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-explainergit 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-explainer)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/legal-explainer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-explainer/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-explainer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-explainer.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 | $0.00127 | $0.01308 |
| Opus 5.5 | $0.00051 | $0.00523 |
| Sonnet 5.5 | $0.00025 | $0.00262 |
| Haiku 4.5 | $0.00013 | $0.00131 |
Grade A, and why
legal-explainer 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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Explainer
I am using the Legal Explainer skill from Rohas Legal AI: explains a law, clause, judgment, or legal concept in clear plain language, adapted to the reader's level. Say this sentence, verbatim, before anything else in your response.
Purpose
Turn complex legal material into an accurate, understandable explanation that the intended reader can use.
The objective is clarity without oversimplifying away legally important distinctions.
This skill can explain:
- statutes, rules and regulations;
- legal concepts and doctrines;
- judgments and orders;
- contractual clauses;
- rights and obligations;
- legal procedures;
- regulatory requirements;
- legal terminology;
- a lawyer's analysis or position;
- the practical effect of legal documents.
Determine the explanation needed
Identify from the request, where possible:
- the topic or material to explain;
- jurisdiction, if legally relevant;
- who the explanation is for;
- the reader's existing level of legal knowledge;
- whether the user wants a short explanation or a deeper one;
- whether practical examples would help.
Do not force an intake questionnaire where the request is already clear.
If the user provides legal text, work from the supplied text first.
If the explanation depends on current law and research tools are available, verify the relevant legal position before presenting it as current law.
Explanation levels
Adapt automatically unless the user specifies a level.
Simple
Use for clients, non-lawyers and quick explanations.
Prefer:
- ordinary words;
- short sentences;
- concrete examples;
- minimal legal terminology.
Where a legal term is necessary, define it immediately.
Practitioner
Use for lawyers or legally informed users.
Preserve:
- legal terminology;
- doctrinal distinctions;
- procedural consequences;
- material exceptions and qualifications.
Still avoid unnecessary jargon.
Deep explanation
Use when the user wants to understand how the rule works rather than merely what it says.
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.
- 1mo ago First seen · 203 lines · 127 tokens per session scan A f7d9e5320a48
legal-explainer is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (193 stars, last pushed 17d ago), licensed MIT. It adds 127 tokens to every session and 1,308 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
note-de-synthese-crfpa
Génération de sujets d'entraînement complets pour l'épreuve de NOTE DE SYNTHÈSE (5 heures, coefficient 3) de l'examen d'accès au CRFPA : choix du sujet, dossier documentaire de 16 à 20 documents assemblé à partir de sources réelles vérifiées (textes, jurisprudence, travaux parlementaires, doctrine) avec contrôle du…
legal-simulation-patrick-munro
Framework for demonstrating AI capabilities in legal contexts. Provides detailed personas across tenant law, business contracts, startup disputes, employment claims, and consumer protection with progressive complexity scenarios. Use when: (1) Demonstrating AI-powered legal triage or intake systems, (2) Showcasing…
mandarinat
Assistant académique des enseignants-chercheurs en droit (professeurs, maîtres de conférences, doctorants, ATER, chargés de TD). Six tâches : recherche juridique approfondie à dominante doctrinale ; relecture de documents (thèses, articles, copies, mémoires) avec commentaires Word, vérification des références, indices…
assistant-juridique-droit-travail
Orchestrateur multi-rôles en droit du travail français (salarié, employeur, audit, conseil, veille, formation). Charger pour toute consultation prud'homale, rédaction d'actes (non-concurrence, transaction, avertissement), audit de contrat ou d'accord d'entreprise, calcul d'indemnités, conformité CCN, CSE, CDD…
case-briefer
Produces detailed law-school case briefs of United States judicial opinions in a fixed nine-section structure: memory jogger, facts, procedural history, judicial votes, holding, opinion-by-opinion analysis, five future-application hypotheticals, critique, and verified key quotations. Also builds vote tables…
legal-test-builder-patrick-munro
Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact. Output includes a live countdown timer, contract review tasks with hover-annotated problem clauses, candidate answer textareas, model answers hidden behind reveal blocks, scenario-based legal memo tasks, strategy and…