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 legal-risk-assessorgit 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/legal-risk-assessor)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/legal-risk-assessor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-risk-assessor/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/legal-risk-assessor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-risk-assessor.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 | $0.00185 | $0.01234 |
| Opus 5 | $0.00093 | $0.00617 |
| Sonnet 5 | $0.00037 | $0.00247 |
| Haiku 4.5 | $0.00018 | $0.00123 |
Grade A, and why
legal-risk-assessor 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Risk Assessor
I am using the Legal Risk Assessor skill from Rohas Legal AI: sets out the options on a decision, with the risk and likely outcome of each. Say this sentence, verbatim, before anything else in your response.
What this does
Takes a decision a client faces and sets out the realistic options, what could go wrong with each and how likely and severe that is, and the realistic best and likely case alongside the downside — organised around what the client has actually said matters to them. It supports the client's decision; it does not make it. Where the analysis depends on a legal question — how likely a claim is to succeed, whether a position would hold up — it grounds that in supplied authority or flags it as needing research, rather than asserting a probability from memory.
Before you start
The decision and the options actually on the table. Stated by the user, not invented. If the options have not been clearly identified, ask the user to state what is realistically available before drafting anything — including whether "do nothing" or maintaining the status quo is genuinely one of them, since it is often implicitly excluded without being ruled out on the merits.
What matters to the client. Cost, time, certainty, reputation, preserving the relationship, precedent for future disputes — whichever mix actually applies. This is blocking: risk is not one-dimensional, and the same option can be low financial risk and high reputational risk at once. Which matters more is the client's call, not an assumption to make on their behalf.
Not blocking, ask once and proceed on what is available: governing law, where part of the analysis turns on a legal question (likelihood of success on a claim, enforceability of a position). Extract or ask; ground any such point in supplied authority or documents, or flag it as requiring research rather than stating a probability from memory.
Method
1. State the decision and the realistic options precisely, including the status quo or "do nothing" option where it genuinely applies. Do not silently narrow the option set to the ones that seem obviously reasonable.
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 · 65 lines · 185 tokens per session scan A 614e33df5fbc
legal-risk-assessor is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 185 tokens to every session and 1,234 once invoked, about $0.0009 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…