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 First-Touch-Inc/firsttouch-agent-skill-packs --skill website-visitor-followupgit clone --depth 1 https://github.com/First-Touch-Inc/firsttouch-agent-skill-packsWrote 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/first-touch-inc/firsttouch-agent-skill-packs/website-visitor-followup)<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/website-visitor-followup"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/website-visitor-followup/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/first-touch-inc/firsttouch-agent-skill-packs/website-visitor-followup"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/website-visitor-followup.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 | $0.00082 | $0.01318 |
| Opus 5 | $0.00041 | $0.00659 |
| Sonnet 5 | $0.00016 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
website-visitor-followup 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Visitor Follow-Up
No-source note: If the workspace has no HubSpot tracking, RB2B/list source, or visitor export, skip this play and use this pack's persona AI SDR play instead.
Solo/default path: a single owner can run this from an approved visitor/source list and approve every touch themselves. If you later run it with a team, add owner-based routing, per-seat cap sharing, approval review, and FirstTouch/HubSpot logging checks.
Outcome: Convert high-intent website visits into social touches while the account is actively researching.
First-run onboarding gate
Before running this skill for the first time in a workspace, load ../../references/onboarding.md and complete the onboarding questions. Do not proceed until you know: LinkedIn account type (free/basic = no connection notes; recommend 10 connection requests/day and never exceed the FirstTouch max of 20/day; Sales Navigator/Premium = connection notes available; recommend 20 connection requests/day and never exceed the FirstTouch max of 30/day), HubSpot access (MCP, service key/private app token, HubSpot list only, or none), and which play the user wants to run. Recommend high-intent plays before outbound to keep the LinkedIn account healthy. If HubSpot is unavailable, do not run HubSpot-specific steps unless the user provides a HubSpot list FirstTouch can access.
When to use
- a de-anon tool identifies a target account/contact on key pages
- HubSpot website activity shows pricing / demo / product-page interest
- the user says "work website visitors"
Inputs
- signal source: HubSpot's native website tracking (default) OR a de-anon platform like RB2B (recommended if native HubSpot web-visit volume is too low to be useful)
- page threshold: which pages count (pricing, demo, product, integrations, etc.)
- identity confidence: known contact vs likely account only
Step-by-step
Before drafting or queueing any contact, run Gate 0 suppression/DNC from ../../references/safety-governance.md. Suppressed, unsubscribed, opted-out, or do-not-contact records are skipped and logged.
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.
- 11d ago First seen · 97 lines · 82 tokens per session scan A 47fb1669fbf3
website-visitor-followup is a skill published in the GitHub repository First-Touch-Inc/firsttouch-agent-skill-packs (5 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,318 once invoked, about $0.0004 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
linkedin-mcp
Use LinkedIn data for profile, company, job, post, feed, inbox, recruiting, and outreach work through the bundled LinkedIn MCP server. Use only for an explicit LinkedIn request.
social-carousel
A three-card social media carousel where one headline continues across three square images. The cards can include a brand mark, numbering, a visual focus, and a call to action.
linkedin-content
Use when writing the actual words of one LinkedIn feed post — turning a raw idea, story or asset into ready-to-paste copy: a text post, a document/carousel cover with slide copy and caption, or a short native-video script. Covers fixing a weak hook, reformatting a wall of text for the mobile feed, and a CTA that…
sdr-humanizer
Transform AI-generated sales messages into natural, human-like conversations that build trust and rapport.
gr-social-distill
A content-repurposing workflow that turns one published blog post into several social-media formats, including an X thread, a Xiaohongshu post, a LinkedIn carousel, and a dev.to or Zenn article.
supermemory
Semantic memory layer powered by vector search. Store, recall, and connect conversation insights across all customer interactions.