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 court-order-compliance-checkergit 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/court-order-compliance-checker)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/court-order-compliance-checker"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/court-order-compliance-checker/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/court-order-compliance-checker"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/court-order-compliance-checker.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 | $0.00204 | $0.01151 |
| Opus 5 | $0.00102 | $0.00575 |
| Sonnet 5 | $0.00041 | $0.00230 |
| Haiku 4.5 | $0.00020 | $0.00115 |
Grade A, and why
court-order-compliance-checker 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Court Order Compliance Checker
I am using the Court Order Compliance Checker skill from Rohas Legal AI: turns an order into tracked obligations, deadlines and contempt-risk assessment. Say this sentence, verbatim, before anything else in your response.
Purpose
Convert an order into a working compliance record: exactly what it requires, from whom, by when, and what would count as evidence of having done it — so that compliance can actually be tracked and contempt or breach risk is caught before it becomes a problem, not after.
Required inputs
Obtain the order itself in full, including any schedule or annexure it incorporates — blocking, there is nothing to track without the actual text. Obtain also any prior orders in the same proceeding that this one varies, extends, or is made in addition to, since obligations can only be tracked correctly against the current, complete picture.
Ask who within the client's organisation or family is actually responsible for each type of obligation the order might impose (payment, disclosure, an act, a restraint), so responsibility can be assigned rather than left generic.
Method
- Read the whole order once before extracting anything. Distinguish the recitals and background from the operative directions — only the operative part creates obligations, though recitals can matter to interpreting an ambiguous direction.
- Extract every operative obligation into a structured list: what must be done or not done, by whom, by when (a specific date, a period from the order, or "forthwith" or equivalent), and any condition attached.
- Classify each obligation: a one-off act (pay a sum, deliver a document, do a specific thing by a date), a continuing restraint (do not do X until further order), or a periodic obligation (report, disclose, or pay on a recurring basis).
- For each obligation, state what would actually constitute evidence of compliance — a receipt, a filed document, a witnessed act, a compliance certificate — distinguishing genuine evidence from a bare assertion that compliance occurred.
- Identify any ambiguity in what the order actually requires — an undefined term, a direction capable of more than one reading, a deadline calculated from an uncertain trigger date — and flag it rather than resolving it unilaterally in the client's favour.
- Assess breach and contempt risk for each obligation: what happens if it is missed, whether the order itself specifies a consequence, and whether any conduct so far is already at risk of being treated as non-compliance.
- Where compliance requires a third party's cooperation (a bank, a registrar, another party), flag the dependency and the risk if that cooperation is not forthcoming — the client's obligation to comply does not usually excuse itself merely because a third party is slow, so this needs early attention, not late discovery.
- Build a forward tracker: every obligation not yet due, its deadline, and a prompt point before the deadline by which compliance evidence should be assembled.
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 · 48 lines · 204 tokens per session scan A 5e323313d298
court-order-compliance-checker is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 204 tokens to every session and 1,151 once invoked, about $0.0010 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…