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 eigenweltlabs/legalwork --skill docx-editgit 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/skills/eigenweltlabs/legalwork/docx-edit)<a href="https://agentmods.dev/skills/eigenweltlabs/legalwork/docx-edit"><img src="https://agentmods.dev/badge/skills/eigenweltlabs/legalwork/docx-edit/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/eigenweltlabs/legalwork/docx-edit"><img src="https://agentmods.dev/badge/skills/eigenweltlabs/legalwork/docx-edit.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 | $0.00128 | $0.02381 |
| Opus 5 | $0.00064 | $0.01190 |
| Sonnet 5 | $0.00026 | $0.00476 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
docx-edit 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Word (.docx) reading + editing
This skill is how this firm reads and edits Word documents with AI. It has three backends, and your FIRST step is always to pick the right one:
Step 0 — where are you running?
- Unless the user explicitly named a different workspace document, call
inapp_docx_read_documentfirst. If it succeeds, the target is the document open in LegalWork's right-hand editor: use the IN-APP LIVE backend below. - If no matching in-app document is open, call
word_read_document. If it succeeds, the target is the document open in Microsoft Word: use the WORD LIVE backend. - Only when both live reads report no matching document may you use the FILE backend. Bash is the fallback, not the way to inspect a document already open beside the chat.
IN-APP LIVE mode — edit the document open in LegalWork
- Read with
inapp_docx_read_documentor find exact text withinapp_docx_find_text. Both return stableparaIdanchors. - Edit with
inapp_docx_suggest_changeand comment withinapp_docx_add_comment. Every agent text edit is a tracked change and saves back to the workspace automatically. - Accept or revert edits with
inapp_docx_accept_changes/inapp_docx_reject_changes. First callinapp_docx_read_changes, then pass the relevant IDs. For "revert my edits", reject only changes authored by the agent; never remove unrelated pre-existing redlines. - Do the accept/reject action yourself when asked. Do not tell the user to click review controls or claim the live editor lacks the tool.
- Never use bash or the FILE pipeline for this open document. Do not create a
.redlined.docxcopy: the redline appears in the document the user is viewing. - Hand back one or two short sentences; the user can review the tracked change beside the chat.
WORD LIVE mode — edit the open Microsoft Word document with word_* tools
- Read with
word_read_document(andword_searchto locate clauses) before editing, so anchors are verbatim. - Edit with
word_replace_text/word_insert_text: they apply native tracked changes directly in the open document. Attach a shortword_add_commentrationale to each substantive edit.word_run_codecovers formatting and anything the typed tools miss. - Never write files in LIVE mode. No
docx-agent.mjs, no.redlined.docx, no copy of the open document. The redlines are already in front of the user: they accept or reject them in Word (Review ribbon). Do not tell them to open another file or the LegalWork viewer. - Hand back: one or two short sentences on what you redlined and a reminder to review the tracked changes in Word.
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.
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.
- 2d ago Changed · +13 lines · -17 tokens per session b6330a317451
- 10d ago First seen · 140 lines · 145 tokens per session scan A 9600f3985c51
docx-edit is a skill published in the GitHub repository eigenweltlabs/legalwork (103 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 2,381 once invoked, about $0.0006 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 skills, from other repositories
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
handbook-updates
Diff a proposed handbook change against the current version, flag ripple effects and state supplement impacts. Use when user says "update the handbook", "add this to the handbook", "handbook change", or has a policy ready for insertion.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…