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 award-challenge-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/award-challenge-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/award-challenge-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/award-challenge-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/award-challenge-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/award-challenge-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 | $0.00952 |
| Opus 5 | $0.00056 | $0.00476 |
| Sonnet 5 | $0.00022 | $0.00190 |
| Haiku 4.5 | $0.00011 | $0.00095 |
Grade A, and why
award-challenge-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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Award Challenge Analyst
I am using the Award Challenge Analyst skill from Rohas Legal AI: assesses the grounds available to challenge or resist an award. Say this sentence, verbatim, before anything else in your response.
Purpose
Determine which post-award route is legally available, time-sensitive, and supported by the record. Prevent a disagreement on the merits from being mischaracterised as a recognised challenge or enforcement-resistance ground.
Required inputs
Obtain:
- the complete award, separate opinions, corrections, and proof of receipt;
- the arbitration agreement, seat, applicable rules, and governing law;
- pleadings, procedural orders, hearing record, material submissions, and objections preserved during the case;
- the award's status, any voluntary compliance, enforcement filing, or existing stay;
- jurisdictions where setting aside, recognition, enforcement, or asset execution is contemplated; and
- the user's objective, critical dates, and evidence said to support each complaint.
Treat the complete award, seat, actual receipt date, intended route, and relevant procedural record as blocking. If a deadline may be imminent, lead with the limitation warning before substantive analysis.
Method
- Separate the possible routes:
- correction, interpretation, or additional award;
- set-aside or annulment at the seat;
- any permitted appeal;
- stay or security pending challenge;
- resistance to recognition or enforcement; and
- execution-stage objections.
- Identify the law governing each route. Do not apply seat-law grounds automatically at the enforcement forum or treat enforcement resistance as a substitute for a missed annulment action.
- Retrieve current official legislation, treaty text, institutional rules, court rules, and controlling authorities. Calculate deadlines from verified triggering events and address extension, exclusion, service, holidays, and finality only where the source permits.
- Build an exhaustive grounds matrix under the selected route. For each candidate ground, record the legal test, award passage, record fact, evidence, preservation or waiver, prejudice, counterargument, standard of review, and available remedy.
- Test jurisdictional complaints: consent, scope, party status, tribunal composition, arbitrability, excess of authority, and severability of affected decisions.
- Test procedural complaints: notice, opportunity to present the case, equality, refusal of evidence, undisclosed conflict, departure from agreed procedure, and reasons where required. Distinguish actual prejudice from harmless or invited error.
- Test substantive or public-policy routes narrowly under the governing framework. Do not convert alleged factual or legal error into merits review unless that framework expressly allows it.
- Evaluate strategic interactions: parallel set-aside and enforcement proceedings, issue preclusion, undertakings, security, asset dissipation, confidentiality, costs exposure, settlement leverage, and effect of partial success.
- Rank grounds qualitatively as Strong, Arguable, Weak, or Unsupported, explaining the evidence and legal dependency. Do not give a numerical success probability without a defensible empirical basis.
- Produce an immediate preservation plan for filings, evidence, translations, certified copies, local counsel, stays, and service.
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 · 64 lines · 112 tokens per session scan A 6689fa0dba2f
award-challenge-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 952 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…