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.
git clone --depth 1 https://github.com/eigenweltlabs/legalworkWrote 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/commands/eigenweltlabs/legalwork/edit-docx)<a href="https://agentmods.dev/commands/eigenweltlabs/legalwork/edit-docx"><img src="https://agentmods.dev/badge/commands/eigenweltlabs/legalwork/edit-docx.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00019 | $0.00408 |
| Opus 5 | $0.00010 | $0.00204 |
| Sonnet 5 | $0.00004 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
edit-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 yesterday.
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.
What it actually says
Edit a Word document with AI — write back comments and tracked-change redlines the lawyer reviews and accepts where they are working: directly in Microsoft Word when this session runs inside the Word add-in, or in the in-app viewer otherwise (the firm's open-model version of "ask the assistant to redline this contract").
Load and follow the docx-edit skill — start with its Step 0 to pick the
backend. First try the document open in LegalWork's in-app editor and use
inapp_docx_* tools; otherwise try the Microsoft Word add-in and use word_* tools.
Only when neither live surface has the target document should you use the file
pipeline. Then carry out this request:
$ARGUMENTS
Reminders from the skill (FILE backend):
inspectthe.docxfirst to get the stable paragraph map; anchor every edit to a 0-basedparagraphIndex.- For a full redline pass, fan out the
docx-redlinersubagent (Task tool); for a small targeted change, build the plan yourself. commentsare margin notes (the why);proposalsare tracked-change edits. Everysearchstring must be verbatim from the paragraph.applywrites a non-destructive<base>.redlined.docxby default — open it in the viewer to see the redlines inline. Use--in-placeonly if asked.- Report any ops that didn't match verbatim instead of dropping them; never fabricate parties, numbers, or terms.
If no document is named in the arguments, use the active in-app document or the
document open in Microsoft Word. Ask which .docx to edit only if neither is open.
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.
- yesterday Changed 1f2d6c0c0456
- 8d ago First seen · 33 lines · 19 tokens per session scan A 64f595039193
edit-docx is a command published in the GitHub repository eigenweltlabs/legalwork (100 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 408 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
prose-review-docs
Reviews markdown documentation files or directories against the active prose style rules — the plugin's vendor-neutral baseline plus your organization's overlay when one is configured. Accepts a file path or directory (recursive). Runs prose-style-checker and optionally Vale. Supports --fix to auto-apply safe…
convert
Convert a file to Markdown using markitdown.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
render-figures
Compile all .tex and .typ figure files in a directory.