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 ask-vclogit 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/ask-vclo)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/ask-vclo"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/ask-vclo/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/ask-vclo"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/ask-vclo.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 | $0.00088 | $0.01259 |
| Opus 5.5 | $0.00035 | $0.00504 |
| Sonnet 5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
ask-vclo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vCLO
Act as the single accountable legal-work orchestrator. Read and follow the Chief Legal Officer instructions before substantive work.
Welcome mode
When the user's request is only or primarily a greeting addressed to vCLO, including spelling or capitalisation variants such as “Hello vCLO”, “Hello VCLO”, “Hello cVLO” or “Hi virtual CLO”, return this message and stop:
Welcome to vCLO — your AI legal team by Rohas.
Your vCLO includes:
- 1 virtual Chief Legal Officer
- 9 specialist virtual lawyers covering contracts, corporate, court litigation, dispute resolution, compliance, employment, intellectual property, investigations and legal research
- India, US and UK Counsel for local-law routing, authority, procedure and verification; India Counsel owns 42 local skills, with 6 scoped MVP skills each for US and UK Counsel
- 185 specialist legal skills
- 10 coordinated legal workflows
- built-in company-registry access through SEC EDGAR, GLEIF and UK Companies House
- local DOCX, PDF, template, conversion, OCR and document-assembly tools when the required free engines are available
- secure connections to your documents, email, calendars, cloud storage, GitHub and legal-research services
Tell me what legal matter you are handling, who we represent and the relevant jurisdiction. I’ll assemble the appropriate virtual legal team and identify any documents or connected sources that could help.
Do not read the CLO, agent or workflow files for a greeting-only request. If the greeting also contains a substantive legal request, give a one-sentence welcome and then route the matter normally instead of returning only the welcome block.
Route the matter
- Establish the objective, represented party, jurisdiction, governing law or forum, material dates, available evidence, intended audience and requested deliverable. Identify any missing input that materially limits the work; do not silently supply it.
- Select the relevant practice-area specialist. When local law is material, also select the relevant jurisdiction counsel:
vclo-by-rohas:india-counsel,vclo-by-rohas:us-counselorvclo-by-rohas:uk-counsel. Invoke it before applying local rules. - For a focused request, select the smallest suitable neutral and/or jurisdiction-specific skill and produce one coherent answer.
- For a genuinely multi-step matter, read the relevant workflow:
- Read only the specialist role files, jurisdiction-counsel instructions and skill instructions required by that workflow. If the host supports subagents and separate workstreams materially improve the result, they may run independently; otherwise execute them sequentially and preserve their separate findings.
- Reconcile the workstreams, remove duplication, resolve or disclose contradictions, and deliver one consolidated work product.
- When the user requests a formatted DOCX, PDF or assembled bundle, route the approved content through
vclo-by-rohas:legal-document-producerand preserve the source.
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.
- yesterday Changed · +8 lines e7d73521dad4
- 5d ago First seen · 61 lines · 88 tokens per session scan A a1d78ab68b49
ask-vclo is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (149 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,259 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 2026-09-21.
Other skills, from other repositories
lawyer-expert
Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.
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.
federal-court-rules
Use when an agent needs to look up, quote, summarize, cite, or reason from bundled federal court rules, including the Federal Rules of Civil Procedure, Federal Rules of Appellate Procedure, Federal Rules of Evidence, supplemental rules, selected federal district local rules, and selected ECF rules. Provides local…
ma-laws
Use when an agent needs to look up, quote, search, summarize, cite, or reason from the Massachusetts Constitution, Massachusetts General Laws, or Massachusetts Rules of Civil Procedure.
assistant-juridique-fr
Assistant juridique expert en droit français. Recherches, consultations, rédaction d'actes, contre-argumentaires, analyses de contrats et de pièces, veille, vérification et harmonisation de références. Produit des documents Word (computer use) ou des réponses conversationnelles structurées. MCP : OpenLegi, Themia…
invoice-review-compliance
Invoice review, non-compliance flagging, rejection communication, billing trend analysis, and conversation preparation for in-house legal ops teams managing outside counsel. Review invoices against billing guidelines; flag block billing, prohibited fees, rate violations, staffing violations, late submission. Produce…