docx-handler

docx-handler is a skill for Claude Code from bjorn-ingmanson/thefroject-plugins. It costs 52 tokens per session (643 once invoked), scanned A, original, MIT.

A tool for reading, editing, and creating Microsoft Word files in the .docx format, including converting content from Markdown, a plain-text formatting system.

In plain words
What is it for?
Extracting document content, generating Word reports from Markdown, and applying tracked-change-style edits to existing files.
Why use it?
It avoids manually copying document text and helps preserve headings, lists, tables, styles, and targeted edits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the thefroject-customer-success plugin — 47 skills, 11 commands shipped together

Good fit Extracting document content, generating Word reports from Markdown, and applying tracked-change-style edits to existing files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bjorn-ingmanson/thefroject-plugins/docx-handler
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 bjorn-ingmanson/thefroject-plugins --skill docx-handler
Clone the repo
git clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-plugins

Made for: Claude Code.

Or install thefroject-customer-success, the plugin that ships this one along with the rest of its 47 skills, 11 commands.

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 docx-handler

README.md
[![agentmods](https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/docx-handler/github.svg)](https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/docx-handler)
Your own site
<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/docx-handler"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/docx-handler/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 docx-handler

Your own site · 80×15
<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/docx-handler"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/docx-handler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 643 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 $0.00052 $0.00643
Opus 5.5 $0.00021 $0.00257
Sonnet 5.5 $0.00010 $0.00129
Haiku 4.5 $0.00005 $0.00064

Measured 2mo ago against content hash 9c55a4caf224, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docx-handler 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 2mo 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.

customer-success/skills/docx-handler/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DOCX Handler

Operate on Microsoft Word files (.docx). Extract content, generate new documents from markdown, or apply targeted edits.

Pick the right approach

  1. Python with python-docx — best for reading and writing with style awareness.
  2. Pandoc (pandoc input.md -o output.docx) — best for converting markdown → Word with reasonable defaults.
  3. Node with docx library — use if Python isn't available.

If nothing is installed, prefer pip install python-docx for reads/edits or use Pandoc for markdown conversion. Tell the user you're installing it.

Reading

Print a quick structure summary so the user knows what's inside:

Pages: ~12 | Words: 3,840 | Sections: 4 | Tables: 2 | Headings: 18

Extract text faithfully — preserve heading levels, lists, and table structure when converting to markdown. Don't paraphrase.

Generating from markdown

When the user asks for a Word version of markdown content:

  1. Save the source markdown to outputs/<topic>.md first (so they have both versions).
  2. Convert with Pandoc when available; fall back to python-docx building paragraphs by section.
  3. Apply a heading style hierarchy (Heading 1 → Heading 2 → Heading 3) so the document is navigable.
  4. Tables: render as Word tables, not pasted text.

Editing

For targeted edits ("change every instance of X to Y"):

  • Read the document, list the matches, ask before applying if there are more than 5.
  • Preserve formatting: a styled run (bold, color, font) should keep its style after the substitution.
  • For larger rewrites, prefer regenerating from a cleaned markdown source rather than in-place editing.

Output format

Save to outputs/<original-stem>-edited.docx for edits, outputs/<topic>.docx for new documents. Print a one-line report: path, sections added/changed, tables included.

Common mistakes

  • Stripping styles when extracting (read with style awareness, don't dump plain text).
  • Generating Word from markdown but losing tables or list nesting.
  • Overwriting the source file.
  • Inserting unicode characters that Word renders as boxes — verify the output opens cleanly.

Read the full file on GitHub · 62 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. 2mo ago First seen · 62 lines · 52 tokens per session scan A 9c55a4caf224

Subscribe to this mod's changes

docx-handler is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 643 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 2026-08-31.

Related

docx-handler compared with skills from other repositories

docx-handler next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docx-handlerbjorn-ingmanson/thefroject-pluginsSkill14mo agoMITA52Claude Code
orbit-notionnexu-io/open-designSkill107ktodayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35kyesterdayApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9kyesterdayApache-2.0A68Claude Code
report-to-pdfasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A17Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A54Claude Code, Codex