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 arbitration-clause-reviewergit 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/arbitration-clause-reviewer)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/arbitration-clause-reviewer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/arbitration-clause-reviewer/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/arbitration-clause-reviewer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/arbitration-clause-reviewer.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 | $0.00121 | $0.00915 |
| Opus 5 | $0.00060 | $0.00458 |
| Sonnet 5 | $0.00024 | $0.00183 |
| Haiku 4.5 | $0.00012 | $0.00092 |
Grade A, and why
arbitration-clause-reviewer 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 12d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbitration Clause Reviewer
I am using the Arbitration Clause Reviewer skill from Rohas Legal AI: checks a clause for seat, venue, rules, appointment and pathology. Say this sentence, verbatim, before anything else in your response.
Purpose
Test whether the clause creates a workable arbitration process and identify exactly where ambiguity, invalidity, delay, or satellite litigation could arise. Separate textual certainty from conclusions that depend on the governing law or current institutional rules.
Required inputs
Obtain the clause and every provision it incorporates or interacts with, including governing-law, notices, escalation, jurisdiction, and execution provisions. Obtain the complete contract where possible; mark conclusions limited when reviewing an excerpt.
Identify or ask for:
- the contract's governing law;
- the intended or stated arbitral seat and any hearing venue;
- the named institution and rules, including the applicable version if known;
- the party structure, especially multi-party or non-signatory issues; and
- the user's side and commercial objective if revisions are requested.
Proceed with a diagnostic review when an item is missing, but label the consequence Unresolved. Do not supply an institution, seat, or governing law from memory as though the parties selected it.
Method
- Quote or reproduce the operative clause accurately and list every cross-reference. Flag missing schedules, broken references, inconsistent defined terms, and competing dispute provisions.
- Separate the potentially relevant laws: law governing the main contract, law governing the arbitration agreement, procedural law of the seat, and law at any enforcement forum. Do not collapse them into one merely because the contract names a governing law.
- Test formation and scope: written agreement, incorporation, parties bound, disputes covered, exclusions, survival, optionality, and whether escalation language is mandatory or aspirational.
- Test the arbitral architecture: seat, venue, institution or ad hoc process, rules, language, number of arbitrators, qualifications, appointment sequence, default appointing authority, and replacement process.
- Test procedural interfaces: negotiation or mediation conditions, limitation effects, interim and emergency relief, court carve-outs, consolidation, joinder, confidentiality, costs, and service.
- Model failure scenarios. Ask what happens if a party refuses to appoint, the named institution no longer exists, the rules conflict with the clause, deadlines overlap, or seat and exclusive-court wording point to different places.
- Verify law-dependent conclusions and current institutional provisions from authoritative sources when the user asks for an enforceability opinion. Cite the exact provision or rule relied on and state what remains unverified.
- Propose replacement wording only when requested. Preserve the parties' commercial choices, provide a clean clause, and explain each material change. Use placeholders instead of inventing missing choices.
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.
- 12d ago First seen · 56 lines · 121 tokens per session scan A b67c11e3034c
arbitration-clause-reviewer is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 121 tokens to every session and 915 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…