agentmods.dev

legal-ai-skills

legal-ai-skills is a plugin for Claude Code from rohasnagpal/legal-ai-skills. Its manifest loads nothing; the 175 skills it bundles cost 19,807 tokens per session together, scanned A, original, MIT.

An installable legal-assistance plugin containing specialist legal roles, jurisdiction-specific counsel for India, the US, and the UK, legal skills, workflows, company registries, research connectors, and local document production.

In plain words
What is it for?
Legal research, jurisdiction-specific legal assistance, company-registry lookups, structured legal workflows, and producing documents locally.
Why use it?
It groups legal research and document-related work into one coding-agent add-on instead of requiring separate legal tools. Its work can be tailored to the listed jurisdictions and legal tasks.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 183repo +3 changed 6d ago A scan tokens not measured original MIT

Good fit Legal research, jurisdiction-specific legal assistance, company-registry lookups, structured legal workflows, and producing documents locally.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add rohasnagpal/legal-ai-skills
/plugin install legal-ai-skills
View source ↗ rohasnagpal/legal-ai-skills
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.

Clone the repo
git clone --depth 1 https://github.com/rohasnagpal/legal-ai-skills

Made for: Claude Code.

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 legal-ai-skills

README.md
[![agentmods](https://agentmods.dev/badge/plugins/rohasnagpal/legal-ai-skills/legal-ai-skills/github.svg)](https://agentmods.dev/plugins/rohasnagpal/legal-ai-skills/legal-ai-skills)
Your own site
<a href="https://agentmods.dev/plugins/rohasnagpal/legal-ai-skills/legal-ai-skills"><img src="https://agentmods.dev/badge/plugins/rohasnagpal/legal-ai-skills/legal-ai-skills/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 legal-ai-skills

Your own site · 80×15
<a href="https://agentmods.dev/plugins/rohasnagpal/legal-ai-skills/legal-ai-skills"><img src="https://agentmods.dev/badge/plugins/rohasnagpal/legal-ai-skills/legal-ai-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 175 skills cost 19,807 tokens a session between them.
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.
Security

Grade A, and why

legal-ai-skills 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 6d 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.

.claude-plugin/marketplace.json#legal-ai-skills · 14 lines

What it actually says

{
  "name": "legal-ai-skills",
  "version": "4.1.1",
  "source": "./plugins/legal-ai-skills",
  "description": "One installable AI law firm: a Managing Partner, 17 Specialist Lawyers, India, US and UK Jurisdiction Counsel, 226 legal skills, 20 workflows, company registries, official legal-research connectors and local document production. Say Hello Rohas to begin.",
  "author": {
    "name": "Rohas Nagpal",
    "url": "https://rohasnagpal.com"
  },
  "skills": [
    "./skills/"
  ],
  "strict": false
}
Contents

What it installs

The manifest is a name and a version. 175 skills travel with it, and installing the plugin installs all of them — 19,807 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#legal-ai-skills 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.

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. 6d ago Changed 9820c6047310
  2. 7d ago First seen · 14 lines scan A 18118ddb3732

Subscribe to this mod's changes

legal-ai-skills is a plugin published in the GitHub repository rohasnagpal/legal-ai-skills (183 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-10.

Legal and complianceResearchaiai-agentslawlaw-firmlawslawtech
Related

Other plugins, from other repositories

prawo-pl-eli

Polskie prawo z oficjalnego API ELI Sejmu (Dz.U./Monitor Polski) do każdego pytania z prawa polskiego oraz pracy nad umowami i pismami procesowymi: wyszukiwanie aktów, pojedyncze artykuły, tekst jednolity, nowelizacje i podstawa prawna. Read-only — źródło pierwotne zamiast cytowania przepisów z pamięci lub portali.

jamarpl21/prawo-pl-eli · not measured

prawo-pl-orzeczenia-ms

Orzeczenia sądów powszechnych (SA/SO/SR) bezpośrednio z Portalu Orzeczeń MS: wyszukiwanie, metryka, pełne uzasadnienia, powołane przepisy, PDF i RSS. Publiczny HTML/XML przez standardową bibliotekę Pythona, bez przeglądarki.

jamarpl21/prawo-pl-eli · not measured

fl-laws

Look up and search Florida Statutes, the Florida Constitution, and statewide Florida court rules using a verified local corpus downloaded on first use.

DocketDrafter/docketdrafter-plugins · not measured

dilekce-cerceveleri

12 hukuki argüman çerçevesine (IRAC ailesi: MIRAT, IRAAC/IRRAC, ILAC, IPAC/IDAR, TREAC/TREACC; CREAC ailesi: CRAC, CRuPAC, CREXAC, CRRACC; TREAT; Toulmin; klasik retorik) göre Türk hukuku dilekçe ve savunma yazım skill'leri. docx/html/udf/pdf çıktısı üretir; tüm içerik KVKK-temiz yer tutuculudur.

esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri · not measured

humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says.

blader/humanizer · not measured

nextjs

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

vercel/next.js · not measured