doc-producer

doc-producer is an agent for Claude Code from modu-ai/moai-cowork. It costs 171 tokens per session (1,136 once invoked), scanned A, original, Apache-2.0.

An office-document specialist that turns a goal and source material into deliverables such as HWPX, DOCX, XLSX, PPTX, PDF, HTML reports, HTML slide decks, or Notion templates. It can also parse Korean official documents.

In plain words
What is it for?
Use it to produce Korean office documents, presentations, reports, spreadsheets, parsed official documents, and structured Notion workspaces from provided requirements and evidence.
Why use it?
It helps choose and coordinate the right document workflow when the user knows the outcome they need but not the file format or production steps.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the moai-officer plugin — 13 skills, 2 agents shipped together

Good fit Use it to produce Korean office documents, presentations, reports, spreadsheets, parsed official documents, and structured Notion workspaces from provided requirements and evidence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/modu-ai/moai-cowork/doc-producer
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/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-officer, the plugin that ships this one along with the rest of its 13 skills, 2 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 doc-producer

README.md
[![agentmods](https://agentmods.dev/badge/agents/modu-ai/moai-cowork/doc-producer/github.svg)](https://agentmods.dev/agents/modu-ai/moai-cowork/doc-producer)
Your own site
<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.

agentmods 80×15 button for doc-producer

Your own site · 80×15
<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>
Per session 171 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,136 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 $0.00171 $0.01136
Opus 5 $0.00086 $0.00568
Sonnet 5 $0.00034 $0.00227
Haiku 4.5 $0.00017 $0.00114

Measured 7d ago against content hash b444bff21a3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

plugins/moai-officer/agents/doc-producer.md · 34 lines

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:

  1. 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-analyst plugin's data-analyst agent. If the goal is lifestyle or productivity planning (event, travel, wellness, habit, retro), hand off to moai-coworker's general/office lifestyle skills.
  2. 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).
  3. 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.
  4. Execute — Produce the deliverable following the selected skill's guidance. Query the kordoc MCP 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.
  5. 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).
  6. 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-auditor agent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator naming data-auditor, the artifact path(s), and the specific figures/claims to verify, then incorporate the audit findings on re-delegation.
  7. 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.

Read the full file on GitHub · 34 lines

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. 7d ago First seen · 34 lines · 171 tokens per session scan A b444bff21a3a

Subscribe to this mod's changes

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.