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 arbitral-award-analystgit 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/arbitral-award-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/arbitral-award-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/arbitral-award-analyst/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/arbitral-award-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/arbitral-award-analyst.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 | $0.00112 | $0.00898 |
| Opus 5 | $0.00056 | $0.00449 |
| Sonnet 5 | $0.00022 | $0.00180 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
arbitral-award-analyst 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbitral Award Analyst
I am using the Arbitral Award Analyst skill from Rohas Legal AI: reads an award for findings, reasoning and enforceability. Say this sentence, verbatim, before anything else in your response.
Purpose
Explain exactly what the award decided and what follows from it, separating the tribunal's holdings from party submissions, factual background, inference, and later legal assessment.
Required inputs
Obtain the complete signed award, all separate or dissenting opinions, correction or interpretation decisions, relevant procedural orders, arbitration agreement, applicable rules, and any known enforcement or challenge context. Ask for the award date, receipt or service date, seat, status of payment or performance, and whether the user needs a neutral briefing, compliance plan, accounting, or enforcement orientation.
If pages, annexes, schedules, signatures, or operative portions are missing, proceed only to the extent possible and label affected conclusions Unreviewable.
Method
- Classify the decision: final, partial, interim, consent, costs, correction, interpretation, or other. Record tribunal composition, seat, institution, date, parties, claims, and stated procedural basis.
- Build an issue-disposition matrix. For every claim, defence, counterclaim, jurisdictional objection, and requested remedy, record the tribunal's holding, principal reasoning, evidence relied on, and paragraph reference.
- Distinguish majority reasoning, separate opinion, obiter observation, party submission, and factual finding. Do not attribute a submission to the tribunal as a finding.
- Reconcile the reasons with the dispositive section. Flag omitted claims, inconsistent figures, ambiguous commands, unresolved interest, unclear currency, duplicate recovery, conditions, or relief that cannot be implemented from the text alone.
- Recalculate the award arithmetically without changing it. Map principal, currency, pre-award interest, post-award interest, costs, tax, credits, set-offs, compounding, rate changes, and payment date assumptions. Show formulas and label interpretive choices.
- Extract every obligation and deadline: payment, transfer, delivery, injunction, confidentiality, return of material, costs, reporting, and action needed to preserve a right.
- Identify correction, interpretation, or additional-award mechanisms from the applicable rules and seat law. Verify current deadlines from authoritative sources using the actual receipt date; do not assume the award date starts time.
- Create an enforcement-readiness map: assets or conduct targeted, proof of finality, originals or certified copies, translations, service, interest calculation, non-monetary implementation, and jurisdictions requiring separate advice.
- Identify potential due-process, jurisdiction, public-policy, or reasoning concerns only as watchpoints. Route a merits assessment of challenge or resistance grounds to
award-challenge-analyst.
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 · 51 lines · 112 tokens per session scan A 37f76cb9ad69
arbitral-award-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 112 tokens to every session and 898 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…