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 adr-brief-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/adr-brief-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/adr-brief-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/adr-brief-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/adr-brief-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/adr-brief-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 | $0.00188 | $0.01792 |
| Opus 5 | $0.00094 | $0.00896 |
| Sonnet 5 | $0.00038 | $0.00358 |
| Haiku 4.5 | $0.00019 | $0.00179 |
Grade A, and why
adr-brief-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 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Brief Drafter
I am using the ADR Brief Drafter skill from Rohas Legal AI: brief putting a party's position to a mediator or conciliator, adapted to the process and to whether it's shared or confidential. Say this sentence, verbatim, before anything else in your response.
What this does
Drafts the brief that gives a mediator or conciliator enough reliable context to work the dispute effectively. Two decisions govern everything else in the document and must both be made before drafting starts: which process this is (mediation or conciliation — the neutral's role, statutory or institutional confidentiality protections, and procedural conventions differ between them and should not be assumed interchangeable), and who will read the brief (confidential to the neutral only, or shared with the other party). Getting either wrong produces a document that either wastes its usefulness to the neutral or damages the party's position if the other side reads it.
Before you start
Which process — mediation or conciliation. Ask, and do not assume they work the same way. Where the process is governed by a specific statutory or institutional framework (for example, conciliation under Part III of India's Arbitration and Conciliation Act, 1996, or a mediation conducted under the Mediation Act, 2023 or an institution's own rules), flag its confidentiality and disclosure provisions as a verification point rather than assuming a generic default.
Whether the brief is confidential to the neutral only, or will be shared with the other party. Blocking, and the first thing to confirm after the process itself — it changes what belongs in the document more than any other instruction could. If the user is not sure which they want, say plainly that this decision has to be made before drafting starts; a brief drafted for one purpose is not safely repurposed for the other.
The facts, the party's position, and their interests. Blocking. Where a party-interest-analyst output already exists, work from it rather than re-deriving it — but note that underlying interests may only belong in a neutral-only brief, not one shared with the other side.
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 · 68 lines · 188 tokens per session scan A 210a3877e7f2
adr-brief-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 188 tokens to every session and 1,792 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 2026-08-30.
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…