What is document-docx?

A toolkit for creating, editing, reviewing, and extracting content from DOCX files, the format used by Microsoft Word.

Use it to generate or edit reports, contracts, proposals, and other Word documents.

It provides structured ways to handle Word documents, including styles, templates, comments, and content extraction.

document-docx — Skill for Claude Code and Codex by vasilyu1983

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.

Any agent

npx skills add vasilyu1983/AI-Agents-public --skill document-docx

Clone the repo

git clone --depth 1 https://github.com/vasilyu1983/AI-Agents-public

Made for: Claude Code, Codex.

Or install ai-agents, the plugin that ships this one along with the rest of its 144 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/document-docx/github.svg)](https://agentmods.dev/skills/vasilyu1983/ai-agents-public/document-docx)

Your own site

<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/document-docx"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/document-docx/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/document-docx"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/document-docx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,336 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. Third-party audits

Socket warn 23 Sept 2026
Snyk warn 23 Sept 2026
NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.02336
Opus 5.5	$0.00018	$0.00934
Sonnet 5.5	$0.00009	$0.00467
Haiku 4.5	$0.00004	$0.00234

Measured 20d ago against content hash 6e25e2100e1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

document-docx 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 20d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/docx_extract.py, scripts/docx_inspect_ooxml.py, scripts/docx_quality_gate.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/universal/document-docx/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document DOCX Skill - Quick Reference

This skill covers the specialist .docx lanes: docxtpl template pipelines, python-docx structural edits and extraction, LLM/RAG ingestion, and accessibility/EAA compliance.

Boundary: when the official Anthropic docx skill is available, prefer it for plain create/edit (docx-js), tracked-change (redline) authoring via <w:ins>/<w:del> with validate.py, and comment authoring. When the user asks for "a document" without naming a format and a document connector or artifact type is available, prefer that over generating a .docx.

Core Decision Rules

Non-developers own the layout in Word, and code supplies data: docxtpl. Code decides the structure: python-docx (Python) or docx (Node).
Render templates fail-closed. docxtpl's defaults render a missing variable as blank and insert &/< unescaped, so the file opens fine and passes a tag scan. Use scripts/docx_render_template.py (StrictUndefined + autoescape); see references/template-workflows.md.
Tracked changes: never promise high-level library support, and never fake redlines with colour or strikethrough. Route authoring to the official docx skill's OOXML workflow. See references/tracked-changes.md.
Semantic HTML from a trusted file: mammoth, then sanitise (it does no sanitisation). Markdown/JSON for RAG: a Markdown converter or scripts/docx_extract.py; see references/llm-extraction-workflows.md.
DOCX feeding a KB or index: tables inside content controls are silently missing from Document.tables, tables pasted as images have no text, tracked changes need an explicit accept/original policy, and filenames can lie. Run the table-count detection check in references/docx-extraction-failure-modes.md before indexing any file (load it whenever DOCX is ingestion input).
PDF output: Word automation for the highest fidelity; LibreOffice headless for CI and batch.
.doc: convert to .docx first. .docm/.dotm: treat the macros as untrusted and never execute them.
.docx is the editable source; PDF is the release artifact.

Read the full file on GitHub · 113 lines

Files

What ships with it

22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

20d ago Changed · -147 lines · +6 tokens per session 6e25e2100e1e
1mo ago Changed · +4 lines e345a436ea33
1mo ago First seen · 256 lines · 38 tokens per session scan A 929c7c665254

Subscribe to this mod's changes

document-docx is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 10d ago), licensed MIT. It adds 44 tokens to every session and 2,336 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 2026-08-30.

Documents agent-skills agentic-ai ai-agents anthropic chatgpt-prompts claude

upload-artifact

Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload…

closedloop-ai/claude-plugins · 103 tokens

extract-plan-md

Sync plan.md with plan.json content. MUST be used after ANY edit to plan.json to keep plan.md in sync. Triggers: After editing plan.json with Edit tool (REQUIRED - always sync after edits) User asks to "sync plan.md", "update plan.md", "extract the md from a plan" Converting plan.json to markdown or viewing plan as…

closedloop-ai/claude-plugins · 99 tokens

atlas-report

Render agent findings as a styled HTML report in the browser. Use when asked for "full report", "detailed report", "show in browser", or when CLI output exceeds the 40-line budget.

tonone-ai/tonone · 44 tokens

xlsx

Create, read and edit Microsoft Excel .xlsx spreadsheets — data tables, formulas, multiple sheets, number formats, conditional formatting, charts, frozen panes and named ranges. Also covers reading an existing workbook to extract values or formulas, recalculating formulas so cached values are correct, converting to…

smith-network-solutions/threadknot · 84 tokens

docx

Create, read and edit Microsoft Word .docx documents — reports, letters, contracts, formatted multi-section documents with headings, tables, images, headers/footers and styles. Also covers reading an existing .docx to extract or modify its content, filling a .docx template, converting to PDF, and the raw OOXML route…

smith-network-solutions/threadknot · 102 tokens

pdf

Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…

smith-network-solutions/threadknot · 88 tokens