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 rohasnagpal/legal-ai-skills --skill legal-document-producergit clone --depth 1 https://github.com/rohasnagpal/legal-ai-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/rohasnagpal/legal-ai-skills/legal-document-producer)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/legal-document-producer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-document-producer/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/rohasnagpal/legal-ai-skills/legal-document-producer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-document-producer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00103 | $0.01019 |
| Opus 5.5 | $0.00041 | $0.00408 |
| Sonnet 5 | $0.00021 | $0.00204 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
legal-document-producer 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.
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.
Legal Document Producer
I am using the Legal Document Producer skill from vCLO: template-aware DOCX and PDF production, conversion, OCR, assembly and final-format quality control. Say this sentence, verbatim, before anything else in your response.
Turn completed or supplied legal content into a professional, usable document without silently changing its legal effect.
Production brief
Establish the source document or approved text, document type, intended audience, required output format, governing template or style guide, jurisdiction and forum where formatting rules matter, language, clean or comparison version, schedules and exhibits, deadline, and requested output location.
If no template is supplied, use a restrained professional legal-document style and say that no firm, client or court template was applied. Do not describe a document as court-ready, filing-ready, execution-ready or compliant with a house style unless the relevant current requirements or template were supplied and checked.
Method
- Preserve the source. Work from a copy or create a new output; never overwrite the source unless the user expressly requests it.
- Inventory the content and attachments. Record missing schedules, broken references, illegible pages, unsupported files and unresolved placeholders before production.
- Select the output route in document-production options. Prefer local processing for confidential material. Use Google Docs, Microsoft 365, iManage or NetDocuments only when the relevant connector is actually available and the user has authorised the source, destination and action.
- Apply the template and document structure. Use consistent page setup, hierarchy, paragraph styles, multilevel numbering, defined-term presentation, tables, cross-references, headers, footers, page numbers, signature blocks, schedules, annexures and exhibit labels appropriate to the document type.
- Preserve substance. Do not reword operative text, repair an apparent legal defect, complete a blank, accept a change or remove a comment merely to improve presentation. List substantive or ambiguous issues separately for the relevant drafting or review skill.
- Perform only the requested technical operations: DOCX or PDF generation, format conversion, OCR, searchable-text creation, template application, pagination, bookmarks, table of contents, exhibit or bundle assembly, and permitted metadata cleaning.
- Run final quality control against both the source and rendered output. Check completeness, text order, clause numbering, defined terms, cross-references, tables, page breaks, footnotes, headers and footers, signatures, schedules, hyperlinks, bookmarks, OCR accuracy, selectable text, fonts, tracked changes, comments and metadata.
- Deliver the produced files with a short production note recording source files, template, output format, operations performed, tools used, unresolved defects and checks still requiring human review.
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.
- yesterday First seen · 62 lines · 103 tokens per session scan A 09b239c937cf
legal-document-producer is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (149 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,019 once invoked, about $0.0004 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 2026-09-25.
Other skills, from other repositories
law-to-markdown
A skill that converts legal provisions and regulatory documents from plain text, PDF, or Word format into Markdown. Markdown is a plain-text format commonly used for structured documents.
gdpr-privacy-notice-eu-oliver-schmidt-prietz
Draft GDPR/DSGVO-compliant privacy notices as .docx for any EU/EEA jurisdiction and audience. Use when user asks to create a privacy policy/notice, mentions "Datenschutzerklärung", "politique de confidentialité", "privacy notice", needs Art. 13/14 disclosures, AI Act transparency, cookie policy, or notices for…
eu-ai-act-report-oliver-schmidt-prietz
Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries. This skill should be used when the user asks to "generate an AI Act report", "create a compliance assessment report", "document the AI Act analysis", "create a Prüfbericht", "export as…
litigation-deadline-calendar
Calendar litigation and arbitration deadlines from a scheduling order. Parses a PDF scheduling order, identifies key dates, computes backward deadlines using the applicable rules (Colorado CRCP, Federal FRCP, or arbitration forum rules for AAA/JAMS), and generates an .ics calendar file for Outlook or Google Calendar…
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.