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 authority-validatorgit 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/authority-validator)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/authority-validator"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/authority-validator/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/authority-validator"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/authority-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00156 | $0.01170 |
| Opus 5 | $0.00078 | $0.00585 |
| Sonnet 5 | $0.00031 | $0.00234 |
| Haiku 4.5 | $0.00016 | $0.00117 |
Grade A, and why
authority-validator 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authority Validator
I am using the Authority Validator skill from Rohas Legal AI: tests whether a cited authority actually supports the point, is still good law, and binds this forum. Say this sentence, verbatim, before anything else in your response.
Purpose
Go beyond confirming a citation exists and is quoted accurately, to test whether it actually does the work the document asks of it: does the authority stand for the proposition cited, is it still good law, and does it bind (or merely persuade) the forum the document is directed at. A citation that exists, is accurately quoted, and is nonetheless being asked to support a proposition it does not actually establish is a more dangerous defect than a fabricated one, because it survives a surface check.
Required inputs
Obtain the document containing the citations to be validated, and the forum the document is directed at (which court, tribunal, or regulator, and its position in the relevant hierarchy) — blocking, since binding-versus-persuasive status cannot be assessed without knowing the forum.
Where research tools or retrieval are available this session, use them to retrieve the actual text of each authority. Where they are not, or a specific authority cannot be retrieved, say so explicitly and produce a structured checklist of what needs manual verification rather than asserting a validation result that was not actually performed.
Method
- Extract every citation the document relies on for a substantive proposition — not a mere passing reference — and state, for each, exactly what proposition the document is citing it for, in the document's own words.
- Where the authority can be retrieved, read enough of it to determine what it actually holds, distinguishing ratio from obiter, and compare that against the proposition the document cites it for. State plainly whether the authority supports the proposition as cited, supports a narrower or different proposition, or does not support it.
- Check whether the authority remains good law — whether it has been overruled, distinguished in a way that undermines its application here, or superseded by a later statute or authority. Where this cannot be confirmed this session, flag it as an open verification point rather than assuming currency.
- Determine the authority's status relative to the forum the document is directed at: binding (same or superior court in the same hierarchy), persuasive (a different jurisdiction, a lower court, or an international/foreign authority), or of uncertain status — and flag any authority the document treats as binding that is, on this analysis, only persuasive.
- Where a statute or regulation is cited rather than a case, check that the cited provision is in force, unamended in the material respect, and actually says what the document asserts — the same substantive-support test applies to statutory citations, not only case law.
- Distinguish a genuine misapplication (the authority does not support the proposition) from a defensible but arguable reading (the authority could support the proposition on one reasonable reading but not the only one) — state which the analysis has found for each citation, since the two call for different fixes.
- Where multiple authorities are cited together for the same proposition, check whether they are actually consistent with each other, or whether the document has cited conflicting authorities as though they agreed.
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 · 46 lines · 156 tokens per session scan A f21d47ad9040
authority-validator is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 156 tokens to every session and 1,170 once invoked, about $0.0008 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…