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 regulatory-change-monitorgit 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/regulatory-change-monitor)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/regulatory-change-monitor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/regulatory-change-monitor/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/regulatory-change-monitor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/regulatory-change-monitor.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 | $0.00056 | $0.00709 |
| Opus 5 | $0.00028 | $0.00354 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
regulatory-change-monitor 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regulatory Change Monitor
I am using the Regulatory Change Monitor skill from Rohas Legal AI: controlled baselines, official-source changes, legal-effect timelines and implementation impact. Say this sentence, verbatim, before anything else in your response.
Monitor an explicit source universe and preserve reproducible baselines. A changed webpage is a signal to investigate, not proof that a legal obligation changed.
Monitoring specification
Record the jurisdictions, topics, entities and activities in scope; official gazettes, journals, legislative databases, regulator pages, registers, feeds, notices, and licence communications; source URLs or identifiers; cadence; languages; baseline date; materiality rules; owners; distribution; and escalation deadlines.
Monitoring method
- Create a source register with issuing body, authority level, document family, identifier, publication channel, expected cadence, access method, and fallback.
- Capture a baseline with retrieval timestamp, title, version, date, status, effective and application dates, stable URL, and hash or equivalent evidence.
- Retrieve from official sources and preserve the observed version. If a source is unavailable, changed structurally, blocked, or stale, log the failure and use a designated official fallback without silently treating "not found" as no change.
- Detect additions, removals, amendments, corrections, replacements, withdrawals, status changes, deadline changes, and altered annexures or forms. Ignore cosmetic noise only under a documented rule.
- Classify each item as proposal, consultation, adopted act, publication, commencement, applicability, transition, guidance, FAQ, licence communication, enforcement, or judicial development. Preserve the distinction between them.
- Verify the legal effect through the enabling instrument and official publication. Record adoption, publication, entry into force, application, transition, sunset, territorial reach, affected persons, and any dependency on further measures.
- Map the delta to obligations, products, customers, policies, controls, contracts, disclosures, filings, systems, data, vendors, training, assurance, and governance.
- Assign impact, confidence, urgency, accountable owner, decision point, action, dependency, evidence, and due date. Escalate imminent or potentially prohibitive changes immediately rather than waiting for the routine report.
- Maintain a changelog linking old and new versions, source evidence, analysis, reviewer, alerts sent, acknowledgements, decisions, actions, and closure proof.
- If recurring execution is requested, use the available scheduling mechanism only after confirming scope, cadence, notification route, access, and failure handling.
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 · 63 lines · 56 tokens per session scan A b1eb360d0ac7
regulatory-change-monitor is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 56 tokens to every session and 709 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
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…