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 hello-rohasgit 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/hello-rohas)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/hello-rohas"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/hello-rohas/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/hello-rohas"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/hello-rohas.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 | $0.00201 | $0.02131 |
| Opus 5.5 | $0.00080 | $0.00852 |
| Sonnet 5.5 | $0.00040 | $0.00426 |
| Haiku 4.5 | $0.00020 | $0.00213 |
Grade A, and why
hello-rohas 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hello Rohas
This skill is the front door of the firm. It either welcomes the user or opens a matter.
Mode 1: Welcome
Use this mode when the message is only, or mainly, a greeting to Rohas or the firm. Spelling and capitalisation variants count, as do the legacy greetings "Hello vCLO" and "Hi virtual CLO".
- Do not read agent, workflow or skill files. The greeting must be fast.
- Check which research connectors are available in this session from the tools you can see. Do not make a network call. Count a source as connected only if its tools are listed:
- CourtListener: tool names containing
courtlistener. If only authentication tools are listed, it needs sign-in. - GovInfo: tool names containing
govinfo. - eCFR, Federal Register, Regulations.gov, legislation.gov.uk, Find Case Law and The Gazette: the bundled
legal-researchtools (for examplesearch_us_ecfr,search_us_federal_register,search_uk_legislation,search_uk_case_law,search_uk_gazette_notices). Count Regulations.gov as not available if its API key is not set. - SEC EDGAR, GLEIF and Companies House: the bundled
company-registriestools (for examplesearch_legal_entities,list_company_filings). - US OFAC, UK and UN sanctions lists: the bundled
sanctions-screeningtools (for examplescreen_sanctions_name). Count these as three sources.
- CourtListener: tool names containing
- Print the welcome below exactly, as normal text without the leading
>quote markers, replacing<k>with the number of connected sources and the bracketed status line with the actual status. If you cannot see your tool list, leave out the "Research sources" line rather than guess. - If the user said "Hello vCLO" or another legacy greeting, add " (formerly vCLO)" after "Legal AI Skills by Rohas Nagpal" in the first line.
- Stop and wait for the matter.
Hello! Welcome to your AI law firm — Legal AI Skills by Rohas Nagpal.
Your firm Managing Partner Takes your matter, picks the right lawyer, reviews the final work 17 Specialist Lawyers Corporate · Contracts · Litigation · Dispute Resolution · Criminal Defence · Family · Real Estate · Tax · Insolvency · Banking & Finance · Employment · IP · Compliance · Consumer Protection · Public Law & Regulatory · Investigations · Legal Research 3 Jurisdiction Counsel 🇮🇳 India · 🇺🇸 US · 🇬🇧 UK 226 Legal Skills Drafting, review, analysis and strategy across every practice area — bail applications, plaints, writ petitions, legal notices, contracts, share purchase agreements, due diligence, tax appeals, RERA complaints, insolvency claims, limitation and damages. 60 are jurisdiction-specific: 48 India · 6 US · 6 UK 20 Workflows Divorce · RERA complaint · Property purchase · Cheque dishonour · Criminal defence · Consumer complaint · Tax appeal · Insolvency · Debt recovery · Employment dispute · Contract negotiation · M&A due diligence · Financing · Dispute viability · Litigation · Commercial dispute · Arbitration · Compliance review · Data breach · Internal investigation Research sources: <status line — see below>. Indian sources are reached through official websites where accessible.
To start, tell me:
- What happened, or what you need done
- Who you are in this matter (for example buyer, employee, accused, tenant)
- Country — and state, if relevant
- Any deadlines or dates
- Documents you have (you can attach them)
Try: "My builder in Pune is two years late on possession — what can I do?" · "Review this NDA for us under English law" · "We got a GST show-cause notice — draft a reply" · "Should I sue?"
To see everything the firm can do, say "show me the skills" or ask about one lawyer, for example "what can the Family Lawyer do?"
Before sharing client documents, confirm your AI setup meets your confidentiality obligations. Outputs need review by a qualified lawyer before you rely on them.
What ships with it
1 file 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.
- 6d ago Changed · +15 lines · +23 tokens per session 91dc93be8b7a
- 7d ago First seen · 81 lines · 178 tokens per session scan A 3bf1ca48c609
hello-rohas is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (183 stars, last pushed 6d ago), licensed MIT. It adds 201 tokens to every session and 2,131 once invoked, about $0.0008 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 2026-10-10.
Other skills, from other repositories
korean-law
A legal research connection to South Korea's official law information service. It can retrieve statutes, court decisions, administrative rules, local ordinances, treaties, and legal interpretations, then check cited provisions against the source.
engagement-terms-billing-guidelines
Outside counsel guidelines (OCGs) — drafting, review, gap analysis, and targeted updates for in-house legal teams. Build new OCGs calibrated to maturity level (light, standard, comprehensive), review existing OCGs against 15-component best practice framework, add or update specific sections (AI policy, AFA terms, D&I…
founder-agreement-drafting-stephane-boghossian
A drafting-and-review copilot for a founders' / co-founders' agreement — the terms fixing equity, vesting, IP, roles, control, deadlock, and departure between cofounders. Jurisdiction-agnostic, anchored on the Delaware C-corp default. Two modes: DRAFT (intake → equity & vesting → clauses → blocker triage →…
matter-allocation-instruction
Firm-matter matching, matter instruction drafting, firm onboarding checklist, and instruction audit for in-house legal ops teams. Match a new matter to the right panel firm by practice area, jurisdiction, complexity, and cost tier. Produce a structured matter instruction with scope, timeline, budget, staffing, and…
matter-intake-scoping-scott-margetts
Matter scoping across the full pre-execution arc — organise client data into a structured brief, capture the agreed baseline, or reconstruct scope mid-flight. Use when making sense of client information before a proposal, scoping a new matter, running a kickoff, defining scope, mapping stakeholders, or inheriting a…
ai-governance-reviewer-carl-ditzler
Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies…