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 agentmods add skills/protomated/protomated-plugins-official/meeting-prepnpx skills add protomated/protomated-plugins-official --skill meeting-prepgit clone --depth 1 https://github.com/protomated/protomated-plugins-officialWrote 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/protomated/protomated-plugins-official/meeting-prep)<a href="https://agentmods.dev/skills/protomated/protomated-plugins-official/meeting-prep"><img src="https://agentmods.dev/badge/skills/protomated/protomated-plugins-official/meeting-prep.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00055 | $0.01751 |
| Opus 5 | $0.00028 | $0.00875 |
| Sonnet 5 | $0.00011 | $0.00350 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
meeting-prep 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 6d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/meeting-prep — Meeting Prep Brief Generator
⚠️ AI-ASSISTED DRAFT — ATTORNEY REVIEW REQUIRED This output was generated by an AI assistant. It has not been reviewed by a licensed attorney. Verify all facts and dates before relying on this brief. This is not legal advice.
Generate a one-page pre-meeting brief by pulling context from local matter files and recent email. Designed to be scanned in two minutes before you walk into the room.
Invocation
/meeting-prep [matter folder path]
/meeting-prep [client name and meeting description]
Workflow
Step 1 — Identify the meeting
Ask or infer from the argument:
- Who is the meeting with? (client, opposing counsel, mediator, judge, deponent)
- What type of meeting? (client check-in, deposition, mediation, settlement conference, court hearing, intake)
- When? (date and time)
- Where / what format? (in-person, phone, video)
If not provided, ask before proceeding.
Step 2 — Read the matter folder
Use the Filesystem connector to locate the matter folder. Read:
intake-summary.md— parties, facts, claims, key deadlines (primary source)- Recent notes or hearing summaries
- Any documents relevant to today's meeting (depo outline, mediation statement, motion)
- Prior meeting notes (look for files named
meeting-*ornotes-*)
Step 3 — Scan recent Gmail for context
Use the Gmail connector to scan recent emails for this matter:
- Search:
[client name] OR [matter keywords](last 14 days) - Look for: recent correspondence with opposing counsel, any new developments, client questions pending, court or opposing counsel communications
Note any items that have come up since the last substantive communication.
Step 4 — Identify meeting type and tailor the brief
Generate the appropriate brief format based on meeting type:
Client Meeting Brief
# Client Meeting Brief — [Client Name]
**Date:** [Date] | **Time:** [Time] | **Format:** [In-person / Phone / Video]
**Prepared:** [Today's date] — AI-assisted, attorney review required
---
## Matter Status in One Sentence
[Where the case stands right now in plain language]
## Since We Last Spoke
[Key developments since the last client communication — filings, offers, court dates, opposing counsel activity]
## Today's Agenda (suggested)
1. [Primary topic — what the client needs to hear or decide]
2. [Secondary topic]
3. [Open items / pending client actions]
## Decisions Needed from Client
- [Any decision the client must make — settlement authority, document production consent, etc.]
## Action Items Pending from Client
- [List any documents, information, or responses the client still owes]
## Things NOT to Discuss
[Any topics that should be avoided — pending privileged work, items under negotiation, anything the client asked to be handled carefully]
## Key Facts to Have Ready
- Incident date: [date]
- Statute of limitations: [date]
- Next court date / deadline: [date and description]
## Open Questions
- [Anything you need to ask or confirm during the meeting]
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.
- 6d ago First seen · 254 lines · 55 tokens per session scan A a27a4c0f7cc3
meeting-prep is a skill published in the GitHub repository protomated/protomated-plugins-official (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,751 once invoked, about $0.0003 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 2026-08-31.
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
Generate guided Chinese software copyright application materials from a real project. Use this skill when the user asks for 软件著作权, 软著申请资料, 软著代码材料, 操作手册, 申请表信息, or wants Word/TXT materials for software copyright registration. The workflow analyzes the imported project, extracts real source code, creates Markdown drafts…
iflytek-contract-intelligence-review
Use when user asks to review contracts, detect contract risks, or perform compliance checks. 合同智能审核 - 对合同扫描件、图片合同、双语合同进行完整审核。 覆盖 OCR 识别、条款分析、风险检测、合规校对、翻译摘要全流程。 适用于法务审核、采购合同审查、供应链合规检查等场景。 关键词:合同审核、风险检测、条款分析、合规校对、contract review、risk detection。.
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…