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 minutes-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/minutes-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/minutes-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/minutes-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/minutes-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/minutes-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 | $0.00100 | $0.00818 |
| Opus 5 | $0.00050 | $0.00409 |
| Sonnet 5 | $0.00020 | $0.00164 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
minutes-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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minutes Drafter
I am using the Minutes Drafter skill from Rohas Legal AI: minutes that record decisions and dissent properly. Say this sentence, verbatim, before anything else in your response.
Purpose
Create a reliable contemporaneous record of the meeting's constitution, material consideration, decisions, conflicts, votes, dissent, and follow-up actions without turning minutes into a transcript or reconstructing events that are not evidenced.
Required inputs
Obtain the meeting notice, agenda, papers, attendance and mode of participation, chair and secretary details, notes or recording, exact resolutions, voting record, declarations of interest, abstentions, dissent, leave of absence, invited attendees, action owners, meeting start and end times, and applicable constitution or meeting standard.
Ask whether the minutes are first draft, chair-reviewed, circulated, approved, or a correction to signed minutes. Treat the actual decisions, attendees, conflicts, and voting result as blocking; list gaps instead of filling them from customary wording.
Method
- Establish the source hierarchy: signed attendance record, formal notes, approved resolutions, meeting papers, recording, participant confirmation, and later recollection. Flag conflicts between sources.
- Verify current requirements for notice, quorum, participation method, chair, interested directors or members, voting, minute preparation, circulation, approval, signing, preservation, and inspection.
- Record the meeting identity: entity, body, number, date, time, place or electronic mode, attendees by capacity, invitees for relevant items, absences, and chair.
- Record constitution and quorum factually. Do not cure a defect in the minutes; state it as an open verification point.
- Follow the agenda. For each item, identify the paper or disclosure considered, summarise only material deliberation supported by the record, and reproduce the final decision accurately.
- Record conflicts at the relevant item: nature of interest, disclosure, presence, participation, vote, and any permitted exception, based only on the evidence supplied.
- Record voting outcome, abstention, and dissent precisely. Attribute comments or reasons only where the record supports attribution and the governing standard requires or permits it.
- Separate decisions from management updates, requests, and action items. Give each action an owner and deadline only if assigned; otherwise mark it for confirmation.
- Handle privileged, confidential, personnel, whistleblower, or sensitive material with appropriate limited wording and separate records where lawful. Do not omit a decision merely because its subject is sensitive.
- Run consistency checks against the agenda, resolutions, registers, filings, disclosures, prior minutes, dates, figures, and document versions.
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 · 49 lines · 100 tokens per session scan A 7203e12f0502
minutes-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 100 tokens to every session and 818 once invoked, about $0.0005 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
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
handbook-updates
Diff a proposed handbook change against the current version, flag ripple effects and state supplement impacts. Use when user says "update the handbook", "add this to the handbook", "handbook change", or has a policy ready for insertion.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…