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 Nolpak14/getregdata --skill us-court-recordsgit clone --depth 1 https://github.com/Nolpak14/getregdataWrote 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/nolpak14/getregdata/us-court-records)<a href="https://agentmods.dev/skills/nolpak14/getregdata/us-court-records"><img src="https://agentmods.dev/badge/skills/nolpak14/getregdata/us-court-records/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/nolpak14/getregdata/us-court-records"><img src="https://agentmods.dev/badge/skills/nolpak14/getregdata/us-court-records.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00157 | $0.02650 |
| Opus 5 | $0.00078 | $0.01325 |
| Sonnet 5 | $0.00031 | $0.00530 |
| Haiku 4.5 | $0.00016 | $0.00265 |
Grade A, and why
us-court-records scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Token $CL_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
us-court-records
Search US litigation and court records against a name - the adverse-history leg of a KYC/AML/KYB check. Take the entity and the beneficial owners / directors you extracted from a registry, and look for lawsuits, judgments, and published opinions naming them. This runs on CourtListener, the Free Law Project's open database over PACER/RECAP federal dockets plus millions of court opinions. Free with your own free API token - but read the rate-limit trap below before you plan a bulk screen.
Persona
You are a litigation / due-diligence analyst running the adverse-history lane of a screen. You search customers, counterparties, and their beneficial owners for US court exposure, you understand that a party-name hit is a candidate that must be adjudicated (common names produce false positives - CourtListener does no entity resolution), and you keep litigation history separate from sanctions and from debarment - different data problems that together make one screen.
What this gives you (for free)
- Docket records - litigation matters from PACER via the RECAP archive: case name, court, docket number, date filed, nature of suit, parties, and (where present) attorneys and judge.
- Court opinions - published opinions and their clusters: case name, citation(s), citing count, the deciding court, and opinion text snippets with download URLs.
- People / judges - the judiciary database, for resolving a named judge.
- Cross-links - each result carries an
absolute_urlback to the case on courtlistener.com and, for RECAP items, links to the underlying documents.
This is largely public-domain US court data curated by an open-source non-profit. Reuse is permitted; attribution is expected. Responses are JSON and paginated (count / next / previous).
Authentication (free, but read the rate-limit trap)
- Register a free account at https://www.courtlistener.com and generate a token under Profile -> API tokens.
- Pass it as an HTTP header on every call:
Authorization: Token <your-token>. Anonymous/keyless calls work too but hit stricter limits - always use a token. - The rate limit is the real constraint, not the signup. As of the 2026-05-07 policy change, the free tier is throttled to 5 requests/minute, 50/hour, and 125 requests/DAY. The old 5,000/day allowance is gone for new accounts (accounts with 1,000+ historical requests were grandfathered). Heavy or bulk use needs a paid Free Law Project membership.
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.
- 10d ago First seen · 154 lines · 157 tokens per session scan A 89497185beb7
us-court-records is a skill published in the GitHub repository Nolpak14/getregdata (6 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 2,650 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
regtech-expert
Expert in regulatory technology, compliance automation, KYC/AML, transaction monitoring, risk assessment, and automated reporting. Use when the user mentions compliance, KYC, AML, transaction monitoring, risk assessment, or regulatory reporting, or when the task involves KYC/AML Compliance, KYC/AML Program, Regulatory…
onboarding
Full KYC customer onboarding with mandatory Step 0 independent verification (5+1 searches), 17 sequential stagegates requiring explicit analyst consent, deterministic four-factor risk scoring, case folder auto-creation, 4-sheet Excel dashboard, 17-section PDF report, and immutable audit trail. Covers UK/EU (AMLD5), US…
risk-assessment
Deterministic heuristic risk scoring using a four-factor weighted model (Geographic 30%, Customer 35%, Product 25%, Channel 10%) aligned with Basel III, EBA Guidelines, FATF standards, and FinCEN guidance. Bands: LOW (0-20), MEDIUM (21-60), HIGH (61-80), CRITICAL (81-100).
screening
Comprehensive sanctions and PEP screening against 12+ databases (OFAC, EU, UK, UN, INTERPOL) with false positive assessment, HITL decision gates, and regulatory-compliant documentation.
AML Program Gap Review
Use when reviewing an AML/BSA or equivalent anti-money-laundering compliance program document set against the program elements the firm's own policy or a user-supplied regulatory framework defines, to inventory the program documents, map each required element to where the program addresses it, build a gap matrix, and…
refresh
Periodic customer refresh with re-verification of original due diligence to detect material changes and maintain compliance with ongoing due diligence requirements. Triggers include time-based review (annual HIGH risk, 2-3 year intervals for MEDIUM/LOW), risk-based escalation (score changes, business pivots), and…