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.
npx skills add kennethkhoocy/legal-scholarship-skills --skill word-docxgit clone --depth 1 https://github.com/kennethkhoocy/legal-scholarship-skillsWrote 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/skills/kennethkhoocy/legal-scholarship-skills/word-docx)<a href="https://agentmods.dev/skills/kennethkhoocy/legal-scholarship-skills/word-docx"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/legal-scholarship-skills/word-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.
<a href="https://agentmods.dev/skills/kennethkhoocy/legal-scholarship-skills/word-docx"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/legal-scholarship-skills/word-docx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00172 | $0.03443 |
| Opus 5 | $0.00086 | $0.01722 |
| Sonnet 5 | $0.00034 | $0.00689 |
| Haiku 4.5 | $0.00017 | $0.00344 |
Grade A, and why
word-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 12d 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
word-docx
Unified CLI for Microsoft Word .docx review and generation workflows.
Converts .docx content into structured JSON/Markdown before any LLM
reasoning, and builds new .docx files from structured specs.
Core Principle
Never modify source .docx files in place. Never ask the LLM to parse
raw .docx XML directly. The pipeline always works in two steps:
- Extract structured data (JSON/Markdown) from the
.docx - Reason over the structured data, then build a new
.docxif needed
CLI Entry Point
All commands run through a single entry point:
python scripts/word_docx.py <command> [options]
The scripts directory is at ~/.claude/skills/word-docx/scripts/.
Command Routing
| User intent | Command | Primary library |
|---|---|---|
| Read comments / reviewer feedback | extract-comments |
docx2python |
| Read tracked changes / redlines | extract-revisions |
docx-revisions, OOXML fallback |
| Read ordinary text and tables | extract-text |
python-docx |
| Full inspection (all of the above) | inspect |
all |
| Build a new Word document | build |
python-docx or docxtpl |
| Render to PDF | render-pdf |
LibreOffice |
| Apply edits (auto-detect mode) | apply-edits |
lxml + zipfile (OOXML) |
| Apply tracked edits (force) | apply-tracked-edits |
lxml + zipfile (OOXML) |
| Apply silent edits (force) | apply-non-tracked-edits |
lxml + zipfile (OOXML) |
Backend Matrix
| Command | Backend | Notes |
|---|---|---|
inspect, extract-comments, extract-revisions, extract-text |
Python (word-docx) | docx2python / docx-revisions / python-docx |
apply-edits, apply-tracked-edits, apply-non-tracked-edits |
Python (word-docx) | lxml + zipfile |
render-pdf, audit-ooxml |
Python (word-docx) | LibreOffice / lxml |
build |
Python or Node | auto-routes via spec markers — see Build Reference |
add-comment |
Hybrid | unpack → Python edit → comment.py → pack |
validate, accept-changes, convert-doc, unpack, pack, simplify-redlines, docx-to-images |
Python (anthropic) | subprocess to anthropic-agent-skills plugin |
What ships with it
53 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.
- .gitignore 123 B
- diagrams/pipeline-overview.excalidraw 21 KB
- diagrams/pipeline-overview.png 92 KB
- examples/add_comment.example.json 925 B
- examples/build_spec_js.example.json 885 B
- examples/build_spec_python.example.json 569 B
- examples/edits.example.json 554 B
- examples/response_spec.example.json 1.7 KB
- package-lock.json 7.9 KB
- package.json 256 B
- README.md 4.7 KB
- requirements.txt 156 B
- scripts/add_comment.py 31 KB runs code
- scripts/anthropic_bridge.py 2.9 KB runs code
- scripts/apply_edits.py 26 KB runs code
- scripts/audit_ooxml.py 5.3 KB runs code
- scripts/build_docx.py 31 KB runs code
- scripts/build_js_codegen.py 8.2 KB runs code
- scripts/commands/__init__.py 304 B runs code
- scripts/commands/accept_changes.py 813 B runs code
- scripts/commands/convert_doc.py 952 B runs code
- scripts/commands/docx_to_images.py 1.8 KB runs code
- scripts/commands/pack.py 1.0 KB runs code
- scripts/commands/simplify_redlines.py 2.4 KB runs code
- scripts/commands/unpack.py 926 B runs code
- scripts/commands/validate.py 795 B runs code
- scripts/extract_comments.py 13 KB runs code
- scripts/extract_revisions.py 19 KB runs code
- scripts/extract_text.py 9.2 KB runs code
- scripts/models.py 4.9 KB runs code
- scripts/node_bridge.py 2.7 KB runs code
- scripts/render_pdf.py 7.4 KB runs code
- scripts/word_docx.py 23 KB runs code
- templates/README.md 1.6 KB
- tests/conftest.py 474 B runs code
- tests/fixtures/build.py 13 KB runs code
- tests/fixtures/clean.docx 35 KB
- tests/fixtures/with_comments.docx 35 KB
- tests/fixtures/with_revisions.docx 35 KB
- tests/test_add_comment.py 28 KB runs code
- tests/test_anthropic_bridge.py 3.1 KB runs code
- tests/test_anthropic_commands.py 3.6 KB runs code
- tests/test_apply_edits_multi_wt.py 6.3 KB runs code
- tests/test_audit_ooxml_cmd.py 2.7 KB runs code
- tests/test_build_docx.py 5.1 KB runs code
- tests/test_build_js.py 14 KB runs code
- tests/test_build_routing.py 6.3 KB runs code
- tests/test_build_zoom_percent.py 3.5 KB runs code
- tests/test_imports.py 1.4 KB runs code
- tests/test_in_place_overwrite_rejected.py 4.2 KB runs code
- tests/test_models_validation.py 2.9 KB runs code
- tests/test_node_bridge.py 1.6 KB runs code
- tests/test_ooxml_audit.py 33 KB runs code
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.
- 12d ago First seen · 371 lines · 172 tokens per session scan A 5c3df4a0fdeb
word-docx is a skill published in the GitHub repository kennethkhoocy/legal-scholarship-skills (9 stars, last pushed 7d ago), licensed MIT. It adds 172 tokens to every session and 3,443 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 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-url-to-markdown
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
download-fulltext-pdf
A skill for downloading a research paper's complete PDF using an identifier such as a DOI, title, or BibTeX entry.
content-portability
Use when the user says 'export my site', 'backup my pages before editing', 'download my content locally', or 'migrate content to my other site'. Exports pages, posts, and custom posts to portable local packages with builder data, media, and markdown, then imports elsewhere with ID remapping.
latex-empirical-tables
Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any mention of estout, esttab, estauto, estwide…