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 mardab96/b2b-lead-generation-claude-skills --skill meeting-prep-five-minutesgit clone --depth 1 https://github.com/mardab96/b2b-lead-generation-claude-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/mardab96/b2b-lead-generation-claude-skills/meeting-prep-five-minutes)<a href="https://agentmods.dev/skills/mardab96/b2b-lead-generation-claude-skills/meeting-prep-five-minutes"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/meeting-prep-five-minutes/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/mardab96/b2b-lead-generation-claude-skills/meeting-prep-five-minutes"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/meeting-prep-five-minutes.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.00967 |
| Opus 5 | $0.00031 | $0.00483 |
| Sonnet 5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
meeting-prep-five-minutes 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Prep in Five Minutes
Use this skill when
There is a call soon and nobody has read anything about the company.
You have twenty minutes before a call. The goal is to walk in knowing three things you did not know, rather than forty you will not remember.
The output is deliberately short. A brief nobody reads before the call is worth less than no brief, because it also consumed the prep time.
Required input
- Company name and website.
- Who is on the call, and their roles.
- Whether this is a first call, a follow-up, or a late-stage conversation. The brief is different for each.
- What you sell.
Useful if it exists, skipped without complaint if not:
- previous emails or notes with this account
- how they arrived: inbound, outbound, referral, event
- which competitor they are likely using
- your typical deal size and the size this one looks like
Analysis workflow
- Establish the basics fast: what they sell, roughly how big, who they sell to. Two minutes, not twenty.
- Work out who is actually in the room. A founder, a head of department and a procurement lead each want a different conversation, and preparing for the wrong one is worse than preparing for none.
- Find at most three specifics worth mentioning. More than three will not survive the first five minutes of an actual conversation.
- Write the questions you cannot answer from research. The point of the call is what the website does not say, so a brief that answers everything has prepared the wrong things.
- Name the likely objection for this profile, and the honest response to it.
- Write the disqualifiers explicitly, then decide what a good outcome is. Not "a great conversation", a specific next step.
Decision rules
- Three facts maximum. This is a hard limit, not a guideline.
- Questions beat statements in the brief. If the brief is mostly things to say, it is a pitch script and the call will feel like one.
- If the research contradicts what the CRM says about this account, flag the contradiction rather than smoothing it over.
- If this is a follow-up call, the previous conversation outranks anything found online.
- If nothing meaningful can be found, say so and lean the brief entirely on questions. That is a normal outcome for small and private companies.
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 · 96 lines · 0 tokens per session scan A 9b13bddbd216
meeting-prep-five-minutes is a skill published in the GitHub repository mardab96/b2b-lead-generation-claude-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 967 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…