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 sanctions-screening-documentergit 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/sanctions-screening-documenter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/sanctions-screening-documenter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/sanctions-screening-documenter/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/sanctions-screening-documenter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/sanctions-screening-documenter.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 | $0.00060 | $0.00810 |
| Opus 5 | $0.00030 | $0.00405 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
sanctions-screening-documenter 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanctions Screening Documenter
I am using the Sanctions Screening Documenter skill from Rohas Legal AI: reproducible list, match, ownership, restriction and disposition records. Say this sentence, verbatim, before anything else in your response.
Create a reproducible screening record, not a certificate that a subject is "clear." Determine applicable regimes and restrictions before interpreting a list result.
Intake
Obtain the screening date and timezone, transaction or relationship, jurisdictions and nexus, parties and roles, legal and trading names, aliases and scripts, dates and places of birth or incorporation, nationalities, addresses, identifiers, ownership and control, goods or services, routes, currencies, banks, vessels or aircraft, screening tool and settings, prior alerts, licences, and escalation procedure.
Screening and documentation method
- Map sanctions jurisdiction from incorporation, nationality, location, conduct, persons, goods, technology, transport, currency, payment chain, and contractual commitments. Include UN measures only through the relevant domestic or regional implementation unless the decision-maker is directly bound otherwise.
- Identify the current official lists, regime instruments, sectoral or activity- based restrictions, ownership and control rules, general licences, exceptions, reporting duties, and regulator guidance applicable at the screening time.
- Preserve list provider, list names, official source, publication or retrieval timestamp, version or delta, dataset format, tool version, matching configuration, transliteration, thresholds, and any source outage or fallback.
- Record the exact subject data screened and its provenance. Expand known aliases, former names, native scripts, identifiers, addresses, and connected parties; do not reduce screening to one Latin-script name.
- Review every candidate using multiple identifiers, list program and measure, aliases, dates, locations, reference numbers, and narrative data. Treat a score as triage, not proof of match or non-match.
- Analyse direct listing and current jurisdiction-specific ownership and control, including aggregation, indirect holdings, control rights, trusts, intermediaries, and entities acting for or on behalf of designated persons.
- Assess transaction restrictions beyond asset freezes: sectoral finance, trade, services, investment, export, import, shipping, aviation, circumvention, and facilitation. Verify licence or exception scope, conditions, parties, dates, and use.
- Classify the result as confirmed match, likely match, unresolved, false positive, no candidate returned, or other policy category. State evidence, counterevidence, reviewer, rationale, limitations, escalation, and approval.
- Follow applicable hold, reject, freeze, block, report, licence, recordkeeping, confidentiality, and no-tipping-off procedures without taking irreversible action solely from an automated alert.
- Set rescreening triggers for list changes, ownership or identity changes, new transaction facts, geographic exposure, licence expiry, and periodic review.
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.
- 9d ago First seen · 71 lines · 60 tokens per session scan A e70239b69b9c
sanctions-screening-documenter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 60 tokens to every session and 810 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.