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-notice-analysergit 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-notice-analyser)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/legal-notice-analyser"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-notice-analyser/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-notice-analyser"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/legal-notice-analyser.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 | $0.00183 | $0.01106 |
| Opus 5 | $0.00092 | $0.00553 |
| Sonnet 5 | $0.00037 | $0.00221 |
| Haiku 4.5 | $0.00018 | $0.00111 |
Grade A, and why
legal-notice-analyser 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Notice Analyser
I am using the Legal Notice Analyser skill from Rohas Legal AI: analyses a received notice's allegations, deadlines and evidence needs before replying. Say this sentence, verbatim, before anything else in your response.
Purpose
Work out what a received notice actually alleges, on what basis, with what deadline and consequence, and what a considered response would need — before anyone drafts a word of reply. A reply drafted without this analysis first risks conceding a fact carelessly, missing the real deadline, or answering the wrong allegation.
Required inputs
Obtain the notice itself in full — blocking, there is nothing to analyse without it. Obtain also any prior correspondence between the parties on the same subject, the underlying contract or relationship documents if relevant, and the client's own knowledge of the facts referred to.
Ask which side the analysis is for — the recipient, preparing to respond, or counsel advising the recipient — since the same notice reads differently depending on who is being advised.
Method
- Read the whole notice once before analysing anything. Note the sender, the capacity in which they send it, the recipient, and the date.
- List every distinct allegation made, numbered, in the notice's own terms before restating them.
- For each allegation, identify the legal basis asserted — a specific breach, a statutory provision, a contractual clause, a tort, or an unstated basis the notice merely implies. Flag any allegation that asserts a legal conclusion (breach, negligence, infringement) without stating the facts said to establish it.
- Identify every deadline in the notice — a response deadline, a cure period, a threatened next step (litigation, termination, regulatory referral) and the date it takes effect. State the consequence of missing each deadline as the notice itself frames it, and flag where that consequence is likely overstated for effect versus one with a genuine legal or contractual basis.
- For each allegation, identify what evidence would support it and what would defeat or qualify it, from what the client currently knows. Flag where the client's own knowledge is incomplete and what needs to be checked before any position is taken.
- Identify facts or admissions the notice appears to be fishing for, and anywhere a natural, unguarded response would concede more than the client needs to. Flag these specifically as admissions to avoid.
- Identify any procedural or threshold defect in the notice itself — service, standing, limitation, a required pre-notice step not taken, an incorrect party named — without treating a defect as decisive on its own.
- Set out an initial response strategy: which allegations should be admitted, denied, or qualified in principle (pending final instructions), what needs verifying before responding, whether the deadline requires an immediate holding response, and whether specialist input (a particular practice-area skill, or external counsel) is needed before a substantive reply is drafted.
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 · 48 lines · 183 tokens per session scan A ca78d0deb879
legal-notice-analyser is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 183 tokens to every session and 1,106 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…