A toolkit for creating, inspecting, and editing Microsoft Word .docx documents while preserving their internal formatting.

It helps create new Word files, revise existing ones, add comments, and make careful low-level changes when ordinary document conversion could lose formatting.

It reduces the risk of damaging existing document layout, comments, or other Word features during edits.

docx — Skill for Claude Code by HybridAIOne/hybridclaw

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/HybridAIOne/hybridclaw

agentmods

npx agentmods add skills/hybridaione/hybridclaw/docx

Made for: Claude Code.

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/hybridaione/hybridclaw/docx/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/docx)

Your own site

<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/docx"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/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/hybridaione/hybridclaw/docx"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/docx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 839 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

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	$0.00025	$0.00839
Opus 5.5	$0.00010	$0.00336
Sonnet 5.5	$0.00005	$0.00168
Haiku 4.5	$0.00003	$0.00084

Measured 27d ago against content hash 79bd75df9238, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 27d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/accept_changes.cjs, scripts/comment.cjs), 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/docx/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DOCX

Use this skill whenever the user asks to create, revise, comment on, or inspect a .docx document.

Default Workflow

For new documents with straightforward structure, write Markdown first and convert it with pandoc.
For programmatic creation, write a CommonJS .cjs script and use require("docx"). The container exposes global Node packages through NODE_PATH; avoid bare ESM import "docx" examples.
For editing an existing .docx, never round-trip the original file through docx or pandoc. Unpack the OOXML, edit the XML you need, and repack it.

Existing-File Editing Workflow

node skills/office/unpack.cjs input.docx tmp/docx-edit
node skills/office/validate.cjs tmp/docx-edit
node skills/office/pack.cjs tmp/docx-edit output.docx

Edit only the relevant parts under tmp/docx-edit/word/:

document.xml for the main body
styles.xml for styles
numbering.xml for list definitions
header*.xml / footer*.xml for page furniture
_rels/*.rels when you add new parts

Rules

Preserve existing formatting by editing OOXML directly for in-place revisions.
Escape XML-sensitive characters (&, <, >) and preserve xml:space="preserve" when surrounding spaces matter.
Use DXA table widths and explicit cell widths instead of percentages when layout must survive Word and Google Docs.
Keep relationship ids, comment ids, and content-type overrides consistent when adding parts.
Never write plain text or placeholder text directly to a .docx file path. If generation fails, stop and report the error.

Comments And Reviews

Use node skills/docx/scripts/comment.cjs --help to insert a comment around an exact text match inside an unpacked DOCX tree.
Use node skills/docx/scripts/accept_changes.cjs /tmp/docx-edit --json to accept straightforward tracked changes after unpacking.
The helper currently targets word/document.xml. For complex tracked changes, nested fields, or multi-run matches, edit the OOXML manually after unpacking.

Read the full file on GitHub · 103 lines

Files

What ships with it

2 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.

27d ago Changed · +4 lines 79bd75df9238
1mo ago Changed · +4 lines b99fdf73bc14
2mo ago First seen · 95 lines · 25 tokens per session scan A 03d5ac6b3d29

Subscribe to this mod's changes

docx is a skill published in the GitHub repository HybridAIOne/hybridclaw (159 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 839 once invoked, about $0.0001 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 RAG and vectors ai enterprise-ai gdpr local-llm proactive-agent

docx next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
docxHybridAIOne/hybridclaw	Skill	159	yesterday	MIT	A	25	Claude Code
markitdownK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	62	Claude Code, Codex
docxHKUDS/DeepTutor	Skill	55k	yesterday	Apache-2.0	A	91	Claude Code, Codex
xlsxHKUDS/DeepTutor	Skill	55k	yesterday	Apache-2.0	A	88	Claude Code, Codex
surfsense-dataMODSetter/SurfSense	Skill	17k	yesterday	Apache-2.0	A	0	Claude Code, Codex
surfsense-htmlMODSetter/SurfSense	Skill	17k	yesterday	Apache-2.0	A	89	Claude Code, Codex
xberg-extracting-tablesxberg-io/xberg	Skill	9.5k	yesterday	MIT	A	36	Claude Code