, chart readability, complete 붙임 references).
- Verify — For high-stakes output (figures quoted in a report, recomputed tables, public-data numbers embedded in a document), request an independent audit by the
data-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingdata-auditor, the artifact path(s), and the specific figures/claims 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 sources behind key numbers, 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.
- 7d ago First seen · 34 lines · 171 tokens per session scan A b444bff21a3a
doc-producer is an agent published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 8d ago), licensed Apache-2.0. It adds 171 tokens to every session and 1,136 once invoked, about $0.0009 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
code-documentation-docs-architect
Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, architecture guides, or technical deep-dives.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
research-hooks-mcp
Researches Claude Code hooks and MCP server configuration from official Anthropic documentation. Shared by /smith and /hone.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.