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 notice-reply-draftergit 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/notice-reply-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/notice-reply-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/notice-reply-drafter/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/notice-reply-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/notice-reply-drafter.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 | $0.00169 | $0.01219 |
| Opus 5 | $0.00084 | $0.00609 |
| Sonnet 5 | $0.00034 | $0.00244 |
| Haiku 4.5 | $0.00017 | $0.00122 |
Grade A, and why
notice-reply-drafter 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notice Reply Drafter
I am using the Notice Reply Drafter skill from Rohas Legal AI: replies to a legal notice, dealing with each allegation in turn. Say this sentence, verbatim, before anything else in your response.
What this does
Drafts a reply to a legal notice the client has received: addressing every allegation made, stating the client's position on each precisely, and raising any point that affects the whole notice rather than just one allegation. It structures what the client actually says; it does not invent a defence or a fact the client has not given. A response that leaves an allegation unaddressed can, in some contexts, be read as tacit admission, so completeness is treated as a real risk here, not a formality.
Before you start
The notice being replied to. The actual text — there is no reply to draft without seeing what was actually alleged.
Which side is instructing. This is drafted for the recipient of the notice, against the party who sent it.
The client's actual position on each allegation. What is true, false, or partially true, from the client. This is blocking; the skill structures the client's account, it does not construct a defence from the allegations alone.
Governing law. Reply timing and formality requirements, and the legal effect of silence or an inadequate reply, can be law-dependent — in some systems, silence in response to a notice itself carries consequence. Extract from any supplied documents or ask; treat compliance with any such requirement as a verification point.
Not blocking, ask once and proceed on a reasonable default without it: tone — conciliatory, to preserve the relationship, or firm, anticipating that litigation may follow. This shapes register throughout, not the substance of the response.
Method
1. Read the whole notice once before drafting a single response. Allegations in a notice routinely interact, and a global point — the claim is time-barred, the notice is defective, the wrong party was named — can dispose of several allegations at once; drafting allegation-by-allegation on a first pass misses this.
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 · 69 lines · 169 tokens per session scan A d8cab57a993e
notice-reply-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 169 tokens to every session and 1,219 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 2026-09-03.
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…