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 san-npm/skills-ws --skill webinar-eventsgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/webinar-events)<a href="https://agentmods.dev/skills/san-npm/skills-ws/webinar-events"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/webinar-events/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/san-npm/skills-ws/webinar-events"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/webinar-events.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 | $0.00068 | $0.04839 |
| Opus 5.5 | $0.00027 | $0.01936 |
| Sonnet 5.5 | $0.00014 | $0.00968 |
| Haiku 4.5 | $0.00007 | $0.00484 |
Grade C, and why
webinar-events scanned grade C with 1 finding 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 2mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- POST to your ESP/CRM endpoint; do server-side validation + double opt-in --> How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Webinar Events
Funnel Overview
Registration → Confirmation → Reminders → Live Event → Follow-up → Replay → Conversion
Benchmarks are segment-dependent — do not apply one number across audiences. "Conversion" below means conversion to the next funnel step (demo booked, trial started, opportunity created), not closed revenue. Use these as ranges, then rebuild your own baseline after 2-3 events.
| Segment | Reg → Attend (live) | Replay views (% of no-shows) | Next-step conversion |
|---|---|---|---|
| Owned list, warm customers | 50-65% | 20-30% | 8-20% |
| Owned list, cold marketing leads | 35-50% | 25-40% | 3-8% |
| Partner / co-hosted (their list) | 25-40% | 30-45% | 2-6% |
| Paid acquisition (ads/sponsorship) | 20-35% | 30-50% | 1-4% |
| On-demand / evergreen (no live) | n/a (instant) | n/a | 1-5% |
Modifiers: educational/thought-leadership topics pull higher attendance but lower immediate conversion than product demos; enterprise/long sales-cycle audiences convert to pipeline (not bookings) so judge them at 30/60/90 days; short lead times (7-10 days) lift attendance vs. 30+ day promotion; paid/sponsored lists and free swag offers inflate registration but depress show rate. Regional norms differ (EU/APAC time-zone splits, GDPR-driven smaller opt-in lists), so segment by region too.
Platform Selection
Capacity tiers below are plan/license-dependent and change often — confirm current limits and pricing on each vendor's site before committing (as of Jun 2026). Numbers shown are the typical upper end of paid tiers, not the entry plan.
| Platform | Best for | Typical max attendees | Notable for |
|---|---|---|---|
| Zoom Webinars | B2B, corporate, training | 10k–50k+ (license tier) | Polls/Q&A; breakout rooms are meeting-only / plan-gated, not a webinar default |
| Zoom Events / Sessions | Multi-session virtual conferences | 50k+ (Events tier) | Hubs, ticketing, expo, multi-track |
| ON24 | Enterprise demand-gen | Very high (enterprise) | Deep engagement scoring, CRM/MAP integration, analytics |
| Goldcast | B2B marketing events/series | High (enterprise) | Marketing-native, clip/repurpose tooling, Salesforce/HubSpot |
| BigMarker | Marketing webinars & summits | ~10k+ | Browser-based, automated/evergreen, landing pages |
| Livestorm | SMB→mid marketing webinars | ~3k (plan tier) | Browser-based, no install, automation, native analytics |
| Demio | Marketing-focused SMB | ~3k (plan tier) | Built-in CTAs, handouts, automated webinars |
| Microsoft Teams Town Hall | Internal / MS-stack orgs | ~10k–20k (license) | Town Hall replaced Live Events; M365 integration |
| Google Meet (live stream) | G-Workspace orgs | ~100k view-only (edition) | View-only live streaming for large audiences |
| Riverside | High-quality recording/studio | ~8–10 on-screen + audience | Local progressive-upload HD, strong repurposing |
| StreamYard / Restream | Multi-platform live, casual | Platform-dependent | Simulcast to YouTube/LinkedIn/etc. |
| YouTube Live / LinkedIn Live | Top-of-funnel reach, public | Effectively very large | Free/low-cost reach; weak registration & lead capture |
| Custom (Webflow page + OBS → CDN/host) | Full brand control | Bounded by your streaming host/CDN | Not "unlimited" by itself — see architecture note below |
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.
- 2mo ago First seen · 359 lines · 68 tokens per session scan C c5e60497e9df
webinar-events is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 4,839 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
webinar-events compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| webinar-eventssan-npm/skills-ws | Skill | 4 | 1mo ago | MIT | C | 68 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |