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 sruthir28/enterprise-ai-skills --skill meeting-prep-kitgit clone --depth 1 https://github.com/sruthir28/enterprise-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/sruthir28/enterprise-ai-skills/meeting-prep-kit)<a href="https://agentmods.dev/skills/sruthir28/enterprise-ai-skills/meeting-prep-kit"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/meeting-prep-kit/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/sruthir28/enterprise-ai-skills/meeting-prep-kit"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/meeting-prep-kit.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 | $0.00092 | $0.01475 |
| Opus 5 | $0.00046 | $0.00737 |
| Sonnet 5 | $0.00018 | $0.00295 |
| Haiku 4.5 | $0.00009 | $0.00147 |
Grade A, and why
meeting-prep-kit 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Prep Kit
Personal prep tool for meetings where you are driving an outcome. Not a meeting note-taker. Not a generic agenda builder. The output is for you, the person walking into the room.
Design choices (why this skill is opinionated)
- For you, not the team. Output assumes you already know the context. No "as you know" preambles.
- Outcome-first. Every section ladders back to one thing: what you want when you walk out.
- Top 3, not all 12. Talking points capped at 3. Objections capped at 3. If you can't pick 3, you don't know your ask yet.
- Speakable, not slidable. Talking points are how you'd actually say it out loud — not bullet-point soup.
Inputs the skill needs (interview if missing)
- Who's in the room? Names + roles. Power dynamics matter.
- Meeting length (15 / 30 / 60 min)
- Topic (one sentence)
- The outcome you want. Specific. "Get Sarah to approve $50K budget" — not "discuss budget."
- What they care about (their KPIs, recent context, stated priorities)
- What you have (data, alternatives, asks already discussed offline)
If any of these are missing, ask before drafting. Vague inputs = generic output.
Output format
Pre-read (3 bullets, ≤30 words each)
The minimum context anyone in the room needs before you open your mouth. Three things, no more.
Time-boxed agenda
| Time | Section | Owner |
|---|---|---|
| 0:00 | What this is + the outcome we need | You |
| 0:03 | Context (data, ≤2 min) | You |
| ... | ... | ... |
| Final 5 min | Decision + next steps | You |
Total adds up to meeting length. Decision time is always reserved at the end.
Your talking points (top 3, in order)
- Lead with the strongest — the one fact or framing they can't argue with.
- Address the elephant — name the obvious objection yourself, before they do.
- Make the ask — the one specific yes/no thing you want.
Each in plain spoken language. No corporate-speak, no buzzwords.
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 · 134 lines · 92 tokens per session scan A 7dfaa0494963
meeting-prep-kit is a skill published in the GitHub repository sruthir28/enterprise-ai-skills (139 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 1,475 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 2026-08-30.
Other skills, from other repositories
notes
Create and manage text notes in the workspace.
file-search
Find files and search content across directories.
tmux
Manage tmux terminal sessions.
library
A skill for managing WorkBuddy’s built-in library, which stores online documents, web links, data tables, dashboards, web pages, files, and shared spaces. It also supports publishing, collaboration, and file transfers.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.